JP2020154842A - Information processing equipment, information processing methods and information processing programs - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing device, an information processing method and an information processing program for predicting a full vacancy state of a parking place with high accuracy at an estimated time of arrival at a parking place installed on a road. An information processing device 100 has a storage unit 134 and a prediction unit 135. The storage unit stores full vacancy information indicating the full vacancy status of the parking places installed on the road for each parking place. Based on the fullness information accumulated by the storage unit, the prediction unit predicts the fullness status of the parking place at the estimated arrival time when the moving object to be processed arrives at the parking place. [Selection diagram] FIG. 9

Description

Embodiments of the present invention relate to information processing devices, information processing methods and information processing programs.

Conventionally, a technique for accurately predicting the congestion status of an estimated arrival time has been known. For example, a technique for providing full availability information at an estimated time of arrival at a parking lot is known.

Japanese Unexamined Patent Publication No. 2009-211253

However, according to the above-mentioned prior art, it is possible to accurately predict the fullness of a parking lot at an estimated time of arrival at a parking lot installed on a road, such as a parking meter-type parking lot. Not exclusively. For example, since the above-mentioned conventional technique targets a general parking lot with a limited number of warehousing units, parking at the estimated arrival time based on the statistical information of the number of warehousing units and staying time for each time zone. By calculating the number of vehicles and the number that can be accommodated and comparing them, it is predicted whether or not the parking lot is full at the estimated arrival time.

On the other hand, parking lots installed on roads, such as parking meter-type parking lots, do not have the concept of the number of cars that can be accommodated as shown in the above-mentioned conventional technology, and are compared with general parking lots. And the usage situation is also different. For this reason, the above-mentioned prior art cannot always predict the fullness of the parking place at the estimated time of arrival at the parking place installed on the road with high accuracy.

The information processing device according to the present application is based on a storage unit that stores full vacancy information indicating the vacancy status of a parking place installed on a road for each parking place and the vacancy information accumulated by the storage unit. It is characterized by having a prediction unit that predicts the fullness status of the parking place at the estimated arrival time when the moving body to be processed arrives at the parking place.

According to one aspect of the embodiment, there is an effect that the fullness status of the parking place at the estimated time of arrival at the parking place installed on the road can be predicted with high accuracy.

FIG. 1 is a diagram showing an example of the first information processing according to the embodiment. FIG. 2 is a diagram showing an example of a full-empty information storage unit according to the embodiment. FIG. 3 is a diagram showing an example (1) of the statistical information storage unit according to the embodiment. FIG. 4 is a diagram showing an example (2) of the statistical information storage unit according to the embodiment. FIG. 5 shows an example of information notification according to the embodiment. FIG. 6 is a diagram showing a configuration example of the information processing system according to the embodiment. FIG. 7 is a diagram showing an example of the second information processing according to the embodiment. FIG. 8 is a diagram showing an example of notifying the determination result in the full / empty determination. FIG. 9 is a diagram showing a configuration example of the information processing device according to the embodiment. FIG. 10 is a diagram showing an example of an imaging data storage unit according to an embodiment. FIG. 11 is a diagram showing an example of the parking place information storage unit according to the embodiment. FIG. 12 is a diagram showing another example of information notification. FIG. 13 is a flowchart showing a processing procedure of the first information processing according to the embodiment. FIG. 14 is a flowchart showing a processing procedure of the second information processing according to the embodiment. FIG. 15 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device.

Hereinafter, an information processing apparatus, an information processing method, and a mode for carrying out an information processing program (hereinafter, referred to as “the embodiment”) according to the present application will be described with reference to the drawings. Note that this embodiment does not limit the information processing apparatus, information processing method, and information processing program according to the present application. Further, in the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. An example of the first information processing]
First, an example of the first information processing among the information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of the first information processing according to the embodiment. The first information processing according to the embodiment is performed by the information processing apparatus 100 shown in FIG.

Prior to the description of FIG. 1, the information processing system according to the embodiment will be described with reference to FIG. FIG. 6 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. As shown in FIG. 6, the information processing system 1 according to the embodiment includes an imaging means K, a dorareco device 10, and an information processing device 100. The image pickup means K, the dorareco device 10, and the information processing device 100 are connected to each other via a network N so as to be able to communicate by wire or wirelessly. The information processing system 1 shown in FIG. 6 may include a plurality of imaging means K, a plurality of dra-recording devices 10, and a plurality of information processing devices 100.

Here, the parking place targeted in the present application will be described. The parking lot targeted in the present application is a parking lot installed on the road such as a parking lot for a parking meter (which can be paraphrased as an incidental parking lot attached to the road).

Further, as shown in the image pickup data VG10 of FIG. 1, the parking lot installed on such a road is a parking lot that normally exists for each parking meter, and is a parking lot for parking one vehicle. It is composed of (parking spaces) in a specific area in each area as an aggregate in which (parking space) is connected in one direction (direction of the road). Therefore, in the following embodiment, for example, when it is described as a parking place installed on a road or simply a parking place, the parking place is one aggregate as described above and one parking lot. Both shall be indicated. In addition, when it is necessary to distinguish between them, the terms "aggregate" and "parking area" will be used as appropriate.

In addition, since the parking lots installed on the road are aggregates as described above, they are geographically wider than general parking lots (including coin parking lots) attached to facilities, etc. There is. This is clear from the state of the parking place shown in the imaging data VG10 of FIG. For this reason, there arises a problem that even one aggregate is very far from the destination depending on the parking lot to be used.

The imaging means K is various cameras (for example, security cameras) installed in any facility (for example, utility poles, signals, pedestrian crossings, stores, condominiums, etc.). Further, since the dashcam (drive recorder) device 10 described later also has an imaging means, the dashcam device 10 can be said to be a kind of the imaging means K. For example, if the imaging means K is a security camera, the imaging means K continues to image, for example, an object (for example, a road, a vehicle, or another person) included in the imaging range. Then, for example, the image pickup means K processes the image pickup data obtained by continuous imaging within the predetermined period every predetermined period (for example, one hour, one day, one week, etc.) with the information processing apparatus 100. Send to. As a result, the information processing device 100 can acquire the imaging data from the imaging means K.

The dorareco device 10 is a terminal device (information processing device) related to a drive recorder, and is an information processing device used by a driver (user) of a vehicle (an example of a moving body). It is assumed that the dashcam device 10 according to the embodiment is a terminal device for a car navigation system (car navigation) having a built-in drive recorder. In other words, the dorareco device 10 is an information processing device in which a drive recorder and a terminal device for a car navigation system are integrated. However, in the dashcam device 10, the drive recorder and the terminal device for the car navigation system may be separated and connected to each other externally, or only the drive recorder may be pointed out. In the following, the car navigation service provided in this embodiment will be referred to as "car navigation Z".

Further, the dorareco device 10 has a camera (an example of the imaging means K) that images the outside of the vehicle, and a display screen D that displays the imaging data obtained by imaging by the camera. In addition, route guidance information by the car navigation system is also displayed on the display screen D. Further, it is assumed that a touch panel is adopted for the display screen D. Further, the dorareco device 10 also has a microphone (sound collecting unit) for collecting the driver's voice and a speaker (output unit) for outputting the sound. Further, the dorareco device 10 may also include an in-camera for capturing a predetermined object (for example, the face of a wandering bar) inside the vehicle instead of outside the vehicle. The in-camera may be used, for example, as a function of preventing the driver from falling asleep.

Here, the premise for performing the first information processing according to the embodiment will be described. For example, if there is a parking lot installed on the road such as a parking lot for a parking meter around the destination, the driver wants to use this. In addition, the parking lots installed on the roads are often in fierce competition. For example, even if there is an empty parking lot, it passes through it once and is full by the time it returns. Not a few. For this reason, it would be convenient if the driver could be accurately notified of the availability of the parking place when it arrives near the parking place.

For this reason, it would be convenient to be able to notify the exact availability of such a parking place when it arrives near the parking place installed on the road. However, the parking lot installed on the road has different usage conditions from the general parking lot, and due to the structure that it is installed on the road, fluctuations in the full vacancy status are subject to various external conditions (for example, day of the week, time zone). , The presence or absence of the surrounding environment). For this reason, it is difficult to apply the full vacancy prediction for general parking lots as shown in the above-mentioned prior art, and even if it is applied, the full vacancy situation can be accurately obtained. It is not always predictable.

Therefore, in the present embodiment, attention is paid to the fact that the parking place installed on the road is easily affected by various external conditions (for example, the day of the week, the time zone, and the presence or absence of the surrounding environment), and the parking place is satisfied under these conditions. We are focusing on acquiring availability statistics and predicting the full availability at the estimated arrival time based on the acquired statistics.

Based on the above assumptions, the information processing apparatus 100 according to the embodiment performs information processing according to the embodiment. Specifically, the information processing device 100 accumulates fullness information indicating the fullness status of the parking place installed on the road for each parking place, and based on the accumulated fullness information, the moving body to be processed Predict the availability of the parking place at the estimated arrival time when it arrives at the parking place. Hereinafter, the vehicle will be described as an example of a moving body. For example, the information processing device 100 accumulates the fullness information indicating the fullness status determined based on the imaging data obtained by imaging the parking place by a predetermined imaging means as the fullness information.

Further, the information processing device 100 is statistical information for each parking place obtained based on the accumulated fullness information, and is an arrival prediction based on the statistical information showing the statistics of the fullness situation under a predetermined condition. Predict the availability of parking lots at the time. For example, the information processing device 100 has at least one condition of day, time zone, weather around the parking place, or presence / absence of an event (for example, traffic jam or construction) around the parking place as a predetermined condition. Based on the statistical information obtained based on the fullness information indicating the fullness status in, the fullness status of the parking place at the estimated arrival time is predicted. For example, in the information processing device 100, as statistical information, a parking place at an estimated arrival time is based on a statistical model in which a tendency-based relationship between a fullness condition and a predetermined condition is learned for each parking place. Predict the fullness situation of. As an example of this, the information processing device 100 is a model that outputs information indicating the fullness status of the parking place at the estimated arrival time when the information indicating the estimated arrival time of the vehicle to be processed arrives at the parking place is input. Based on, predict the availability of parking lots at the estimated arrival time.

In the following, an example of the first information processing according to the embodiment will be described step by step with reference to FIG. In addition, a storage unit included in the information processing device 100 will be described as appropriate. Further, the information processing apparatus 100 according to the embodiment can use the imaging data acquired by any imaging means, but in the present embodiment, for the sake of simplicity, the information processing apparatus 100 uses the imaging means. It is assumed that only the imaging data obtained by imaging with the security camera, which is an example of K, is used for the first information processing. Of course, the information processing apparatus 100 can use, for example, the imaging data obtained by imaging by the dorareco apparatus 10, or can use these imaging data together. For example, the information processing apparatus 100 can determine the fullness condition under a predetermined condition with high accuracy by using the imaging data obtained by various imaging means.

In the example of FIG. 1, the imaging means K, which is a security camera, constantly images an object within the imaging range. For example, the imaging means K shall obtain the imaging data VG10 by such imaging. The imaging data VG10 is moving image data having a reproduction time for that period, which is obtained by continuing to image by the imaging means K for a predetermined period. Then, the imaging means K transmits the imaging data VG10 to the information processing device 100. As a result, the information processing apparatus 100 acquires the imaging data VG10 from the imaging means K (step S11).

In the example of FIG. 1, a predetermined section of the road L1 is captured in the imaging data VG10. A parking lot PK1 for a parking meter is installed in this predetermined section. That is, in this predetermined section, the parking place PK1 which is an aggregate of one parking lot (parking lot for parking one vehicle) corresponding to each parking meter is copied.

Further, in the example of FIG. 1, the parking lot PK1 having a geographical spread along the direction in which the road L1 extends is divided into three areas such as area AR11, area AR12, and area AR13. In the following, such an area may be referred to as a "parking area". Each parking lot area includes six parking lots. It should be noted that the area of each parking place including the parking place PK1 may be arbitrarily divided, the area may be divided manually, or the image by the information processing device 100 may be used. It may be done dynamically by analysis.

Next, the information processing device 100 makes a fullness determination to determine the fullness status of the parking place PK based on the image pickup data VG10 (step S12). For example, the information processing device 100 determines the fullness status of each parking lot area in the "day of the week" and the "time zone" for each "day of the week" and the "time zone" corresponding to the image pickup data VG10. Make a judgment. For example, the information processing device 100 extracts the imaging data in each “time zone” for each “day of the week” from the imaging data VG10, and analyzes the extracted imaging data to obtain a full vacancy status in each parking lot area. To judge. Then, the information processing apparatus 100 finally determines whether the parking lot area is full or empty during the "time zone" based on the determined fullness condition.

In addition, the information processing device 100 may also perform a full / empty determination for the parking lot imaged in the imaged data in real time when the image is being taken, based on the imaged data obtained by the image pickup by the dorareco device 10 of each vehicle. it can. Then, the information processing apparatus 100 can also apply the fullness condition determined by this to the generation of the statistical model described below, for example. Therefore, based on the image pickup data acquired from the dorareco device 10 of each vehicle, the information processing device 100 performs the fullness determination and the fullness determination for the parking lot imaged in the image pickup data in real time when the image pickup is performed. A series of processes related to the fullness determination will be described later as the second information processing with reference to FIG. 7 and the like.

Next, the information processing device 100 stores the fullness information based on the determination result (fullness status) of the fullness determination in step S12 in the fullness information storage unit 121 (step S13). For example, the information processing device 100 indicates to the full / empty information storage unit 121 the full / empty status of each parking area in the “day” and “time zone” for each “day” and “time zone”. The full-empty information is stored in the full-empty information storage unit 121.

