JP2020030870A - Congestion prediction system, terminal, congestion prediction method, and congestion prediction program - Google Patents

Abstract

To predict congestion at an arbitrary location by collecting images of mobile objects on a road.SOLUTION: A congestion prediction device 100 collects images of mobile objects on a road captured by a plurality of terminals 110 and position information indicating positions at which the images were captured. An image processing unit 101 performs image processing on the collected images, and extracts traffic information, which is information relating to the mobile objects existing in the images. A traffic information processing unit 103 calculates information relating to congestion prediction for the road corresponding to the captured position using the traffic information extracted by the image processing unit 101, and generates congestion prediction information, which is then transmitted to the terminals 110.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a traffic congestion prediction system, a terminal device, a traffic congestion prediction method, and a traffic congestion prediction program for predicting traffic congestion using an image captured from a moving object. However, the use of the present invention is not limited to the congestion prediction system, the terminal device, the congestion prediction method, and the congestion prediction program.

  2. Description of the Related Art Conventionally, as a technique for predicting traffic congestion on a road, a server that determines a traffic congestion state at a vehicle position based on a speed from a vehicle and an average speed of the vehicle position has been disclosed (for example, see Patent Document 1 below). This technique also describes that an image captured by a vehicle is analyzed for use in determining traffic congestion.

  In addition, there is a system that determines traffic congestion using an image captured by a camera fixedly installed on a road.

JP 2011-134195 A

  However, with the above-described conventional technique, it was not possible to predict traffic congestion at an arbitrary location. Further, the configuration of the traffic congestion determination using an image has a problem that the installation cost is high and there is a limitation that only the traffic congestion determination can be performed in a place where the camera is fixedly installed.

In addition, it determines whether or not a section of the road on which the vehicle is traveling is congested based on information such as speed received from the vehicle, and cannot predict future congestion. There is. The problem to be solved by the present invention includes the above-mentioned problem as an example.

  In order to solve the above-mentioned problems and achieve the object, a traffic congestion prediction system according to the first aspect of the present invention provides an acquisition unit that acquires an image of a moving object on a road and position information indicating the position of the image, An image processing unit that extracts traffic information that is information on a moving object present in the image, and a traffic jam prediction on the road corresponding to a photographed position using the traffic information extracted by the image processing unit And a traffic information processing unit that calculates information about the traffic information.

  The terminal device according to claim 6, wherein the terminal transmits the image to a traffic congestion prediction device that predicts traffic congestion of the moving object on the road based on an image of the moving object on the road. An apparatus, an imaging unit that captures an image of a moving object on a road, and a processing unit that adds position information of the captured image to the image captured by the imaging unit and transmits the information to the traffic congestion prediction device. It is characterized by having.

  Further, the terminal device according to the invention of claim 7 is a terminal device connected to a traffic congestion prediction device that performs traffic congestion prediction of the moving object on the road based on an image of a moving object on the road, The information processing apparatus further includes a processing unit that requests the traffic congestion prediction device for traffic congestion including a desired position and time, and outputs information related to the traffic congestion prediction received from the traffic congestion prediction device.

  Further, the traffic congestion prediction method according to the invention of claim 8 is a traffic congestion prediction method performed by the traffic congestion prediction device, wherein an acquisition step of acquiring an image of a moving object on a road and position information indicating a position of the photographed object; An image processing step of extracting traffic information that is information on a moving object present in the image, and using the traffic information extracted in the image processing step, to predict traffic congestion on the road corresponding to a photographed position And a traffic information processing step of calculating information on the traffic information.

  According to a ninth aspect of the present invention, there is provided a traffic congestion prediction program for causing a computer to execute the above-described traffic congestion prediction method.

FIG. 1 is a block diagram illustrating a configuration example of a traffic congestion prediction system according to an embodiment. FIG. 2 is a flowchart illustrating an example of a processing procedure of the traffic congestion prediction system according to the embodiment. FIG. 3 is a block diagram illustrating an example of a hardware configuration of the navigation device. FIG. 4 is a block diagram illustrating an example of a hardware configuration of the server. FIG. 5 is a flowchart showing the content of processing of image transmission by the navigation device. FIG. 6 is a flowchart showing a process of generating traffic information by the server. FIG. 7 is a chart showing an example of the content of traffic information. FIG. 8 is a flowchart showing the process of congestion prediction using traffic information. FIG. 9 is a flowchart showing the processing contents from the traffic jam prediction request to the transmission of the traffic jam prediction information. FIG. 10 is an explanatory diagram showing a state of occurrence of natural congestion.