An example of steps S12 and S13 is shown. As an example, the information processing device 100 finally determines whether the area AR11 is full or empty during this period, targeting the "0 o'clock level" on "Sunday, February 10, 2019". An example is shown. For example, the information processing apparatus 100 extracts the imaging data corresponding to the “midnight” of “February 10, 2019 (Sunday)” from the imaging data VG10. Then, the information processing device 100 determines the fullness status of the parking lot for each parking lot included in the area AR11 by analyzing the extracted imaging data, and the time occupied by the determined fullness status is a predetermined time. Based on whether or not the condition is satisfied, it is determined whether the area AR 11 is full or empty during the period.

For example, the predetermined time condition is "50 minutes or more of the time zone (1 hour), and 80% or more of the parking lots in the parking lot area are full". In such a state, for example, the judgment result by the full / empty judgment is four out of the six parking lots included in the area AR11 during the "midnight level" of "Sunday, February 10, 2019". Suppose it indicates that the parking lot was always empty. In such a case, the information processing apparatus 100 determines that the area AR 11 is empty at the "midnight level" on "Sunday, February 10, 2019". Then, the information processing device 100 inputs "0" indicating an empty vehicle in the corresponding input field in the full / empty information storage unit 121. An example of such an input will be shown later in FIG. The time condition as described above is only an example, and an arbitrary time condition may be set.

As another example, whether the information processing device 100 targets the "23:00 level" on "Sunday, February 10, 2019" and the area AR11 is full or empty during this period. Is shown as an example of finalizing. For example, the information processing apparatus 100 extracts the imaging data corresponding to the "23:00 level" of "Sunday, February 10, 2019" from the imaging data VG10. Then, the information processing apparatus 100 determines the full vacancy status in the parking lot for each parking lot included in the area AR 11 by analyzing the extracted imaging data, and is based on the time condition occupied by the determined vacancy status. Therefore, it is determined whether the area AR11 is full or empty during this period.

For example, the judgment result based on the full / empty judgment here is that all six parking lots included in the area AR11 are full for 50 minutes or more out of the "23:00 level" on "Sunday, February 10, 2019". It is assumed that it was shown that it was. In such a case, the information processing apparatus 100 determines that the area AR 11 is full at "23:00" on "Sunday, February 10, 2019". Then, the information processing device 100 inputs "1" indicating fullness in the corresponding input field in the full / empty information storage unit 121. An example of such an input will be shown later in FIG.

As described above, in step S12, the information processing apparatus 100 determines the fullness status of each parking lot area in the "day of the week" and the "time zone" for each "day of the week" and the "time zone", and at the same time It is determined whether the parking lot area is full or empty based on whether or not the time occupied by the determined fullness condition satisfies a predetermined time condition. In addition, the information determined in this way can be said to be a kind of fullness information indicating a fullness situation. Therefore, the information processing device 100 stores the fullness information in the fullness information storage unit 121.

Here, FIG. 2 shows an example of the full / empty information storage unit 121 according to the embodiment. In the example of FIG. 2, the full / empty information storage unit 121 has items such as “road ID”, “parking place ID”, “location information”, “area ID”, and “date / time information”. In addition, the "date and time information" includes information indicating a "day of the week" such as "Sunday, February 10, 2019" and information indicating a "time zone" such as "0 o'clock".

The "road ID" indicates identification information that identifies the road. For example, the road identified by the road ID "L1" means the road L1. The "parking place ID" indicates identification information that identifies a parking place installed on the road identified by the corresponding "road ID". For example, the parking place identified by the parking place ID "PK1" means that it is the parking place PK1. The "location information" is location information indicating the location of the parking location identified by the corresponding "parking location ID". As an example, the "location information" is location information indicating in which section of the road the parking location identified by the corresponding "parking location ID" is installed. The "area ID" indicates identification information for identifying the parking lot area. For example, the parking lot area identified by the area ID "AR11" means the area AR11.

In such a state, for example, in the input field associated with the item "Sunday, February 10, 2019", the item "0 o'clock", and the item "AR11" (area ID), step S12 The fullness information indicating the judgment result of the fullness judgment in is input. More specifically, the input fields associated with the item "Sunday, February 10, 2019", the item "0 o'clock", and the item "AR11" (area ID) are determined to be full. The full / empty information determined based on whether or not the determination result satisfies the predetermined time condition is input. According to the above example shown in step S12, the information processing apparatus 100 is determined to be full for each parking lot in the area AR11 at "0 o'clock" on "Sunday, February 10, 2019", and the determination result. By comparing with the predetermined time conditions, it is determined that the area AR11 was empty at "0 o'clock" on "Sunday, February 10, 2019". Therefore, in the input field associated with the item "Sunday, February 10, 2019", the item "0 o'clock", and the item "AR11" (area ID), it is indicated that the vehicle is empty. 0 ”is entered.

Further, according to the above example shown in step S12, the information processing apparatus 100 determines the fullness of each parking lot in the area AR11 at "23:00" on "Sunday, February 10, 2019". And, by comparing with the predetermined time conditions, it is determined that the area AR11 was full at "23:00" on "Sunday, February 10, 2019". Therefore, the input fields associated with the item "Sunday, February 10, 2019", the item "23:00", and the item "AR11" (area ID) indicate that the vehicle is full. 1 ”is entered.

The information processing device 100 determines whether or not the sky is full in the "day of the week" and the "time zone" for each "day of the week" and the "time zone" based on the imaging data over a predetermined period, thereby performing the "day of the week" and the "time". Determine the availability of the obi. Therefore, the full / empty information storage unit 121 accumulates full / empty information for each “day of the week” and “time zone”.

Next, the information processing apparatus 100 performs a tendency analysis (statistical tendency analysis) between the fullness situation and a predetermined condition (for example, day of the week, time zone, weather, event, etc.). Generate a statistical model that is a trained model (step S14). For example, the information processing apparatus 100 analyzes and analyzes the tendency of the full sky condition under the weather "fine" (or weather "rain") condition in the time zone for each time zone of each day of the week. A trained model is generated (generation processing pattern 1). Further, for example, the information processing apparatus 100 analyzes and analyzes the tendency of the vacancy situation under the condition that an event (for example, construction work or traffic jam) occurs in the time zone for each time zone of each day of the week. Generates the trained model (generation processing pattern 2).

First, an example of the generation processing pattern 1 will be described with reference to FIGS. 2 and 3. FIG. 3 is a diagram showing an example of the statistical information storage unit 122 according to the embodiment. For example, it is assumed that the full / empty information storage unit 121 stores full / empty information as shown in FIG. In such a state, the information processing apparatus 100 identifies, for example, the "time zone" in which the weather is "fine" (or the weather "rain") from the "time zone" of each day by comparing with the weather information. , The full / empty information in the specified "time zone" is extracted from the full / empty information storage unit 121. The information processing device 100 can acquire weather information from an external predetermined server device. In the following, the weather "fine" will be described as an example, but the same processing is performed for the weather "rain". In addition, the weather to be processed is not limited to "fine" and "rain".

FIG. 2A shows a part of an example in which the information processing apparatus 100 extracts the full sky information in the “time zone” when the weather is “fine” from the full sky information storage unit 121. In the example of FIG. 2A, the information processing apparatus 100 sets the "time zone" when the weather was "fine" from "2 o'clock" to "22:00" on "Sunday, February 10, 2019". Is specified, and the full / empty information in each period is extracted from the full / empty information storage unit 121. Further, in the example of FIG. 2A, the information processing apparatus 100 sets the "time zone" when the weather was "fine" at "0:00" and "1 o'clock" on "February 11, 2019 (Monday)". The "table" and "2 o'clock" are specified, and the full / empty information in each period is extracted from the full / empty information storage unit 121. Further, in the example of FIG. 2A, the information processing apparatus 100 sets the "time zone" when the weather was "fine" at "23:00" and "0:00" on "Sunday, February 17, 2019". The "unit" is specified, and the full / empty information in each period is extracted from the full / empty information storage unit 121.

After extracting in this way, the information processing apparatus 100 then uses the extracted full-sky information for each time zone of each day to indicate the weather "fine" (or weather "rain") in that time zone. Analyze the trend of fullness below and generate a trained model of the analyzed trend. As an example, the information processing apparatus 100 learns how the parking lot in the area AR11 tends to be full at "8 o'clock" on "Sunday" under the condition of "fine weather". Generate the model. Further, as another example, the information processing apparatus 100 shows the tendency of the parking lot in the area AR11 to be full at "9 o'clock" on "Sunday" under the condition of "fine weather". Generate a model that has been trained.

In other words, when the estimated arrival time when the vehicle to be processed arrives at the parking place PK1 (or the vicinity of the parking place PK1) is input, the information processing apparatus 100 indicates that the parking place PK is full at the estimated arrival time. Generate a model that outputs information indicating. In the examples of FIGS. 1 and 2, the information processing apparatus 100 corresponds to the estimated arrival time when the estimated arrival time at which the vehicle to be processed arrives at the parking place PK1 (or the vicinity of the parking place PK1) is input. A model is generated that outputs information indicating the fullness status for each parking lot area included in the parking place PK1 which is the fullness status in the time zone.

The information processing device 100 stores the generated model in the statistical information storage unit 122. In the generation processing pattern 1, the information processing apparatus 100 is a statistic obtained by learning the tendency of the vacancy status for each parking lot area, which is the vacancy status for each time zone of each day of the week under the condition of "clear weather". I am generating a model. Therefore, the information processing device 100 stores each statistical model under the weather "fine" condition in, for example, the statistical information storage unit 122-1 (a). The statistical information storage unit 122-1 (a) shown in FIG. 3A shows the state at this time. Further, in the generation processing pattern 1, the information processing apparatus 100 learns the tendency of the full vacancy status for each parking lot area, which is the full vacancy status for each time zone of each day of the week under the weather "rain" condition. We are generating a statistical model. Therefore, the information processing apparatus 100 stores each statistical model under the weather "rain" condition in, for example, the statistical information storage unit 122-1 (b). The statistical information storage unit 122-1 (b) shown in FIG. 3 shows the state at this time.

In the example of FIG. 3, the statistical information storage unit 122-1 (a) has items such as “road ID”, “parking place ID”, “area ID”, and weather “fine”. In addition, the weather "fine" includes information indicating a "day of the week" such as "day" and information indicating a "time zone" such as "midnight".

The "road ID", "parking place ID", and "area ID" in the statistical information storage unit 122 correspond to those of the full / empty information storage unit 121, and thus the description thereof will be omitted. Weather "fine" indicates that the model can be used under "weather" conditions.

In such a state, in the example of FIG. 3A, for example, the weather "fine" item, the item "day", the item "0 o'clock", and the item "AR11" (area ID) are associated with each other. In the input field, the statistical model ssM11-24a is input. In such an example, the information processing apparatus 100 tends to be full (for example, at least one) in the parking lot in the area AR11 at "midnight" on "Sunday" under the condition of "fine weather". Shows an example in which a statistical model ssM11-24a is generated and input as a model learned whether or not there is a tendency for empty parking spaces or a tendency for the parking lot to always be full. That is, such an example is a case where the weather at the estimated arrival time when the vehicle to be processed arrives at the parking place PK1 (or around the parking place PK1) is expected to be "fine", and the estimated arrival time is ". An example in which the statistical model ssM11-24a is generated as a model for inputting the estimated arrival time in the case of "0 o'clock" is shown.

Further, in the example of FIG. 3, the statistical information storage unit 122-1 (b) has items such as "road ID", "parking place ID", "area ID", and weather "rain". In addition, the weather "rain" includes information indicating a "day of the week" such as "day" and information indicating a "time zone" such as "midnight".

In such a state, in the example of FIG. 3B, for example, the weather "rain" item, the item "Sunday", the item "0 o'clock", and the item "AR11" (area ID) are associated with each other. In the input field to be input, the statistical model rsM11-24a is input. In such an example, under the condition of the weather "rain", the information processing device 100 tends to be full (for example, at least one) in the parking lot in the area AR11 at "midnight" on "Sunday". Shows an example in which a statistical model rsM11-24a is generated and input as a model learned whether or not there is a tendency for empty parking spaces or a tendency for the parking lot to always be full. That is, such an example is a case where the weather at the estimated arrival time when the vehicle to be processed arrives at the parking place PK1 (or around the parking place PK1) is expected to be "rain", and the estimated arrival time is ". An example in which the statistical model rsM11-24a is generated as a model for inputting the estimated arrival time in the case of "0 o'clock" is shown.

Next, an example of the generation processing pattern 2 will be described with reference to FIGS. 2 and 4. FIG. 4 is a diagram showing an example (2) of the statistical information storage unit 122 according to the embodiment. For example, it is assumed that the full / empty information storage unit 121 stores full / empty information as shown in FIG. In such a state, the information processing apparatus 100 compares with the event information, for example, from the "time zone" of each day of the week to the "time zone" in which the event "construction" (or event "traffic jam") has occurred. Is specified, and the full / empty information in the specified “time zone” is extracted from the full / empty information storage unit 121. The information processing device 100 can acquire event information from an external predetermined server device. In the following, the event "construction" will be described as an example, but the same processing will be performed for the event "traffic jam". In addition, the events to be processed are not limited to "construction" and "traffic jam".

FIG. 2B shows a part of an example in which the information processing apparatus 100 extracts the full / empty information in the “time zone” which was the event “construction” from the full / empty information storage unit 121. In the example of FIG. 2B, the information processing apparatus 100 has "January 7, 2019 (Sunday)" to "January 17, 2019 (Monday)" as the "time zone" that was the event "construction". "0 o'clock" to "23:00" up to "0 o'clock" to "23:00" are specified, and the full / empty information in each period is extracted from the full / empty information storage unit 121.

When extracted in this way, the information processing apparatus 100 then uses the extracted full / empty information for each time zone of each day of the week, and the event "construction" (or event "traffic jam") article in that time zone. It analyzes the tendency of the full sky situation below and generates a model that trains the analyzed tendency. As an example, in the information processing device 100, under the condition that the event "construction" has occurred in the vicinity of the area AR11, what kind of vacancy situation is in the parking lot in the area AR11 at "8 o'clock" on "Sunday". Generate a model that has been trained to have a tendency to. Further, to show another example, under the condition that the event "construction" has occurred in the vicinity of the area AR11, the information processing device 100 has a parking lot in the area AR11 at "9 o'clock" on "Sunday". Generate a model that has been trained to see if it tends to be full.

It should be noted that events such as construction and traffic jams often occur only in a specific time zone, and then the information processing device 100 may not be able to generate a model in all the time zones. In addition, since there are parking places in the vicinity where no events such as construction or traffic jams have occurred, the information processing device 100 cannot generate a model even in such a case. Therefore, in such a time zone in which the record of the event is very small or there is no record at all, the information processing apparatus 100 is based on the full / empty information in the time zone in which the record of the event is sufficient. You may predict the fullness information in the time zone when the actual results are insufficient, and generate a model using the predicted fullness information. Further, when the event results on the roads whose usage conditions are relatively close to each other due to the similar road conditions and the surrounding environment are available, the information processing apparatus 100 has the results based on the full sky information indicated by the results. The full / empty information in the shortage time zone may be predicted, and a model may be generated using the predicted full / empty information.

The information processing device 100 stores the generated model in the statistical information storage unit 122. In the generation processing pattern 2, the information processing device 100 is the full vacancy status for each time zone of each day of the week under the condition that the event "construction" has occurred, and the tendency of the full vacancy status for each parking lot area. Is generating a trained statistical model. Therefore, the information processing apparatus 100 stores each statistical model under the condition that the event "construction" has occurred, for example, in the statistical information storage unit 122-2 (a). The statistical information storage unit 122-2 (a) shown in FIG. 4 (a) shows the state at this time. Further, in the generation processing pattern 2, the information processing device 100 is a full vacancy status for each time zone of each day of the week under the condition that the event "traffic jam" has occurred, and is a full vacancy status for each parking lot area. We are generating a statistical model that has learned the trends of. Therefore, the information processing device 100 stores each statistical model under the condition that the event "traffic jam" has occurred, for example, in the statistical information storage unit 122-2 (b). The statistical information storage unit 122-2 (b) shown in FIG. 4 shows the situation at this time.

In the example of FIG. 4, the statistical information storage unit 122-2 (a) has items such as "road ID", "parking place ID", "area ID", and event "construction". In addition, the event "construction" includes information indicating a "day of the week" such as "day" and information indicating a "time zone" such as "midnight".

The "road ID", "parking place ID", and "area ID" in the statistical information storage unit 122 correspond to those of the full / empty information storage unit 121, and thus the description thereof will be omitted. The event "Construction" indicates that it is a model that can be used under conditions where "construction" is occurring.

In such a state, in the example of FIG. 4A, for example, the event "construction" item, the item "Sunday", the item "0 o'clock", and the item "AR11" (area ID) are associated with each other. In the input field, the statistical model csM11-24a is input. In such an example, under the condition that the event "construction" has occurred in the information processing device 100, what kind of vacancy tendency (for example) is in the parking lot in the area AR11 at "midnight" on "Sunday". , At least one of them shows an example in which a statistical model csM11-24a is generated and input as a model learned whether or not there is a tendency of empty parking spaces, or a tendency of always being full. That is, such an example is a case where "construction" is expected to occur in the vicinity of the parking place PK1 at the estimated arrival time when the vehicle to be processed arrives at the parking place PK1 (or around the parking place PK1). An example is shown in which a statistical model csM11-24a is generated as a model for inputting the estimated arrival time when the estimated arrival time is in the “0 o'clock range”.

Further, in the example of FIG. 4, the statistical information storage unit 122-2 (b) has items such as "road ID", "parking place ID", "area ID", and event "traffic jam". In addition, the event "traffic jam" includes information indicating a "day of the week" such as "day" and information indicating a "time zone" such as "0 o'clock".

In such a state, in the example of FIG. 4B, for example, the event "traffic jam" item, the item "Sunday", the item "0 o'clock", and the item "AR11" (area ID) are associated with each other. In the input field to be input, the statistical model tsM11-24a is input. In such an example, under the condition that the information processing device 100 is experiencing the event "traffic jam", what kind of vacancy tendency (for example) is the parking lot in the area AR11 at "midnight" on "Sunday". , At least one of them shows an example in which a statistical model tsM11-24a is generated and input as a model learned whether or not there is a tendency of empty parking spaces or a tendency of always being full. That is, such an example is a case where "traffic jam" is expected to occur in the vicinity of the parking place PK1 at the estimated arrival time when the vehicle to be processed arrives at the parking place PK1 (or around the parking place PK1). An example is shown in which a statistical model tsM11-24a is generated as a model for inputting the estimated arrival time when the estimated arrival time is in the “0 o'clock range”.

As shown in FIGS. 2 to 4, in the first information processing, the information processing apparatus 100 separates the weather condition and the event condition and generates a statistical model corresponding to each. However, the information processing device 100 determines, for example, what kind of vacancy situation tends to occur when the weather is "fine" and the event "construction" occurs for each parking lot area and time zone. A statistical model trained for each may be generated.

An example of model generation in step S14 of FIG. 1 has been described with reference to FIGS. 2 to 4. From here, the explanation returns to FIG. Next, the information processing device 100 determines whether or not there is a vehicle whose destination is set on the car navigation Z (that is, a vehicle to be processed) (step S15). For example, the information processing device 100 determines the car navigation Z. By accessing the provided external server device, it is determined whether or not there is a vehicle whose destination is set (that is, a vehicle to be processed) on the car navigation system Z. If the vehicle to be processed does not exist (step S15; No), the information processing device 100 waits until the vehicle to be processed appears.

On the other hand, when the vehicle to be processed exists (step S15; Yes), the information processing apparatus 100 acquires the estimated arrival time when the vehicle to be processed arrives at the destination (step S16). For example, the information processing device 100 may acquire the estimated arrival time when the vehicle to be processed arrives at the destination by accessing an external server device that provides the car navigation system Z, or may acquire the estimated arrival time based on the destination. The estimated arrival time may be acquired (calculated) on the device side. In the example of FIG. 1, the information processing apparatus 100 confirms the existence of the vehicle C8 for which the destination O is set as the vehicle to be processed in step S15, and the estimated arrival time to the destination O in step S16. It is assumed that "22:30 on Sunday, February 24, 2019" has been acquired.

Further, although not shown in FIG. 1, the information processing apparatus 100 also determines whether or not there is a parking place in the vicinity of the destination O (for example, an area within a predetermined radius of the destination O) and parks. If it is determined that the place exists, the estimated time of arrival at this parking place is also set to, for example, "22:30 on Sunday, February 24, 2019". For the sake of simplicity, in the example of FIG. 1, the information processing apparatus 100 has a parking place PK1 near the destination O, so that the vehicle C8 arrives at the parking place PK1 as an estimated arrival time. It is assumed that "22:30 on Sunday, February 24, 2019" has been set.

In such a state, the information processing apparatus 100 has the information processing device 100 at "22:30 on Sunday, February 24, 2019", which is the estimated arrival time when the vehicle C8 arrives at the parking place PK1 near the destination O. The optimum statistical model for predicting the fullness of the parking place PK1 is extracted from the statistical information storage unit 122 (step S17). For example, the information processing device 100 has the weather at "Sunday 22:00", "February 24, 2019 (Sun) 22:00", and "February 24, 2019 (Sun) 22:00". Based on the presence or absence of an event (for example, construction or traffic jam) in the vicinity of the parking place PK1, the optimum statistical model for predicting the fullness status of the parking place PK1 is extracted from the statistical information storage unit 122. For example, the information processing device 100 identifies the weather "fine" at "22:00 on Sunday, February 24, 2019" based on the weather information, and "February 24, 2019 (Sunday), 2019" based on the event information. It is assumed that no event is specified at "22:00 on Sunday).

When specified in this way, the information processing device 100 associates the statistical information storage unit 122-1 (a) corresponding to the weather "fine" with "Sunday", "22:00", and the area ID "AR11". The statistical model ssM11-22a to be obtained is extracted. Further, the information processing device 100 is associated with the statistical model ssM12- that is associated with "Sunday", "22:00", and the area ID "AR12" from the statistical information storage unit 122-1 (a) corresponding to the weather "fine". 22a is extracted. Further, the information processing device 100 is associated with the statistical model ssM13- that is associated with "Sunday", "22:00", and the area ID "AR13" from the statistical information storage unit 122-1 (a) corresponding to the weather "fine". 22a is extracted.

Next, the information processing apparatus 100 inputs the "estimated arrival time" to the statistical model extracted in step S17, and predicts the fullness status at the "estimated arrival time" based on the output fullness information. (Step S18). In the case of the above example, the information processing apparatus 100 inputs, for example, the estimated arrival time "22:30 on Sunday, February 24, 2019" to the statistical model ssM11-22a. Calculate the score indicating the fullness information of the area AR11 in. Then, the information processing apparatus 100 predicts the fullness status of the area AR 11 based on the calculated score. For example, when the score "1" is calculated (output) as full / empty information, the information processing apparatus 100 enters the area AR11 at the estimated arrival time "February 24, 2019 (Sunday) 22:30". The included parking lot is expected to be full (probably). On the other hand, for example, when the score "0" is calculated (output) as full / empty information, the information processing apparatus 100 has an area at the estimated arrival time "Sunday, February 24, 2019, 22:30". It is predicted that some parking lots included in AR11 are empty (probably).

Similarly, the information processing apparatus 100 inputs the estimated arrival time "22:30 on Sunday, February 24, 2019" to the statistical model ssM12-22a, so that the area at the estimated arrival time is reached. A score indicating full / empty information of AR12 is calculated. Then, the information processing apparatus 100 predicts the fullness status of the area AR12 based on the calculated score. Similarly, the information processing apparatus 100 inputs the estimated arrival time "22:30 on Sunday, February 24, 2019" to the statistical model ssM13-22a, so that the area AR13 at this estimated arrival time Calculate the score indicating the fullness information. Then, the information processing apparatus 100 predicts the fullness status of the area AR13 based on the calculated score.

In the example of FIG. 1, in the information processing device 100, the area AR11 is "highly likely to be full", the area AR12 is "highly likely to be full", and the area AR13 is "lowly likely to be full". (There is a high possibility that there are empty cars in area AR11).

Next, the information processing device 100 notifies the driver of the vehicle C8, which is the vehicle to be processed, of the prediction result in step S18 (step S19). For example, the information processing device 100 notifies information indicating the fullness status in the parking lot area for each parking lot area. In the case of the above example, the information processing apparatus 100 notifies the information indicating the fullness status in each of the area AR11, the area AR12, and the area AR13.

For example, in the information processing device 100, the area AR11 is "highly likely to be full", the area AR12 is "highly likely to be full", and the area AR11 is "highly full" with respect to the driver record device 10-8 of the vehicle C8. It is controlled to notify the driver D8 that the vehicle is unlikely to be full. In response to such control, the driver recorder device 10-8 "is likely to be full" in area AR11, "is likely to be full" in area AR12, and "is unlikely to be full" in area AR13. Is displayed on the display screen D to notify the driver D8. Further, the dorareco device 10-8 can perform notification by voice output as well as display on the display screen D. This point will be described with reference to FIG. FIG. 5 is a diagram showing an example of information notification according to the embodiment.

In the example of FIG. 5, the dorareco device 10-8 is the map information provided by the car navigation system Z, and the map information indicating the vicinity of the destination O is displayed on the display screen D. In such a state, the dorareco device 10 surrounds the section where the parking place PK1 exists with respect to the road L1 included in the map information, for example, with a dotted line, and the area AR11 is “highly likely to be full” in the section. Information JAR11 indicating that the vehicle is full, information JAR12 indicating that the area AR12 is "highly likely to be full", and information JAR13 indicating that the area AR13 is "highly likely to be full" are displayed. It should be noted that such a display mode is only an example, and the mode in which the dorareco device 10-8 notifies the fullness information is not limited.

In addition, the dorareco device 10-8 can also output audio for explaining the display mode shown in FIG. For example, the dorareco device 10-8 outputs audio at a timing before the vehicle C8 enters the road L1, or at a timing when the distance between the vehicle C8 and the parking place PK1 is more than a predetermined distance. For example, the dorareco device 10-8 outputs a voice such as "There is a high possibility that the vehicle is full near the destination O. It is unlikely that the vehicle is full if it is in front of the destination O." By such screen notification and voice notification, the driver D8 can easily grasp which area has a vacancy in a parking lot having a large geographical area as compared with a general parking lot. become. In addition, the driver D8 thought that there might be a vacancy near the destination O due to such a notification, and passed through the vacancy in front of him, but in the end there was a vacancy beyond that. It is possible to avoid the situation where it was not.

By the way, as described above, the information processing device 100 according to the embodiment accumulates the fullness information indicating the fullness status of the parking place installed on the road for each parking place, and the accumulated fullness information Based on the statistics, the availability of this parking place is predicted at the estimated arrival time when the vehicle to be processed arrives at the parking place. Then, the information processing device 100 notifies the driver of the predicted fullness situation. As a result, the information processing device 100 can accurately predict the fullness status of the parking place at the estimated time of arrival at the parking place installed on the road.

In the example of FIG. 1, the information processing apparatus 100 parks the relationship based on the tendency between the fullness status and a predetermined condition (for example, day of the week, time zone, weather, presence / absence of an event) as statistical information. An example of predicting the availability of parking places at the estimated arrival time is shown based on a statistical model learned for each place. However, the information processing device 100 further uses statistical information showing statistics on the frequency of vehicle replacement in the parking place as statistical information, and predicts the full vacancy situation at the estimated arrival time.

For example, since the imaging means K such as a security camera continues to image a certain range for a long period of time, the information processing apparatus 100 analyzes the imaging data VG10 in the example of FIG. 1 to obtain the “day of the week” and the “time”. For each "zone", statistical information showing the statistics of the frequency of vehicle replacement for each parking lot area in the "day of the week" and the "time zone" is acquired. For example, the information processing device 100 analyzes the tendency of the change frequency in the time zone for each time zone of each day of the week for each parking lot area, and generates a model in which the analyzed tendency is learned. As an example, the information processing apparatus 100 generates a frequency statistical model that outputs a score indicating the frequency of replacement in a time zone including the input estimated arrival time when the expected arrival time is input.