(Embodiment)
DESCRIPTION OF EMBODIMENTS Preferred embodiments of a traffic congestion prediction system, a terminal device, a traffic congestion prediction method, and a traffic congestion prediction program according to the present invention will be described below in detail with reference to the accompanying drawings.

  FIG. 1 is a block diagram illustrating a configuration example of a traffic congestion prediction system according to an embodiment. The traffic congestion prediction system according to the embodiment can be configured by a traffic congestion prediction device 100 and a terminal device 110 that are connected to each other by communication.

  The traffic congestion prediction device 100 includes an image processing unit 101, an information combining unit 102, a traffic information processing unit 103, a storage unit 104, and a traffic congestion prediction information management unit 105. The terminal device 110 includes an imaging unit 111, a positioning unit 112, and a processing unit 113.

  The traffic congestion prediction device 100 can be configured using, for example, a single server, but is not limited thereto, and may be configured to use a plurality of servers distributed according to functions of the image processing unit 101 and the traffic information processing unit 103.

  The terminal device 110 captures an image in front of the moving object by the imaging unit 111 and transmits the image to the traffic congestion prediction device 100. At this time, the processing unit 113 transmits the photographing ID and the position information at the time of photographing that has been measured by the positioning unit 112, together with the photographed image of the imaging unit 111. In addition, speed and time information during the movement may be transmitted. Further, the processing unit 113 requests the traffic congestion prediction device 100 to perform traffic congestion prediction by a user operation or the like, processes information of the traffic congestion prediction transmitted from the traffic congestion prediction device 100, and outputs the information to a display unit (not shown) or the like.

  The terminal device 110 transmits an image used for traffic congestion prediction to the traffic congestion prediction device 100 by using a navigation device provided on a mobile body, a smartphone or a mobile phone of a user, a portable personal computer, or the like. In addition, it is possible to request the traffic congestion prediction device 100 for traffic congestion prediction.

  Not limited to these, the terminal device 110 may be configured using a personal computer or the like fixedly installed in a home, a facility (store), or the like. In this case, the terminal device 110 omits the function of transmitting an image used for traffic congestion prediction to the traffic congestion prediction device 100, and requests the traffic congestion prediction device 100 for traffic congestion prediction. In the case of such a terminal device 110, the functions of the imaging unit 111 and the positioning unit 112 can be omitted, and the processing unit 113 of the terminal device 110 requests traffic congestion prediction by a user operation or the like, and is transmitted from the traffic congestion prediction device 100. The information of the predicted traffic congestion is output to a display unit or the like.

  The image processing unit 101 of the traffic congestion prediction device 100 performs image processing on a captured image transmitted from the terminal device 110. In this image processing, the road and the vehicle indicated by the captured image are extracted (detected). Then, the traveling lane (own lane) in which the terminal device 110 (moving body) is traveling, the number of lanes, the number of vehicles for each lane, and the distance between the vehicles are detected. In addition, the type of each vehicle included in the captured image can be detected.

  The information combining unit 102 stores the information on the shooting ID, shooting time, and shooting position of the shot image transmitted from the terminal device 110 in the storage unit 104 in association with each other. When the time of the traffic congestion prediction device 100 is used, the time at which the captured image is received can be used, and transmission of time information on the terminal device 110 side is unnecessary. Further, when the traffic congestion prediction device 100 knows the speed of the moving object provided with the terminal device 110, the traffic congestion prediction device 100 determines, for example, the amount of movement of the terminal device 110 in latitude and longitude and the required travel time. The speed of the moving object can be obtained by the calculation based on the speed.

  The information combining unit 102 associates (combines) the own lane information, which is the result of the image processing performed by the image processing unit 101, with the same shooting ID, and stores the traffic information in the storage unit 104 as traffic information. In addition, the information combining unit 102 stores vehicle information (the number of vehicles) for each lane for each shooting ID in the storage unit 104 as vehicle information for each lane. The traffic information is stored in the storage unit 104 in a state of being classified by road, position, and time zone.