In the above example, in the information processing device 100, at "Monday at 22:00", the area AR11 is "highly likely to be full", the area AR12 is "highly likely to be full", and the area AR13 is "full". It is unlikely that there is an empty car in Area AR11. " Further, the information processing apparatus 100 uses a frequency statistical model, and in "Monday at 22:00", the area AR11 is "highly replaced", the area AR12 is "lowly replaced", and the area AR13 is "replaced". "Infrequent" is predicted.

Then, the information processing device 100 notifies the dorareco device 10-8 that "the area near the destination O is likely to be full at present, but it is highly likely that parking will be possible after a short wait." Can be done. In addition, the information processing device 100 tells the dorareco device 10-8 that "the area closest to the destination O is likely to be full at present, but it is highly possible that it will be possible to park after a short wait. Also, there is a high possibility that the car is currently empty in the area a little away from the destination O, but it may become full soon. ”Involved in the frequency of replacement. Notifications unique to parking lots with geographical expanse can be given. In this way, the information processing apparatus 100 can perform notification with higher usability by making a prediction that also combines statistics on the frequency of replacement.

[2. An example of the second information processing]
By the way, the first information processing according to the embodiment has been described with reference to FIGS. 1 to 4. From here, the second information processing according to the embodiment will be described. As described above, the information processing device 100 determines whether the parking lot is full or empty, which is captured in the imaged data, in real time when the image is taken, based on the imaged data obtained by the image pickup by the dorareco device 10 of each vehicle. You can also do it. Therefore, a series of processes related to the fullness determination will be described below as the second information processing.

Prior to the explanation of the second information processing, other assumptions for performing the second information processing will also be described. For example, even if the map shows the availability of parking lots for parking meters, there are many parking meters that have a lot of competition, so when you arrive, all the parking lots are full. Can occur. For this reason, for example, when passing near a parking lot for a parking meter, if the fullness status of each parking lot is appropriately notified at this parking lot, it is possible to prevent the car from passing through the parking lot of an empty car. can do. For example, once you have passed an empty parking lot, a busy parking lot may be full the next time you return to this parking lot.

For this reason, car navigation systems and drive recorders that can accurately notify the driving driver of the fullness of parking places installed on the road and the fullness of parking places near the driving. It is very convenient if there is, and driving safety is also improved.

Based on the above assumptions, the information processing apparatus 100 according to the embodiment performs the second information processing according to the embodiment. Specifically, the information processing device 100 acquires image pickup data. For example, the information processing device 100 acquires image data captured by a camera mounted on a vehicle traveling on a road. That is, the information processing device 100 acquires the imaged data captured by the drive recorder of the vehicle. Then, the information processing device 100 determines the fullness status of the parking place installed on the road, which is copied in the image pickup data, based on the acquired image pickup data. Then, the information processing device 100 notifies the driver (user) of the determination result. For example, the information processing device 100 determines the current full vacancy status of a parking place where a vehicle equipped with a camera is installed on a road where the vehicle is currently traveling and which exists in the traveling direction of the moving body. .. Specifically, the information processing device 100 determines the fullness status of the parking place for each parking section for parking one moving body as a parking place.

Further, the information processing device 100 determines the fullness status of the parking place based on the imaging data, depending on whether or not the imaging mode of the predetermined imaged object to be captured in the imaging data satisfies the predetermined conditions. .. For example, the information processing device 100 captures a line drawn on a road (for example, a white line indicating a parking lot) as an imaging mode of a predetermined imaged object according to a positional relationship with a moving body. The availability of the parking lot is determined according to whether or not the imaging mode of the line satisfies a predetermined condition. For example, the information processing device 100 determines the availability of a predetermined parking place according to whether or not the shape of the predetermined imaged object is the shape indicated by the imaging mode. For example, the information processing device 100 is a model learned from information in which an imaging mode of a predetermined imaged object and a fullness state of a parking place when the imaged object is imaged as shown by the imaging mode are associated with each other. Based on, the fullness status of the parking place to be processed is determined.

In the following, an example of the second information processing according to the embodiment will be described step by step with reference to FIG. 7. FIG. 7 is a diagram showing an example of the second information processing according to the embodiment. The second information processing according to the embodiment also corresponds to the information processing system 1 shown in FIG. The parking lot targeted by the second information processing is basically a parking lot (parking lot) installed on the road, such as a parking lot for a parking meter, but is a general parking lot. It may also be applied to coin parking and the like.

The description up to step S23 is a process in the previous stage for determining the fullness of the parking place, and is a process for generating a learning model. For learning, the actual results of imaging data samples collected by traveling around the country while each vehicle shoots (records) with a drive recorder are used. Then, by designating the correct answer data (correct answer label, teacher data) for the imaged data sample as the actual result, the information processing apparatus 100 captures, for example, how the line (white line) drawn on the road is copied. When it is, the line is a line indicating a parking lot, and it learns whether the parking lot is empty or full, and generates a model in which the learning result is reflected.

In FIG. 7, three vehicles such as vehicle C1, vehicle C2, and vehicle C3 are illustrated as vehicles for obtaining an imaging data sample, but the number of vehicles is not limited. In addition, there are no restrictions on the type of vehicle. Further, in the example of FIG. 7, the vehicle C1 is driven on the road L1 by the driver D1 and is equipped with the dorareco device 10-1. Further, in the example of FIG. 7, the vehicle C2 is driven on the road L2 by the driver D2, and is equipped with the dorareco device 10-2. Further, in the example of FIG. 7, the vehicle C3 is driven on the road L3 by the driver D3, and is equipped with the dorareco device 10-3. When it is not necessary to distinguish the dorareco device 10-1, 10-2, 10-3, it is simply referred to as the dorareco device 10.

Then, when each of the vehicle C1, vehicle C2, and vehicle C3 dorareco devices 10 is in the process of imaging (recording), for example, the imaging data (moving image data) sample obtained by the imaging is constantly informed. It is transmitted to the processing device 100. On the other hand, each Dora-Reco device 10 may collectively transmit the imaging data samples obtained during this period to the information processing device 100 at certain periods (for example, one day or one week). That is, the timing at which the dorareco device 10 transmits the imaging data is not limited.

The information processing device 100 acquires (receives) the transmitted imaging data sample by transmitting the imaging data sample from each dorareco device 10, and stores the acquired imaging data sample in the imaging data storage unit 123 (step). S21). In the example of FIG. 7, the dorareco device 10-1 transmits the imaging data VG1 as the imaging data sample. Therefore, the information processing device 100 acquires the image pickup data VG1 from the dorareco device 10-1 and stores it in the image pickup data storage unit 123. In the example of FIG. 7, the imaging data VG1 is data showing only one scene (one frame), but the imaging data VG1 is actually a moving image length of 30 minutes (reproduction time 30 minutes). ) Has the concept of time. Further, in the example of FIG. 7, the dorareco device 10-2 transmits the imaging data VG2 as the imaging data sample. Therefore, the information processing device 100 acquires the image pickup data VG2 from the dorareco device 10-2 and stores it in the image pickup data storage unit 123. The imaging data VG2 also has the concept of time. Further, in the example of FIG. 7, the dorareco device 10-3 transmits the imaging data VG3 as the imaging data sample. Therefore, the information processing device 100 acquires the image pickup data VG3 from the dorareco device 10-3 and stores it in the image pickup data storage unit 123. The imaging data VG3 also has the concept of time. The internal configuration of the imaging data storage unit 123 will be described later.

In such a state, the information processing apparatus 100 acquires the correct answer label (step S22). The information processing device 100 acquires a portion tagged by hand with respect to the imaged data sample from the imaged data storage unit 123 as a correct label. Any method is used for this tagging method. For example, if the imaging data sample contains a line indicating a parking lot, the worker paints the line and tags the meaning of the colored portion. For example, the worker tags attributes such as "what kind of line" and "what kind of color" this part is. Further, for example, when a vehicle is parked in a parking lot, the line shows various imaging modes depending on the positional relationship between the line and the parked vehicle (the line is photographed in various shapes). .. Therefore, in each case where the worker shows various imaging modes under the influence of the vehicle in which the line is parked, "empty car when the line has this shape", "full car when the line has this shape", etc. Tagging.

Therefore, as an imaging mode of a predetermined imaged object, the worker can perform an imaging mode indicating how a line drawn on the road is imaged according to the positional relationship with the vehicle. The tagged part is designated as the correct label by tagging indicating the fullness status in each imaging mode. For example, the worker tags the shape indicated by the imaging mode and indicates the fullness status in each shape according to whether or not the shape of the line drawn on the road is a predetermined shape. By doing so, the tagged part is designated as the correct label. This point will be described with reference to an example of each sample data shown in FIG. 7.

In the imaging data VG1, the correct label CL11 is designated by tagging with the meaning that "the U-shaped white line is a parking lot, and in the case of an empty vehicle, the image is taken in a U-shaped appearance". This is an example of the correct answer data. In addition, the correct answer label CL12 means that "the straight white line near the pedestrian crossing is a stop line (not a parking lot), and the area near this straight white line is a parking / stopping prohibited area, so it is not subject to full / empty judgment". This is an example of correct answer data specified by tagging. In addition, the correct answer label CL13 says, "The straight white line near the traffic light is a stop line, and multiple lines are pedestrian crossings, and the area near these lines is a parking / stopping prohibited area, so it is not subject to full sky judgment." This is an example of correct answer data specified by tagging the meaning.

Further, in the imaging data VG2, the correct answer label CL21 is tagged with the meaning that "the U-shaped white line is a parking lot, and in the case of an empty vehicle, the image is captured in a U-shaped appearance". This is an example of the correct answer data specified by. In addition, the correct label CL22 says, "The white line of the key shape is a part of the parking lot, and when the car is full, it is imaged in a manner that looks like a key shape according to the positional relationship with the parked vehicle." This is an example of correct answer data specified by tagging the meaning.

Further, in the imaging data VG3, the correct answer label CL31 indicates that "the white object slightly visible behind the tire is a part of the white line indicating the parking area, and when the vehicle is full, the positional relationship with the parked vehicle is determined. This is an example of correct answer data specified by tagging with the meaning of "captured in such a manner accordingly". In addition, the correct label CL32 says, "The white line of the key shape is a part of the parking lot, and when the car is full, it is imaged in a manner that looks like a key shape according to the positional relationship with the parked vehicle." This is an example of correct answer data specified by tagging the meaning.

The correct label as described above is stored in the imaging data storage unit 123. Further, in the above example, an example in which a worker manually specifies a correct label by tagging is shown, but it takes a lot of time and effort because of the manual work. Therefore, this manual work may be automated or streamlined. As an example of this, the information processing device 100 combines unsupervised learning, semi-supervised learning, etc., determines rewards and punishments like reinforcement learning, and then learns while simulating with an algorithm to generate a model. You may. For this reason, the information processing apparatus 100 does not necessarily have to generate a model by supervised learning. In the following, the explanation will proceed as supervised learning.

Next, the information processing apparatus 100 generates a model in which the full sky condition is learned according to the image pickup mode of the imaged object by learning the full sky situation according to the image pickup mode of the imaged object (step S23). ). Specifically, the information processing apparatus 100 provides information in which an imaging mode of a predetermined imaged object is associated with an empty state of a predetermined parking place when the imaged object is imaged as shown by the imaging mode. To learn the full sky situation according to the imaging mode of the imaged object and generate a model. For example, the information processing device 100 generates a model in which the image pickup mode of the imaged object is learned as correct answer data according to the fullness condition of the parking place.

For example, as described in step S22, the information processing apparatus 100 indicates, as an imaging mode of the imaged object, what shape the line drawn on the road is imaged according to the positional relationship with the vehicle. By using the combination of the imaging mode and the fullness status in each imaging mode as the correct answer data, what kind of pattern the line is empty and what kind of pattern the line is empty are empty. And generate a model.

Further, for example, as described in step S22, the information processing apparatus 100 captures the image of the line drawn on the road in a shape according to the positional relationship with the vehicle as an imaging mode of the imaged object. By using the combination of the imaging mode showing the above and the fullness status in each imaging mode as correct answer data, what kind of pattern the line is empty and what kind of pattern the line is. Learn if the vehicle is full and generate a model.

Further, for example, the information processing apparatus 100 uses the correct answer data in which the time zone, the weather, the illuminance of the surroundings, and the like are further combined as elements to determine what pattern and color the line is when the vehicle is empty. It learns what kind of pattern and color the line is full and generates a model. Further, for example, the information processing device 100 also learns what kind of shape (pattern) line is the parking lot line by learning the information about the prohibited area where the parking / stopping of the vehicle is prohibited. Generate a model.

Further, the information processing apparatus 100 receives an object (object to be copied to the imaged data) when the imaged data from the vehicle to be processed to be notified of the determination result of the fullness determination is input by the above learning. For example, it is a score based on the degree of agreement between the shape (pattern) of the line drawn on the road and the shape (pattern) of the line indicated by the imaging mode as correct data, and the accuracy regarding the availability of the parking place. Generate a model that outputs a score indicating. The generated model is stored in a predetermined storage unit in the information processing apparatus 100. The information processing device 100 may have position information in the storage unit indicating in which area the parking place exists among the areas in which the road is virtually divided in a mesh shape. In such a case, the information processing device 100 may generate a model learned based on the imaged data sample of the area for each area where the parking place exists.

Further, any known technique can be applied to the model learning method. For example, model generation may be performed using various prior arts related to machine learning as appropriate. For example, model generation may be performed using a technique related to machine learning of supervised learning such as SVM (Support Vector Machine). Further, for example, model generation may be performed using a technique related to machine learning of unsupervised learning. For example, model generation may be performed using a technique of deep learning. For example, the model may be generated by appropriately using various deep learning techniques such as RNN (Recurrent Neural Network) and CNN (Convolutional Neural Network). The description regarding the generation of the model is an example, and the generation of the model may be performed by a learning method appropriately selected according to the information that can be acquired and the like.