  The traffic information processing unit 103 calculates the probability of occurrence of traffic congestion for each position and time zone using a statistical function for each of the road information stored in the storage unit 104 and each traffic information classified for each time zone, and predicts the traffic congestion. The information is stored in the storage unit 104 as information. The storage unit 104 stores traffic information based on changes in a plurality of captured images on the same road. The traffic information processing unit 103 stores the traffic information at the time of the request from the terminal device 110 in the past traffic information ( For example, the occurrence of congestion is predicted by comparing with the same time and place.

  The traffic information is not limited to information on the same road, but may be information within a predetermined range (another road).

  At this time, since traffic information for each lane is obtained based on the photographed image, the degree of traffic congestion is determined based on the number of vehicles (equivalent to the inter-vehicle distance and vehicle density) for each lane, and the traffic congestion prediction for each lane is made. It can be carried out.

  The congestion prediction information includes a future congestion prediction near the current position of the terminal device 110, a congestion prediction on a traveling route to the destination of the terminal device 110, a congestion prediction near the destination, and the like. The calculation processing of the traffic congestion prediction information may be calculated in advance for each road (location), or may be performed for the corresponding road (location) at the time of a request from the terminal device 110.

  Further, the traffic congestion prediction information is not limited to predicting traffic congestion for a road corresponding to the position where the image was captured. For example, a road closest to the photographed position information or a road on map information that has been subjected to map matching at the photographed timing may be used.

  The congestion prediction information management unit 105 manages congestion prediction information. The congestion prediction information management unit 105 transmits to the terminal device 110 the congestion prediction information of the position or the area corresponding to the request for the congestion prediction from the terminal device 110.

  For example, the terminal device 110 requests the traffic congestion prediction device 100 for traffic congestion prediction information in a predetermined area near a travel route or a destination when the moving object moves. In addition, at the time of the route search by the moving body, similarly, it requests the traffic congestion prediction information in a predetermined area near the traveling route or the destination. In response to this, the traffic congestion prediction device 100 can extract the traffic congestion prediction information in a predetermined area near the terminal device 110 (mobile) travel route or destination and transmit the information to the terminal device 110.

  FIG. 2 is a flowchart illustrating an example of a processing procedure of the traffic congestion prediction system according to the embodiment. The processing content of traffic congestion prediction performed by the traffic congestion prediction device 100 is shown. First, the traffic congestion prediction device 100 acquires a captured image and positional information, speed, and time at the time of capturing from the terminal device 110 (step S201). As described above, the speed and the time can be obtained without receiving from the terminal device 110.

  Next, the traffic congestion prediction device 100 performs image processing on the captured image (step S202). By this image processing, the traveling lane (own lane), the number of lanes, the number of vehicles for each lane, the type of each vehicle, and the distance between the vehicles are detected. The detected information is associated (combined) with the information (position information, speed, time) acquired in step S201, and traffic information is generated and stored in the storage unit 104.

  The same or different plurality of terminal devices 110 transmit a plurality of captured images to the traffic congestion prediction device 100 at different locations and times. In this way, the traffic congestion prediction device 100 repeatedly executes steps S201 and S202, so that a large number of traffic information is stored in a database for each road location and time. The traffic congestion prediction device 100 performs the following traffic congestion prediction processing using the traffic information.

  Next, the traffic congestion prediction device 100 waits for a request for traffic congestion prediction from the terminal device 110 (step S203: No loop). When a request for traffic congestion prediction is received (step S203: Yes), traffic congestion prediction processing is performed (step S204). In this traffic congestion prediction process, the traffic information generated in step S202 is referred to, and based on the location (range) included in the request, the same location as the time, and the past traffic congestion at the time, the location (range), the time Predict the occurrence of traffic congestion in.

  The location where the occurrence of traffic congestion is predicted does not need to be exactly the same as the location included in the request, but may be the same as the location included in the request and past traffic information and traffic congestion within a predetermined range. Based on this, prediction may be made. Similarly, the time may be a predetermined time zone including the time included in the request.

  Thereafter, the congestion prediction information is transmitted to the terminal device 110 (step S205), and a series of congestion prediction processing ends.