Next, the information processing device 100 performs a determination process for determining the availability of the parking place for the vehicle to be processed, and determines whether or not it is the timing to notify the determination result (step S24). The vehicle to be processed may be any vehicle as long as it has the dorareco device 10. Here, as the vehicle to be processed, a vehicle C5 (driving by the driver D5) traveling on the road L5 will be taken as an example. For example, in the information processing device 100, when the driving mode of the vehicle C5 satisfies a predetermined condition (for example, when the speed becomes slower than the predetermined speed), or when the physical behavior of the driver D10 satisfies the predetermined condition. (For example, when a behavior of looking left and right such as shaking the head is taken), it is determined that the timing is the above. If the information processing apparatus 100 determines that the timing is not the same (step S24; No), the information processing apparatus 100 waits until the condition is satisfied. On the other hand, when the information processing apparatus 100 determines that the timing is such (step S24; Yes), the information processing apparatus 100 performs the process of step S25.

Next, the information processing apparatus 100 executes a fullness determination for determining the fullness status of the parking place for the parking meter existing on the road L5, for example, based on the target imaging data acquired in step S25 (step S26). ). Then, the information processing device 100 notifies the driver D5 of the vehicle C5 to be processed of the determination result of the fullness determination (step S27). For example, the information processing apparatus 100 generates a statistical model in step S14 by accumulating the vacancy information regarding the vacancy status determined by the vacancy determination in step S26 in the vacancy information storage unit 121. can do.

Here, since the imaging data according to the embodiment is a moving image, it is composed of, for example, dozens of image data in one second. Therefore, the fact that the information processing apparatus 100 continuously acquires the image data in real time means that the image data that changes according to the traveling of the vehicle and the passage of time during the traveling is continuously acquired. Therefore, for example, image data GP5-1, image data GP5-2, and image data GP5-3 are given as examples of target imaging data sequentially acquired from the drareco device 10-5 of the vehicle C5. In other words, the target imaging data as a moving image sequentially acquired from the dorareco device 10-5 is composed of the image data GP5-1, the image data GP5-2, and the image data GP5-3.

Further, it is assumed that the image data GP5-1 is data captured at a predetermined time t1 when the vehicle C5 is traveling on the road L5. Further, it is assumed that the image data GP5-2 is data captured at a predetermined time t2 when the vehicle C5 is traveling on the road L5. Further, it is assumed that the image data GP5-3 is data captured at a predetermined time t3 when the vehicle C5 is traveling on the road L5.

First, an example of image data GP5-1 will be described. When the information processing device 100 acquires the image data GP5-1, the information processing device 100 inputs the image data GP5-1 into the model, so that the parking lot shown in the image data GP5-1 is a probability that the parking lot is empty (vacant vehicle rate). ) Is calculated. Based on the correct answer data, the information processing device 100 determines what kind of line is the parking lot line, and when this line is the parking lot line, what kind of line is in accordance with the positional relationship with the nearby vehicle. It is learning whether the vehicle is empty or full when the image is taken in the mode. Therefore, the information processing apparatus 100 does not perform the full / empty determination when no line is projected on the image data GP5-1. On the other hand, when the line of the parking lot is projected on the image data GP5-1, the information processing apparatus 100 calculates the probability that the parking lot is empty by using the model for the parking lot corresponding to this line. Calculating the probability of being empty can be rephrased as calculating the probability of being full (full rate).

For example, when the information processing device 100 calculates a probability of a predetermined value (for example, 90%) or more for the parking lot shown in the image data GP5-1, the information processing device 100 determines that the parking place is empty. When the probability of being less than a predetermined value (for example, 3%) is calculated, it is determined that the parking place is full. After that, as will be described in detail with reference to FIG. 8, the parking lot shown in the image data GP6-1 is full because the vehicle C100 is parked. Therefore, in such an example, the information processing device 100 calculates the probability that the vacancy rate is 3% or less for the parking lot in which the vehicle C100 is parked. Then, the information processing device 100 determines that the parking lot in which the vehicle C100 is parked is full.

In such a case, in step S27, the information processing device 100 notifies the driver D5 of information indicating that the parking lot in which the vehicle C100 is parked is full via the dorareco device 10-5. For example, the information processing device 100 indicates that the parking lot in which the vehicle C100 is parked is full with respect to the image data GP5-1 currently displayed on the display screen D of the dorareco device 10-5. Are superimposed and displayed. As will be described later with reference to FIG. 8, as an example, the information processing apparatus 100 uses the full information IF100 as a rectangular frame line associated with the characters “full” in the parking lot where the vehicle C100 is parked. It is displayed so as to surround it.

Next, an example of the image data GP5-2 will be described. Similarly, when the information processing device 100 acquires the image data GP5-2, the information processing device 100 inputs the image data GP5-2 into the model, so that the parking lot shown in the image data GP5-2 is probable to be empty. (Vacancy rate) is calculated. For example, when the line of the parking lot is projected on the image data GP5-2, the information processing apparatus 100 calculates the probability that the parking lot is empty by using the model for the parking lot corresponding to this line.

For example, when the information processing device 100 calculates a probability of a predetermined value (for example, 90%) or more for the parking lot shown in the image data GP5-2, the information processing device 100 determines that the parking place is empty. When the probability of being less than a predetermined value (for example, 3%) is calculated, it is determined that the parking place is full. In the example of FIG. 8 below, the vehicle C110 is parked in the front parking section shown in the image data GP5-2, and is therefore full. Therefore, the information processing device 100 calculates the probability that the vacancy rate is 3% or less for the parking section in which the vehicle C110 is parked. Then, the information processing device 100 determines that the parking section in which the vehicle C110 is parked is full.

Further, according to the example of FIG. 8, in the image data GP5-2, there is a parking lot for one vehicle between the vehicle C110 and the vehicle C120, and no vehicle is parked in the parking lot. Therefore, the information processing device 100 calculates the probability that the vacancy rate is 90% or more for this parking section existing between the vehicle C110 and the vehicle C120. Then, the information processing device 100 determines that this parking section existing between the vehicle C110 and the vehicle C120 is an empty vehicle.

In the above case, in step S27, the information processing device 100 provides information indicating that the parking lot in which the vehicle C110 is parked is full, and the parking lot existing between the vehicle C110 and the vehicle C120. The driver D5 is notified of the information indicating that the vehicle is empty via the dorareco device 10-5. For example, the information processing device 100 superimposes the full information and the empty vehicle information on the image data GP5-2 currently displayed on the display screen D of the dorareco device 10-5. As will be described later with reference to FIG. 8, as an example, the information processing apparatus 100 uses the full information IF110 as a rectangular frame line associated with the characters “full” in the parking lot where the vehicle C110 is parked. It is displayed so as to surround it. Further, the information processing device 100 displays the empty vehicle information IF 115 as a rectangular frame line associated with the character "empty" so as to surround the parking lot existing between the vehicle C110 and the vehicle C120.

Next, an example of image data GP5-3 will be described. Similarly, when the information processing device 100 acquires the image data GP5-3, the information processing device 100 inputs the image data GP5-3 into the model, so that the parking lot shown in the image data GP5-3 is probable to be empty. (Vacancy rate) is calculated. For example, when the line of the parking lot is projected on the image data GP5-3, the information processing apparatus 100 calculates the probability that the parking lot is empty by using the model for the parking lot corresponding to this line.

For example, when the information processing device 100 calculates a probability of a predetermined value (for example, 90%) or more for the parking lot shown in the image data GP5-3, the information processing device 100 determines that the parking place is empty. When the probability of being less than a predetermined value (for example, 3%) is calculated, it is determined that the parking place is full. In the example of FIG. 8 below, the parking lot shown in the image data GP5-3 is full because the vehicle C120 is parked. Therefore, the information processing device 100 calculates the probability that the vacancy rate is 3% or less for the parking section in which the vehicle C120 is parked. Then, the information processing device 100 determines that the parking section in which the vehicle C120 is parked is full.

In such a case, in step S27, the information processing device 100 notifies the driver D5 of information indicating that the parking lot in which the vehicle C120 is parked is full via the dorareco device 10-5. For example, the information processing device 100 superimposes the full information on the image data GP5-3 currently displayed on the display screen D of the dorareco device 10-5. As will be described later with reference to FIG. 5, as an example, the information processing apparatus 100 uses the full information IF120 as a rectangular frame line associated with the characters “full” in the parking lot where the vehicle C120 is parked. It is displayed so as to surround it.

From here, the notification examples described in the image data GP5-1, the image data GP5-2, and the image data GP5-3 will be described again with reference to FIG. FIG. 8 is a diagram showing an example of notifying the determination result in the full / empty determination. As shown in FIG. 8, the dorareco device 10-5 of the vehicle C5 to be processed receives the notification of the determination result in step S27 and displays the information indicating the fullness status on the display screen D. For example, the dorareco device 10-5 superimposes and displays the determination result for the imaged data at that time according to the imaged data that changes sequentially with the passage of time (step S28).

The image data GP5-1 shown in FIG. 8A is the data captured at a predetermined time t1 when the vehicle C5 is traveling on the road L5 among the moving image data that changes with the passage of time. is there. For example, the dorareco device 10-5 receives a notification (display instruction) from the information processing device 100 and receives a notification (display instruction) from the image data GP5-1 displayed at the current time (time t1) on the display screen D of the own device. , The parking lot in which the vehicle C100 is parked is overlaid with full information indicating that the vehicle is full. As shown in FIG. 8A, the dorareco device 10-5 uses, for example, the full information IF100 as a rectangular frame line associated with the character "full", and the parking section in which the vehicle C100 is parked. Display by enclosing. For example, the dorareco device 10-6 continues to display the full information IF100 until the parking section is completely out of the imaging range due to the traveling of the vehicle C5.

The image data GP5-2 shown in FIG. 8B is, among the moving image data that changes with the passage of time, data captured at a predetermined time t2 when the vehicle C5 is traveling on the road L5. is there. For example, the dorareco device 10-5 receives a notification (display instruction) from the information processing device 100 and receives a notification (display instruction) from the image data GP5-2 displayed at the current time (time t2) on the display screen D of the own device. , Information indicating that the parking lot in which the vehicle C110 is parked is full, and information indicating that the parking lot existing between the vehicle C110 and the vehicle C120 is empty are superimposed and displayed. As shown in FIG. 8B, the dorareco device 10-5 uses, for example, the full information IF110 as a rectangular frame line associated with the character "full", and the parking section in which the vehicle C110 is parked. Display by enclosing. Further, the dorareco device 10-5 displays the vacant vehicle information IF115 as a rectangular frame line associated with the character "empty" so as to surround the parking lot existing between the vehicle C110 and the vehicle C120. For example, the dorareco device 10-5 continues to display the full information IF 110 and the empty vehicle information IF 115 until these parking lots are completely out of the imaging range due to the traveling of the vehicle C5.

The image data GP5-3 shown in FIG. 8C is, among the moving image data that changes with the passage of time, data captured at a predetermined time t3 when the vehicle C5 is traveling on the road L5. is there. For example, the dorareco device 10-5 receives a notification (display instruction) from the information processing device 100 and receives a notification (display instruction) from the image data GP5-3 displayed at the current time (time t3) on the display screen D of the own device. , The parking lot in which the vehicle C120 is parked is overlaid with full information indicating that the vehicle is full. As shown in FIG. 8 (c), the dorareco device 10-5 provides, for example, the full information IF120 as a rectangular frame line associated with the character "full", and the parking section in which the vehicle C120 is parked. Display by enclosing. For example, the Dora-Reco device 10-6 continues to display the full information IF 120 until the parking lot is completely out of the imaging range due to the traveling of the vehicle C5.

The information processing device 100 starts full / empty determination for the detected parking lot when, for example, the line of the parking lot can be detected by matching the correct answer data with the target imaging data or by analyzing the moving image of the target imaging data. can do. As a result, the information processing device 100 notifies the determination result at the stage where, for example, the vehicle C5 is traveling in a position where the vehicle C5 and the parking zone are too far apart and the driver D5 cannot see the existence of the parking zone. can do. Further, in the information processing device 100, the vehicle C5 is traveling in a position where the existence of the information processing device 100 cannot be visually recognized because it is obstructed by another vehicle, such as a parking lot existing between the vehicle C110 and the vehicle C120. The determination result can be notified at the stage. In this way, the information processing device 100 can notify the determination result at a fairly early stage even if the driver does not approach a position where the existence of the parking zone can be completely visually recognized. It is possible to make a judgment as to whether or not it is possible.

As described with reference to FIGS. 4 and 5, the information processing apparatus 100 according to the embodiment performs a fullness determination for determining the fullness status of the empty vehicle place as the second information processing. Specifically, the information processing device 100 acquires the imaged data captured by the drive recorder of the vehicle. Then, the information processing device 100 determines in real time the fullness status of the parking place installed on the road, which is copied in the image pickup data, based on the acquired image pickup data. Then, the information processing device 100 notifies the driver (user) of the determination result in real time.

As a result, the information processing device 100 according to the embodiment is the fullness status of the parking place installed on the road, and the fullness status of the parking lot near the driving is accurately set in real time for the driver who is traveling. You can notify.

Further, since the information processing device 100 also learns information about the prohibited area where parking / stopping of the vehicle is prohibited, for example, the stop line in front of the signal and the pedestrian crossing are recognized as parking sections, and the fullness is determined. It is possible to avoid the situation where it ends up. Further, the information processing device 100 can also learn the area in front of a specific facility (for example, a store, a fire station, a police station) as a parking / stopping prohibited area. Therefore, for example, when a specific imaged object such as a line exists in front of these facilities, the information processing device 100 recognizes this as a parking zone and avoids a situation in which the sky is determined to be full. Can be done.