  According to the above-described embodiment, in order to predict traffic congestion using captured images of a plurality of locations and times on the road captured by a camera of the terminal device, fixedly installed devices such as cameras and sensors on the road are used. It is possible to perform not only the traffic congestion prediction limited to the installation location using but also the traffic congestion prediction at an arbitrary place on the road.

  In addition, since a large number of traffic information for judging a traffic congestion state on a road can be acquired from images transmitted from a large number of terminal devices, the accuracy of congestion prediction at an arbitrary place can be improved.

  As a terminal device, a general-purpose device such as a mobile phone, a smart phone, and a car navigation system equipped with a camera capable of capturing images and transmitting position information can be used. Can also be reduced.

  In addition, when generating the traffic congestion prediction information, the distance between vehicles and the number of vehicles were used, but in addition to this, the weather, the day of the week, traffic information of other roads connected to the road of the requested location, Other data that may be a cause of traffic congestion, such as the presence or absence of an event near a place, may be added as a parameter for traffic congestion prediction. Thereby, the accuracy of the traffic congestion prediction can be further improved.

  The traffic congestion was determined based on the number of vehicles (inter-vehicle distance). However, similarity between an image before traffic congestion at an arbitrary location on the road and a current image transmitted from the terminal device is image-processed, so that images are congested. Can also be used to predict traffic congestion.

  Further, the image captured by the terminal device is not limited to a still image, but may be a moving image. In the case of a moving image, the speed of a moving body in another lane can be determined, so that more detailed traffic information can be obtained.

  In addition, statistics such as multiple regression analysis may be applied to the generation of the traffic jam prediction data. At this time, an optimal algorithm can be rearranged for each road.

  Hereinafter, examples of the present invention will be described. In the present embodiment, a configuration in which the navigation device 300 is mounted on a moving object (vehicle) and the navigation device 300 of each user accesses the server as the above-described traffic congestion prediction device 100 will be described. Here, the navigation device 300 has a function as the terminal device 110 described above, and captures a road at the time of movement of the moving object and transmits the road to the traffic congestion prediction device 100. The navigation device 300 requests the traffic congestion prediction device 100 (server) for traffic congestion prediction information of a desired place.

(Hardware configuration of navigation device 300)
FIG. 3 is a block diagram illustrating an example of a hardware configuration of the navigation device. 3, a navigation device 300 includes a CPU 301, a ROM 302, a RAM 303, a magnetic disk drive 304, a magnetic disk 305, an optical disk drive 306, an optical disk 307, an audio I / F (interface) 308, a microphone 309, a speaker 310, an input device 311, A video I / F 312, a display 313, a communication I / F 314, a GPS unit 315, various sensors 316, and a camera 317 are provided. The components 301 to 317 are connected by a bus 320, respectively.

  The CPU 301 controls the entire navigation device 300. The ROM 302 stores a boot program, a congestion prediction program, and the like. The RAM 303 is used as a work area of the CPU 301. That is, the CPU 301 controls the entire navigation device 300 by executing various programs recorded in the ROM 302 while using the RAM 303 as a work area.

  The magnetic disk drive 304 controls reading / writing of data from / to the magnetic disk 305 under the control of the CPU 301. The magnetic disk 305 records data written under the control of the magnetic disk drive 304. As the magnetic disk 305, for example, an HD (hard disk) or an FD (flexible disk) can be used.

  The optical disk drive 306 controls reading / writing of data from / to the optical disk 307 under the control of the CPU 301. The optical disk 307 is a removable recording medium from which data is read under the control of the optical disk drive 306. The optical disc 307 may use a writable recording medium. As the removable recording medium, an MO, a memory card, or the like can be used in addition to the optical disk 307.

  Examples of information recorded on the magnetic disk 305 and the optical disk 307 include map data, vehicle information, road information, traveling history, and the like. Map data is used when searching for a route in a car navigation system, and background data representing features such as buildings, rivers, the ground surface, and energy supply facilities, and road shapes representing road shapes with links and nodes. This is vector data including data.

  The audio I / F 308 is connected to a microphone 309 for audio input and a speaker 310 for audio output. The sound received by the microphone 309 is A / D-converted in the sound I / F 308. The microphone 309 is installed on, for example, a dashboard section of a vehicle, and the number thereof may be one or more. From the speaker 310, a sound obtained by D / A conversion of a predetermined sound signal in the sound I / F 308 is output.