In addition, the camera of the dorareco device 10 can accurately perform an object placed in an environment where the information obtained by visual recognition is uncertain, such as in the dark or in bad weather, or in other rare environments. It may be recognizable. For these reasons, the present embodiment finds an advantage in using the imaging data. That is, the information processing device 100 can accurately and accurately notify the full vacancy status regardless of the surrounding environment of the vehicle.

Further, it was previously shown that the dorareco device 10 may operate independently as an example of the information processing device that performs the information processing according to the embodiment. In such a case, the dorareco device 10 may operate independently, for example. The vehicle in which the device is installed is set as the vehicle to be processed, and the processing in each step described with reference to FIGS. 7 and 8 is performed. Further, the dorareco device 10 does not generate a model by learning, and for example, acquires a model updated by using the imaged data samples collected up to that point from an external device (for example, the information processing device 100) at predetermined period intervals. You may.

Further, the information processing device 100 relates to payment by short-distance communication between the dorareco device 10 and the parking meter, and for example, bar code payment by the driver holding a bar code displayed on a terminal device such as a smartphone over the parking meter. It may have a function of performing payment processing. Further, when the dorareco device 10 operates independently, for example, even if the dorareco device 10 performs the payment process by transmitting the payment information acquired by the short-distance communication with the parking meter to a predetermined payment server or the like. Good.

Further, in the above example, the information processing apparatus 100 determines whether or not the image pickup mode of the line satisfies the predetermined condition as a predetermined image pickup image to be captured in the image pickup data, and determines the fullness status of the parking place. An example is shown. However, the information processing device 100 can also determine the fullness status of the parking place based on a predetermined object indicating that the parking place exists among the predetermined images captured in the image pickup data. For example, the information processing device 100 determines the availability of a parking place based on a parking meter or a sign (indicating a parking place) corresponding to the parking place as a predetermined object. In this case, for example, based on a model further learned as correct answer data, the information processing device 100, the parking meter when the parking lot is full and the parking lot is empty, or in what imaging mode the sign is imaged. Determine the availability of the parking lot to be processed.

Further, in the information processing device 100, when the parking meter or the sign is copied in the imaging data acquired from the vehicle to be processed to which the determination result is notified, the vehicle to be processed has a parking place for the parking meter. It is also possible to determine that the vehicle has entered an existing area and determine the availability of parking spaces existing in this area.

[3. Information processing device configuration]
Next, the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 9 is a diagram showing a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 9, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. For example, the information processing device 100 is a server device that performs information processing described with reference to FIGS. 1 to 8. On the other hand, the information processing according to the embodiment may be performed by the dorareco device 10 as a terminal device.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes a full / empty information storage unit 121, a statistical information storage unit 122, an imaging data storage unit 123, a parking location information storage unit 124, and a model storage unit 125. Since the full-empty information storage unit 121 and the statistical information storage unit 122 have already been described in FIGS. 2 to 4, the following description will be omitted.

(About the imaging data storage unit 123)
The imaging data storage unit 123 stores information related to imaging data obtained by imaging by the imaging means K or the camera (imaging means) of the dorareco device 10. Here, FIG. 10 shows an example of the imaging data storage unit 123 according to the embodiment. In the example of FIG. 10, the imaging data storage unit 123 has items such as "driver ID", "terminal ID", "date and time", "imaging data", and "correct label".

The "driver ID" indicates identification information that identifies the driver of the vehicle in which the dorareco device 10 is installed. Since the driver is the owner of the dorareco device 10, it can be paraphrased as a "user". The "terminal ID" indicates identification information that identifies the dorareco device 10. The "date and time" indicates the date and time when the "imaging data" was obtained. In the example of FIG. 10, a conceptual symbol such as "DT1" is used for the date and time, but in reality, for example, the date, date, and time information are input. The “imaging data” indicates the imaging data obtained by imaging with the camera (imaging unit) of the dorareco device 10. Since the "imaging data" is used as a sample for correct answer data for learning the information processing apparatus 100, for example, it corresponds to the imaging data sample shown in FIG. 7. Further, the "imaging data" is a moving image, and has a concept of time such as a moving image length of "10 minutes". The "correct answer label" is the correct answer data (teacher data) for machine learning specified by tagging the corresponding "imaging data".

That is, in the example of FIG. 10, the driver (driver D1) identified by the driver ID "D1" is the driver (driver D1), and the driver (driver D1) is identified by the terminal ID "10-1". , An example is shown in which the information processing apparatus 100 stores the "imaging data VG1", which is the imaging data (imaging data sample) acquired by imaging at the date and time "DT1", by transmitting the "imaging data VG1" to the information processing apparatus 100. .. Such an example corresponds to the description in FIG. Further, in the example of FIG. 10, as described with reference to FIG. 7, an example in which the correct answer label CL11, the correct answer label CL12, and the correct answer label CL13 are designated for the imaging data VG1 is shown.

Note that, for example, when the dorareco device 10-5 independently executes the second information processing according to the embodiment, the dorareco device 10-5 can have an imaging data storage unit 123 as shown in FIG. ..

(About parking place information storage unit 124)
The parking place information storage unit 124 stores information regarding the position (location) of a parking place (for example, a parking place for a parking meter) installed on the road. Here, FIG. 11 shows an example of the parking place information storage unit 124 according to the embodiment. In the example of FIG. 11, the parking place information storage unit 124 has items such as "prefecture", "city / ward / town / village", "road ID", "area", and "location information".

"Prefecture" and "city" indicate the prefecture and city including the position indicated by the corresponding "location information". The "road ID" indicates identification information that identifies the road. The "area" indicates identification information for identifying an area in which a parking place exists among the areas in which the road indicated by the "road ID" is virtually divided in a mesh shape. The "position information" is position information indicating the position of the corresponding "area". For this reason, the "location information" can be rephrased as the location information indicating the location of the parking place. In the example of FIG. 11, a conceptual symbol is used for "position information", but it is actually indicated by, for example, an address or latitude and longitude.

That is, in the example of FIG. 11, the position of "PTm1" in each area that is a road passing through M-ku, Tokyo and the road (road RT11) identified by the road ID "RT11" is virtually divided. An example is shown in which a parking place exists in the area "ARm2" at the positions of the areas "ARm1" and "PTm2" and the area "ARm3" at the position of "PTm3". That is, in the example of FIG. 6, an example in which a parking place exists at the position “PTm1”, the position “PTm2”, and the position “PTm3” on the road RT11 is shown.

(About model storage 125)
The model storage unit 125 is a storage unit that stores the model generated by the second information processing of the information processing device 100. The model storage unit 125 stores, for example, a "model ID" that identifies each model and model information indicating the model in association with each other.

(About control unit 130)
Returning to FIG. 9, in the control unit 130, various programs stored in the storage device inside the information processing device 100 are executed by the CPU (Central Processing Unit), the MPU (Micro Processing Unit), etc. using the RAM as the work area. It is realized by. Further, the control unit 130 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 9, the control unit 130 behaves with the acquisition unit 131, the generation unit 132, the fullness determination unit 133, the storage unit 134, the prediction unit 135, the notification unit 136, and the provision unit 137. It has a determination unit 138 and a start control unit 139, and realizes or executes the functions and actions of information processing described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 9, and may be any other configuration as long as it performs information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 9, and may be another connection relationship.

(About acquisition unit 131)
The acquisition unit 131 acquires the imaging data. For example, the acquisition unit 131 acquires image data captured by a camera (camera of the dorareco device 10) mounted on a moving body traveling on a road. For example, when the imaging data is transmitted from the dorareco device 10, the acquisition unit 131 acquires (receives) the imaging data from the dorareco device 10. In addition, the acquisition unit 131 stores the acquired imaging data in the imaging data storage unit 123.

The acquisition unit 131 does not necessarily have to acquire only the image data captured by the camera of the dorareco device 10. For example, a camera (for example, a security camera) installed in a facility (for example, a traffic light, a utility pole, an apartment, a store, etc.) in each place. ), It is possible to acquire the image data obtained by such a camera. Therefore, as an example of the processing, the acquisition unit 131 performs the processing of step S11 described with reference to FIG. 1 and step S21 described with reference to FIG. 7, for example.

(About generator 132)
The generation unit 132 generates a model by learning. The generation unit 132 generates a model learned from the information associated with the imaging mode of the predetermined imaged object and the fullness status of the parking place when the imaged object is imaged as shown by the imaging mode. To do. For example, the generation unit 132 generates a model in which the imaging mode of the imaged object is learned as the correct answer data according to the sky condition of the parking place. For example, the generation unit 132 draws on the road, which is the object to be copied to the image pickup data, when the image pickup data captured by the camera mounted on the moving body to be processed to which the determination result is notified is input. A model is generated that outputs a score indicating the accuracy of the availability of the parking place, which is a score based on the degree of agreement between the shape of the drawn line and the shape of the line indicated by the imaging mode as correct data.

In addition, the generation unit 132 can also generate a model in which information on the prohibited area where parking / stopping of the moving body is prohibited is further learned. For example, the generation unit 132 generates a model by learning information about a prohibited area where parking / stopping of a moving body is prohibited as correct answer data for not performing a full / empty determination. For this reason, the generation unit 132 performs, for example, the processes of steps S22 and S23 described with reference to FIG. 7 as one of the processes.

The generation unit 132 may also perform a process of generating a statistical model as described in step S14 of FIG. For example, the generation unit 132 learns the tendency by performing a tendency analysis (statistical tendency analysis) between the fullness situation and a predetermined condition (for example, day of the week, time zone, weather, event, etc.). Generate a statistical model that is the model that was created. For example, the generation unit 132 analyzes the tendency of the full sky condition under the weather "fine" (or weather "rain") condition in the time zone for each time zone of each day of the week, and learns the analyzed tendency. Generate a statistical model. Further, for example, the generation unit 132 analyzes and analyzes the tendency of the vacancy situation under the condition that an event (for example, construction or traffic jam) occurs in the time zone for each time zone of each day of the week. Generate a trained statistical model.

Incidentally, the model generation in steps S22 and S23 described in FIG. 7 and the generation of the statistical model described in step S14 in FIG. 1 may be performed by different processing units. For example, the former process may be performed by the second generation unit, and the latter process may be performed by the first generation unit.

(About the fullness judgment unit 133)
The fullness determination unit 133 determines the fullness status of the parking place installed on the road, which is captured in the image pickup data, based on the image pickup data acquired by the acquisition unit 131. For example, the fullness determination unit 133 determines the current fullness status of the parking place where the moving body having the dorareco device 10 is installed on the road where the moving body is currently traveling and exists in the traveling direction of the moving body. judge. For example, the fullness determination unit 133 determines the fullness status of the parking lot for each parking lot for parking one moving body as a parking place.

Further, the full / empty determination unit 133 determines the full / empty status of the parking place based on the imaging data, depending on whether or not the imaging mode of the predetermined image image imaged in the imaging data satisfies the predetermined conditions. To do. For example, the sky fullness determination unit 133 is an imaging mode that shows how a line drawn on the road is imaged according to the positional relationship with a moving body as an imaging mode of a predetermined imaged object. The availability of the parking place is determined according to whether or not the imaging mode of the line satisfies a predetermined condition. For example, the vacancy determination unit 133 determines the vacancy status of the parking place according to whether or not the shape of the predetermined imaged object is the shape indicated by the imaging mode.

As an example, the fullness determination unit 133 is learned by the information associated with the imaging mode of the predetermined imaged object and the fullness state of the parking place when the imaged object is imaged as shown by the imaging mode. Based on the model, the availability of the parking place to be processed is determined. For example, the fullness determination unit 133 determines the fullness status of the parking place to be processed based on the model learned as the correct answer data of the imaging mode according to the fullness status of the parking place among the imaging modes of the imaged object. judge. For example, the full / empty determination unit 133 is on the road, which is an object to be captured in the imaging data when the imaging data captured by the camera mounted on the moving object to be processed to which the determination result is notified is input. A score based on the degree of agreement between the shape of the line drawn in and the shape of the line indicated by the imaging mode as correct data, and based on a model that outputs a score indicating the certainty regarding the availability of the parking lot. Determine the availability of the parking lot. Further, the full / empty determination unit 133 determines the fullness status of the parking place in the area other than the prohibited area based on the model in which the information on the prohibited area where parking / stopping of the moving body is prohibited is learned. For this reason, the full / empty determination unit 133 performs the process of step S26 described in FIG. 7, for example, as an example of the process.

In addition, the full / empty determination unit 133 also performs a full / empty determination by analyzing the imaging data. For example, as described in step S12 of FIG. 1, the full / empty determination unit 133 has a parking lot for each “day of the week” and “time zone” corresponding to the imaging data, in the “day of the week” and “time zone”. Judge the fullness status for each area. For example, the full / empty determination unit 133 extracts the imaged data for each “time zone” for each “day of the week” from the imaged data, and analyzes the extracted imaged data to obtain the fullness status in each parking lot area. To judge. Then, the fullness determination unit 133 finally determines whether the parking lot area is full or empty during the "time zone" based on the determined fullness situation.

(About storage unit 134)
The storage unit 134 stores the fullness information indicating the fullness status of the parking lots installed on the road for each parking lot. For example, the storage unit 134 stores the fullness information indicating the fullness status determined based on the imaging data obtained by imaging the parking place by a predetermined imaging means as the fullness information. For example, the storage unit 134 stores the fullness information indicating the determination result (fullness status) in the fullness determination by the fullness determination unit 133. For example, the storage unit 134 stores such full-empty information in the full-empty information storage unit 121, so that the full-empty information storage unit 121 stores the full-empty information. For this reason, the full / empty determination unit 133 performs, for example, the process of step S13 described with reference to FIG. 1 as one of the processes.

(About prediction unit 135)
The prediction unit 135 predicts the fullness status of the parking place at the estimated arrival time when the moving object to be processed arrives at the parking place based on the fullness information accumulated by the storage unit 134. For example, the prediction unit 135 is statistical information for each parking place obtained based on the fullness information accumulated by the storage unit 134, and is based on the statistical information showing the statistics of the fullness situation under a predetermined condition. , Predict the availability of parking lots at the estimated arrival time. For example, the prediction unit 135 determines at least one of a day of the week, a time zone, the weather around the parking place, the presence or absence of traffic congestion around the parking place, and the presence or absence of an event around the parking place. Based on the statistical information obtained based on the fullness information showing the fullness status below, the fullness status of the parking place at the estimated arrival time is predicted.

More specifically, the prediction unit 135 is a parking lot for parking one moving object, and is arbitrary based on the parking lot in a parking place in which a plurality of parking lots are connected in one direction. For each area, it is statistical information for each parking place obtained based on the fullness information indicating the fullness status in the area, and based on the statistical information showing the fullness status statistics under a predetermined condition, Predict the full availability at the estimated arrival time.

For example, the prediction unit 135 uses the statistical information of the parking place at the estimated arrival time based on a statistical model in which the tendency-based relationship between the availability and the predetermined conditions is learned for each parking place. Predict the fullness situation. For example, the prediction unit 135 outputs information indicating the fullness status of the parking place at the estimated arrival time when the information indicating the estimated arrival time when the moving object to be processed arrives at the parking place is input as a statistical model. Based on the statistical model to be used, the availability of parking lots at the estimated arrival time is predicted.

In addition, the prediction unit 135 further uses statistical information showing statistics on the frequency of replacement of moving objects in the parking place as statistical information, and predicts the vacancy situation at the estimated arrival time. In addition, the prediction unit 135 is a parking place at an estimated arrival time when the vehicle arrives at a parking place within a predetermined range from the destination based on the position information indicating the destination specified by the user of the moving object to be processed. Predict the fullness situation of. For this reason, the prediction unit 135 performs, for example, the processes of steps S15 to S18 described with reference to FIG. 1 as one of the processes.

(About notification unit 136)
The notification unit 136 notifies the driver of the determination result by the full / empty determination unit 133. For example, the notification unit 136 is image data captured by a camera mounted on the moving body to be processed to which the determination result is notified, and is captured in the image data displayed in real time on the display screen for each parking place. To display the current availability status. For example, as described with reference to FIG. 8, the notification unit 136 displays full information as a rectangular frame line associated with the character “full” so as to surround the parking lot in which the vehicle is parked. Further, for example, as described in FIG. 2, the notification unit 136 displays vacant vehicle information as a rectangular frame line associated with the character "empty" so as to surround a parking lot in which the vehicle is not parked. .. For this reason, the notification unit 136 performs, for example, the process of step S27 described with reference to FIGS. 7 and 8 as one of the processes.

In addition, the notification unit 136 can also notify the user of information based on the prediction result predicted by the prediction unit 135. That is, the notification unit 136 can also perform the process of step S19 described with reference to FIGS. 1 and 5.

Specifically, the notification unit 136 is a parking lot for parking one moving body, and is an arbitrary parking lot based on the parking lot in a parking place in which a plurality of parking lots are connected in one direction. When the vacancy status in the area is predicted for each area, the user is notified of the information based on the vacancy status in the area. Further, when the notification unit 136 predicts that the parking place is full at the estimated arrival time when it arrives at one parking place existing within a predetermined range from the destination of the user (driver). Will guide you to a parking place that is within a predetermined range from this destination and is predicted to be empty as a full vacancy among other parking lots that are different from one parking place. It is also possible to notify the user of the guidance information.

Now, from here on, other notifications by the notification unit 136 will be described. For example, the information processing device 100 is full-empty information based on a moving body other than the moving body to be notified (the moving body to be processed to which the determination result is notified) to which the information is notified, and is the information of the parking place. The fullness information (judgment result) indicating the fullness status is acquired, and the acquired fullness information is notified to the moving object to be notified of the information. I will explain it more clearly. In the examples of FIGS. 7 and 8, the information processing apparatus 100 acquires the current imaging data from the drareco apparatus 10 of the vehicle C5 to be processed, determines whether the imaging data is full or empty, and superimposes the imaging data on the display screen. An example of notifying the judgment result (that is, full / empty information) is shown in. However, such a series of second information processing is, of course, performed not only on the vehicle C5 but also on many vehicles. For example, the same information processing is performed on the vehicle C6, which is another vehicle when viewed from the vehicle C5. Therefore, the notification described here is based on the imaging data from the vehicle C6, which is another vehicle when viewed from the vehicle C5, and the determination result when the fullness is determined with the vehicle C6 as a reference is used as the dorareco device 10 of the vehicle C5. This is a notification method in which the image data currently projected on the display screen of -5 is reflected.

The premise of making such a notification will be described. For example, according to the example of FIG. 8, the information processing device 100 determines the fullness of the parking section existing on the traveling lane side of the vehicle C5. However, if there is a parking zone on the opposite lane side of the vehicle C5 with respect to the traveling lane and this parking zone is captured in the imaging data, the information processing apparatus 100 can naturally determine that the parking zone is also full. it can. In short, the information processing device 100 can perform a full / empty determination if the parking zone is captured in the imaging data regardless of the traveling lane or the opposite lane of the vehicle to be processed to which the determination result is notified. .. However, since the dorareco device 10 basically tends to image mainly the information on the traveling lane side, the information on the opposite lane side (for example, whether or not there is a parking lot) is obtained from the imaging data. May not be recognized with high accuracy. Then, when the judgment result of the fullness judgment of the image data of the vehicle C6 traveling in the opposite lane is higher than the judgment result of the fullness judgment of the parking lot on the opposite lane side based on the image pickup data of the vehicle C5. There is. Therefore, if the determination result based on the vehicle C6 can also be notified to the driver D5 of the vehicle C5, the driver D5 can be notified of a more accurate full vacancy situation.

Based on the above assumptions, using the vehicle C5 and the vehicle C6 as an example, the information processing device 100 is a vehicle C6 which is a moving body other than the vehicle C5 to be notified of information, and is in the opposite lane. It is the full vacancy information based on the traveling vehicle C6, and acquires the full vacancy information indicating the full vacancy status of the parking lot. Then, the information processing device 100 (notification unit 136) notifies the driver D5 of the vehicle C5 of the acquired full / empty information. This point will be described with reference to FIG. FIG. 12 is a diagram showing another example of information notification.

In the example of FIG. 12, the vehicle C6 is traveling in the opposite lane to the vehicle C5 toward the vehicle C5. For this reason, since the vehicle C6 has already traveled at a point where the vehicle C5 can pass, it is possible to know the information at that point more accurately than when viewed from the vehicle C5 at the same time. For example, at time t4, the vehicle C6 can know the fullness of the two parking lots surrounded by the circles in FIG. 12 earlier than the vehicle C5. In other words, at the time t4, the information processing apparatus 100 can determine the fullness status of the above two vehicle sections more accurately from the image data of the vehicle C6 than from the image data of the vehicle C5.

For example, in the example of FIG. 12, the information processing device 100 identifies a vehicle other than the vehicle C5 to be notified, for example, a vehicle that has traveled at a point where the vehicle C5 can pass in the future. Suppose that vehicle C6 is specified as such a vehicle. Although not shown in FIG. 12, the information processing apparatus 100 may further have a processing unit (for example, a specific unit) that performs such specific processing. Then, at the time t4, which is the time specified in this way, for example, the vehicle C5 and the vehicle C6 are traveling in the positional relationship as shown in FIG.

In such a state, the acquisition unit 131 acquires the imaging data (image data GP5-4) at the time t4 from the dorareco device 10-5 of the vehicle C5 (step S31). Further, in step S31, the acquisition unit 131 also acquires the imaging data (image data) at the time t4 from the drive recorder device 10-6 of the vehicle C6. Next, the full / empty determination unit 133 makes a full / empty determination on the image data GP5-4 by applying the image data GP5-4 to the model (step S32). The details of the fullness determination will be omitted because they are as described in FIG. Further, in step S32, the full / empty determination unit 133 also determines the fullness of the image data from the dorareco device 10-6. For example, the determination result obtained by the full / empty determination of the image data from the dorareco device 10-6 is the determination result based on the vehicle C6.

For example, in the full / empty determination unit 133, the vehicle C200 is parked in the parking lot in front of the vehicle C5 among the two parking lots surrounded by the circles based on the image data from the dorareco device 10-6. It is assumed that the car is full and the parking lot behind is judged to be empty. Such a determination result is a determination result based on the vehicle C6.

Further, in such a case, the notification unit 136 acquires the determination result based on the vehicle C6 from, for example, the full / empty determination unit 133. Then, the notification unit 136 notifies the determination result based on the vehicle C6 and the determination result on the vehicle C5 side together (step S33). For example, the notification unit 136 indicates that the parking lot in front of the vehicle C200 is full and the parking lot behind it is empty as a determination result based on the vehicle C6. Is notified to the driver D5 via the dorareco device 10-5. For example, the notification unit 136 superimposes the full information indicating that the parking section in which the vehicle C200 is parked is full on the image data GP5-4 currently displayed on the display screen of the dorareco device 10-5. To display. As an example, the notification unit 136 displays the full information IF200 as a rectangular frame line associated with the character "full" so as to surround the parking lot in which the vehicle C200 is parked.

Further, the notification unit 136 superimposes and displays vacant vehicle information indicating that the parking lot behind is vacant on the image data GP5-4 currently displayed on the display screen of the dorareco device 10-5. As an example, the notification unit 136 displays the empty vehicle information IF210 as a rectangular frame line associated with the character "empty" so as to surround the parking lot.

FIG. 12A is a diagram reflecting the above-mentioned situation. The image data GP5-4 shown in FIG. 12A is the data captured at the time t4 when the vehicle C5 is traveling on the road L5 among the moving image data that changes with the passage of time. For example, the dorareco device 10-5 receives a notification (display instruction) from the notification unit 136, and receives a notification (display instruction) from the notification unit 136, and the vehicle with respect to the image data GP5-4 displayed at the current time (time t4) on the display screen of the own device. The parking lot in which the C200 is parked is overlaid with full information indicating that it is full. As shown in FIG. 12A, the dorareco device 10-5 uses, for example, the full information IF200 as a rectangular frame line associated with the character “full”, and the parking section in which the vehicle C200 is parked. Display by enclosing. For example, the dorareco device 10-5 continues to display the full information IF200 until the parking lot is completely out of the imaging range due to the traveling of the vehicle C5.

Further, for example, the dorareco device 10-5 receives a notification (display instruction) from the notification unit 136 with respect to the image data GP5-4 displayed at the current time (time t4) on the display screen of the own device. , The vacant vehicle information indicating that the parking lot behind is vacant is superimposed and displayed. As shown in FIG. 12A, the dorareco device 10-5 displays, for example, the empty vehicle information IF210 as a rectangular frame line associated with the character “empty” so as to surround the rear parking lot. For example, the dorareco device 10-5 continues to display the vacant vehicle information IF210 until the parking lot is completely out of the imaging range due to the traveling of the vehicle C5.

As described with reference to FIG. 12, the information processing apparatus 100 is full of sky based on a moving body other than the moving body to be notified (the moving body to be processed to be notified of the determination result) to be notified of information. It acquires fullness information (judgment result) indicating the fullness status of the parking place, and notifies the acquired fullness information to the moving body to be notified of the information. As a result, the information processing device 100 can notify the fullness status more accurately.

Further, in the example of FIG. 12, the information processing device 100 is used as a vehicle (a vehicle to be used for which full-empty information is used for the vehicle to be notified) as a vehicle that has traveled at a point where the vehicle to be notified can pass in the future. , An example of identifying a vehicle other than the vehicle to be notified and traveling in the oncoming lane is shown. Further, an example is shown in which the information processing device 100 notifies the vehicle to be notified of the fullness information indicating the fullness status of the parking place, which is the fullness information based on a vehicle other than the vehicle to be notified. It was. Here, the information processing device 100 is based on, for example, registration information for a predetermined car navigation service, in addition to specifying a vehicle traveling in the oncoming lane as a vehicle traveling at a point where the vehicle to be notified can pass in the future. Then, the roads and destinations that the vehicle to be notified can pass in the future are acquired, and the vehicles that are currently traveling near the roads and destinations that the vehicles to be notified can pass in the future are used for the use of full sky information. It may be specified as a vehicle. Further, the information processing device 100 acquires the fullness information indicating the fullness status of the parking place, which is the fullness information based on the vehicle specified in this way, and notifies the vehicle to be notified.

(About the provider 137)
The providing unit 137 provides the driver with information indicating the position of the parking place where the vehicle can be parked because the vehicle is empty. Assuming that such a parking place is the parking lot described above, for example, assuming that vehicles are parked before and after the parking lot, the driver may overlook this parking lot. Therefore, the providing unit 137 performs the above-mentioned processing. Specifically, the providing unit 137 is a parking place that is copied to the image pickup data based on the image pickup data, and is parked in the vicinity of a parking place where the vehicle can be parked because the vehicle is empty. The driver is provided with information indicating the position of the parking place based on the position of the vehicle. Further, when the feature of the parked vehicle is recognized based on the image pickup data, the providing unit 137 further uses the recognized feature to provide the driver with information indicating the position of the parking place. This point will be described with reference to the example of FIG. 8B.

According to the example of FIG. 8B, when the vehicle C5 is traveling on the road L5 at time t2, the vehicle C110 and the vehicle S120 are parked in front, and an empty vehicle is parked between these vehicles. There is a parcel. Here, such a parking lot is referred to as a parking lot SP1. Then, at the time t2, the driver D5 may not be able to clearly grasp the position of the parking lot SP1 because of being disturbed by the front and rear vehicles C110 and S120. Therefore, for example, the providing unit 137 provides the driver with information indicating the position of the parking lot SP1 based on the position of the vehicle C120 parked in front of the parking lot SP1 and using the characteristics of the vehicle C120. Provide (notify) to. In this example, for the sake of simplicity, the provision example using only the vehicle C120 is shown, but information provision may be performed in which both the vehicle C110 and the vehicle C120 or only the vehicle C110 is used.

Returning to the description, for example, a predetermined processing unit (for example, a recognition unit) of the information processing device 100 indicates that the vehicle C120 is parked in front of the parking lot SP1 based on the image data GP5-2. It is assumed that the vehicle C120 is recognized as a white (color characteristic) one-box car (vehicle type characteristic). In such a case, the providing unit 137 causes the dorareco device 10-5 to output character information or voice such as "the back of the white one-box car that can be seen in front is empty".

It should be noted that this is an example, and when the providing unit 137 recognizes a characteristic object (for example, various facilities such as plants, signals, stores, etc.) as a feature of the surrounding environment of the parking lot SP1. , These features can be further used to provide information pointing to the location of the parking compartment SP1. Further, the providing unit 137 selects and selects a feature that has a higher visibility rate of the driver D5 among the recognized features according to the time zone at that time (for example, time t2) or the weather. Can also be used to provide information indicating the position of the parking lot SP1.

(About behavior judgment unit 138 and start control unit 139)
Here, for example, when the information processing device 100 constantly notifies the fullness determination or the determination result in the fullness determination, the display screen of the dorareco device 10 displays the fullness information or the empty vehicle information as a rectangular frame line. It may be displayed frequently. In this case, such a display may be annoying for drivers who do not plan to park in the parking lot. Therefore, the information processing device 100 determines whether or not the behavior related to the operation of the moving body satisfies the predetermined condition, and when it is determined that the predetermined condition is satisfied, the vacancy status of the predetermined parking place is determined. Start the process related to the notification of the parking place that is empty. For example, the information processing device 100 determines whether or not the driver is trying to park in the parking lot, and only in a situation where the driver is looking for an empty parking lot, a process related to notification of the parking lot (fullness determination). And the process of notifying the judgment result in the full / empty judgment) is started.

Specifically, the behavior determination unit 138 determines whether or not the behavior related to the driving of the vehicle satisfies a predetermined condition. Then, when the behavior determination unit 138 determines that the predetermined condition is satisfied, the start control unit 139 starts a process related to notification of the parking zone (a process of notifying the determination result in the full vacancy determination or the full vacancy determination). For example, when the behavior determination unit 138 determines that the predetermined condition is satisfied, the start control unit 139 instructs the fullness determination unit 133 to start the fullness determination.

Taking the vehicle C5 to be processed as an example, for example, the behavior determination unit 138 determines whether or not the speed of the vehicle C5 is slower than a predetermined speed as the behavior related to the driving of the vehicle C5, and the start control unit 139. When the behavior determination unit 138 determines that the speed of the vehicle C5 is slower than the predetermined speed, causes the fullness determination unit 133 to start the fullness determination.

Further, the behavior determination unit 138 determines whether or not the driving mode when the driver D5 is driving the vehicle C5 has become a predetermined driving mode as the behavior related to the driving of the vehicle C5, and the start control unit 139 determines. When the behavior determination unit 138 determines that the driving mode is a predetermined driving mode (for example, driving the vehicle C5 closer to the side of the road or orbiting the same area), the fullness determination unit 133 Is started to be full.

Further, the behavior determination unit 138 determines whether or not the physical behavior when the driver D5 is driving the vehicle C5 has become a predetermined behavior as the behavior related to the driving of the vehicle C5, and the start control unit 139 determines whether or not the behavior is a predetermined behavior. , When the behavior determination unit 138 determines that the physical behavior of the driver D5 is a predetermined behavior (for example, a behavior of moving the face left and right to look around, an utterance such as "Is there somewhere empty?"). Causes the fullness determination unit 133 to start the fullness determination.

For example, the determination process shown in step S24 of FIG. 7 corresponds to the determination process performed by the behavior determination unit 138.

[4. Processing procedure (1)]
Next, with reference to FIG. 13, the procedure of the first information processing among the information processing according to the embodiment will be described. FIG. 13 is a flowchart showing a processing procedure of the first information processing according to the embodiment.

First, the acquisition unit 131 acquires the imaging data captured by the imaging means K (for example, the camera of the security camera or the dashcam device 10) (step S101).

Next, the full / empty determination unit 133 performs a full / empty determination to determine the fullness status of the parking place captured in the imaged data based on the imaged data acquired by the acquisition unit 131 (step S102).

Next, the storage unit 134 stores the fullness information based on the determination result (fullness status) in step S102 in the fullness information storage unit 121 (step S103). For example, the storage unit 134 indicates to the full / empty information storage unit 121 the fullness status for each “day of the week” and “time zone” and for each parking area in the “day of the week” and “time zone”. Empty information is stored in the full empty information storage unit 121.

Next, the generation unit 132 determines the tendency by performing a trend analysis (statistical trend analysis) between the full sky condition and a predetermined condition (for example, day of the week, time zone, weather, event, etc.). A statistical model, which is a trained model, is generated (step S104). For example, the generation unit 132 analyzes the tendency of the full sky condition under the weather "fine" (or weather "rain") condition in the time zone for each time zone of each day of the week, and learns the analyzed tendency. Generate the model. Further, for example, the generation unit 132 analyzes and analyzes the tendency of the vacancy situation under the condition that an event (for example, construction or traffic jam) occurs in the time zone for each time zone of each day of the week. Generate a trained model.

Next, the prediction unit 135 acquires the estimated arrival time when the vehicle to be processed arrives at the destination (step S105). For example, the prediction unit 135 may acquire the estimated arrival time when the vehicle to be processed arrives at the destination by accessing the external server device that provides the car navigation system Z, or the prediction unit 135 may acquire the estimated arrival time based on the destination. The estimated arrival time may be acquired (calculated) on the side.

In addition, the prediction unit 135 provides a statistical information storage unit that provides an optimal statistical model for predicting the availability of parking places existing in the vicinity of the destination at the estimated arrival time when the vehicle to be processed arrives at the destination. Extract from 122 (step S106). Then, the prediction unit 135 inputs the estimated arrival time to the statistical model extracted in step S106, and predicts the fullness situation at this estimated arrival time based on the output fullness information (step S107). ..

Next, the notification unit 136 notifies the driver of the vehicle to be processed of the prediction result in step S107 (step S108). For example, the notification unit 136 notifies information indicating the fullness status in the parking lot area for each parking lot area. For example, the notification unit 136 causes the drareco device 10 of the vehicle to be processed to output information (for example, screen display or voice output) indicating the fullness status in the parking lot area.

[5. Processing procedure (2)]
Next, the procedure of the second information processing among the information processing according to the embodiment will be described with reference to FIG. FIG. 14 is a flowchart showing a processing procedure of the second information processing according to the embodiment. In the example of FIG. 14, the information processing device 100 collects imaging data (imaging data sample) as a sample for learning from the drareco device 10 of a vehicle traveling in various places, and uses the collected imaging data sample. It is assumed that the model has been generated. When the information processing apparatus 100 acquires (collects) an imaging data sample at any time, the imaging data acquired by the predetermined timing at each predetermined timing (for example, every one week elapses). The samples can be used to update the models generated so far.

First, the behavior determination unit 138 performs a determination process for determining the availability of the parking place for the vehicle to be processed, and determines whether or not it is the timing to notify the determination result (step S201). For example, the behavior determination unit 138 determines whether or not the driving behavior of the vehicle to be processed satisfies a predetermined condition. When the behavior determination unit 138 determines that the driving behavior of the vehicle to be processed does not satisfy the predetermined condition (step S201; No), it determines that it is not the timing to perform the processing, and the predetermined condition is satisfied. Wait until On the other hand, when the behavior determination unit 138 determines that the driving behavior of the vehicle to be processed satisfies the predetermined condition (step S201; Yes), it determines that it is the timing to perform the processing, and starts this determination result. Output to the control unit 139. Further, when the behavior determination unit 138 determines that the predetermined condition is satisfied (step S201; Yes), the start control unit 139 notifies the vehicle to be processed of the determination result in the fullness determination or the fullness determination. Control to start the process.

In response to such control, the acquisition unit 131 acquires imaging data (target imaging data) from the vehicle to be processed (step S202). For example, the acquisition unit 131 acquires the target imaging data obtained by imaging from the dorareco device 10 of the vehicle to be processed. More specifically, the acquisition unit 131 acquires the target imaging data captured in real time while the vehicle to be processed is traveling.

Next, the full / empty determination unit 133 executes, for example, a full / empty determination for determining the fullness status of the parking place captured in the target imaging data based on the target imaging data acquired in step S202 (step S203). ). For example, the vacancy determination unit 133 executes a vacancy determination for determining the vacancy status of the parking zone for each parking zone. For example, the full / empty determination unit 133 has the probability output by inputting the target imaging data into the model, and is the probability that the parking lot to be copied to the target imaging data is empty, or is copied to the target imaging data. The availability of the parking lot is determined based on the probability that the parking lot is full.

Next, the notification unit 136 notifies the driver of the vehicle to be processed of the determination result of the fullness determination (step S204). For example, the notification unit 136 controls the dorareco device 10 of the vehicle to be processed to display full information and empty vehicle information for each parking section copied in the current imaging data.

[6. Hardware configuration]
Further, the information processing apparatus 100 according to the above embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 15 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program that depends on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the communication network 50 and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the communication network 50.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the communication network 50.

[7. Others]
Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

The embodiments of the present application have been described in detail with reference to some drawings, but these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to carry out the present invention in other improved forms.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

1 Information processing system 10 Dorareko device 100 Information processing device 120 Storage unit 121 Full / empty information storage unit 122 Statistical information storage unit 123 Imaging data storage unit 124 Parking location information storage unit 125 Model storage unit 130 Control unit 131 Acquisition unit 132 Generation unit 133 Full / empty judgment unit 134 Accumulation unit 135 Prediction unit 136 Notification unit 137 Providing unit 138 Behavior judgment unit 139 Start control unit

Claims (15)

A storage unit that accumulates fullness information indicating the fullness status of parking places installed on the road for each parking place, and
It is characterized by having a prediction unit that predicts the fullness status of the parking place at the estimated arrival time when the moving body to be processed arrives at the parking place based on the fullness information accumulated by the storage unit. Information processing device. The storage unit is characterized in that, as the fullness information, the fullness information indicating the fullness status determined based on the imaging data obtained by imaging the parking place by a predetermined imaging means is accumulated. The information processing apparatus according to claim 1. The accumulating unit is characterized in that, as the predetermined imaging means, it accumulates the vacancy information indicating the vacancy status determined based on the imaging data imaged by a camera mounted on a moving body. 2. The information processing apparatus according to 2. The prediction unit is statistical information for each parking place obtained based on the fullness information accumulated by the storage unit, and is based on statistical information showing statistics of the fullness situation under a predetermined condition. The information processing device according to any one of claims 1 to 3, wherein the vacancy status of the parking place at the estimated arrival time is predicted. The prediction unit has at least one of the day, time zone, weather around the parking place, presence / absence of congestion around the parking place, and presence / absence of an event around the parking place, as the predetermined conditions. The fourth aspect of claim 4 is to predict the fullness of the parking place at the estimated arrival time based on the statistical information obtained based on the fullness information indicating the fullness under the conditions. The information processing device described. As the statistical information, the prediction unit uses a statistical model in which a tendency-based relationship between the fullness condition and the predetermined condition is learned for each parking place at the estimated arrival time. The information processing device according to claim 4 or 5, wherein the availability of the parking place is predicted. When the information indicating the estimated arrival time when the moving object to be processed arrives at the parking place is input as the statistical model, the prediction unit provides information indicating the fullness status of the parking place at the estimated arrival time. The information processing apparatus according to claim 6, wherein the fullness status of the parking place at the estimated arrival time is predicted based on the statistical model that outputs the above. The prediction unit is a parking lot for parking one moving body, and in the parking place where a plurality of parking lots are connected in one direction, for each arbitrary area based on the parking lot. , Statistical information for each parking place obtained based on the fullness information indicating the fullness status in the area, and based on the statistical information indicating the fullness status statistics under the predetermined conditions. The information processing apparatus according to any one of claims 4 to 7, wherein the fullness situation at the estimated arrival time is predicted. The claim is characterized in that the prediction unit further uses, as the statistical information, statistical information indicating statistics of the frequency of replacement of moving objects in the parking place, and predicts a full vacancy situation at the estimated arrival time. The information processing apparatus according to any one of 4 to 8. The prediction unit is based on the position information indicating the destination specified by the user of the moving object to be processed, and the parking place at the estimated arrival time to arrive at the parking place existing within a predetermined range from the destination. The information processing apparatus according to any one of claims 1 to 9, wherein the information processing apparatus is for predicting the fullness of the vehicle. The information processing device according to claim 10, further comprising a notification unit that notifies the user of information based on the prediction result predicted by the prediction unit. The notification unit is a parking lot for parking one moving body, and in the parking place where a plurality of parking lots are connected in one direction, for each arbitrary area based on the parking lot. The information processing apparatus according to claim 11, wherein when a full vacancy situation in the area is predicted, information based on the vacancy situation for each area is notified to the user. When the notification unit predicts that the parking place is full at the estimated arrival time when it arrives at one parking place within a predetermined range from the destination, the notification unit predicts that the parking place is full. Information to the user that guides the parking place to a parking place that is within a predetermined range and is predicted to be empty as a full vacancy among other parking places different from one parking place. The information processing apparatus according to claim 11 or 12, wherein the information processing apparatus is notified. It is an information processing method executed by an information processing device.
A storage process for accumulating fullness information indicating the fullness status of parking places installed on the road for each parking place, and
It is characterized by including a prediction step of predicting the fullness status of the parking place at the estimated arrival time when the moving object to be processed arrives at the parking place based on the fullness information accumulated by the accumulation step. Information processing method to do. An accumulation procedure for accumulating fullness information indicating the fullness status of parking places installed on the road for each parking place, and
To make a computer execute a prediction procedure for predicting the fullness status of the parking place at the estimated arrival time when the moving object to be processed arrives at the parking place based on the fullness information accumulated by the storage procedure. An information processing program featuring.

Images