  Examples of the input device 311 include a remote controller, a keyboard, and a touch panel having a plurality of keys for inputting characters, numerical values, various instructions, and the like. The input device 311 may be realized by any one of a remote controller, a keyboard, and a touch panel, but may be realized by a plurality of modes.

  The video I / F 312 is connected to the display 313. Specifically, the video I / F 312 includes, for example, a graphic controller for controlling the entire display 313, a buffer memory such as a VRAM (Video RAM) for temporarily recording image information that can be displayed immediately, and an output from the graphic controller. It is composed of a control IC for controlling the display 313 based on the image data to be displayed.

  The display 313 displays icons, cursors, menus, windows, or various data such as characters and images. As the display 313, for example, a TFT liquid crystal display, an organic EL display, or the like can be used.

  The camera 317 captures an image of a road outside the vehicle. The image may be a still image or a moving image. By photographing the road outside the vehicle with the camera 317, another vehicle traveling along with the road is photographed. The captured image is subjected to image processing by the CPU 301 and then transmitted to the traffic congestion prediction device 100 (a server 400 described later) together with the position information of the GPS unit 315.

  The communication I / F 314 is connected to a network via radio, and functions as an interface between the navigation device 300 and the CPU 301. Examples of the communication network functioning as a network include an in-vehicle communication network such as CAN and LIN (Local Interconnect Network), a public line network and a mobile phone network, a Dedicated Short Range Communication (DSRC), a LAN, and a WAN. The communication I / F 314 is, for example, a public line connection module, an ETC (non-stop automatic fee payment system) unit, an FM tuner, a VICS (Vehicle Information and Communication System: registered trademark) / beacon receiver, and the like.

  The GPS unit 315 receives radio waves from GPS satellites and outputs information indicating the current position of the vehicle. The output information of the GPS unit 315 is used together with the output values of various sensors 316 to be described later when the CPU 301 calculates the current position of the vehicle. The information indicating the current position is, for example, information for identifying one point on the map data, such as latitude / longitude and altitude.

  The various sensors 316 output information for determining the position and behavior of the vehicle, such as a vehicle speed sensor, an acceleration sensor, an angular velocity sensor, and a tilt sensor. The output values of the various sensors 316 are used by the CPU 301 to calculate the current position of the vehicle and to calculate the amount of change in speed and azimuth.

  The CPU 301 illustrated in FIG. 3 realizes the function of the processing unit 113 of the terminal device 110 illustrated in FIG. 1 by executing a program stored in the ROM 302 or the like. The function of the imaging unit 111 of FIG. 1 is realized by the camera 317 of FIG. 3, and the function of the positioning unit 112 of FIG. 1 is realized by the GPS unit 315 of FIG.

(Example of server configuration)
FIG. 4 is a block diagram illustrating an example of a hardware configuration of the server. The server 400 included in the traffic congestion prediction device 100 has the same configuration as the navigation device 300 shown in FIG. In the server 400, the GPS unit 315, the various sensors 316, the camera 317, and the like shown in FIG.

  The traffic congestion prediction device 100 shown in FIG. 1 implements a traffic congestion prediction function by causing a CPU 401 to execute a predetermined program using programs and data recorded in a ROM 402 or the like provided in a server 400. The above-described traffic information and traffic congestion prediction information are stored in the magnetic disk 405 of the server 400 or the like. Further, communication with the navigation device 300 is performed via the communication I / F 414, and traffic jam prediction information corresponding to a request from the navigation device 300 is output to the navigation device 300.

  Further, the server 400 may have a function of calculating a transmission time of an image transmitted from each navigation device 300 and a speed of a moving body on which the navigation device 300 is mounted. The server 400 can calculate the speed of the moving object by calculation based on the movement amount of the latitude and longitude of the navigation device 300 and the required travel time.

  The CPU 401 shown in FIG. 4 executes the program stored in the ROM 402 or the like to execute the image processing unit 101, the information combining unit 102, the traffic information processing unit 103, the traffic congestion prediction information management unit 105 of the traffic congestion prediction device 100 shown in FIG. Implement the function of The magnetic disk 305 and the optical disk 307 in FIG. 4 realize the function of the storage unit 104 shown in FIG.

(Image transmission processing by the navigation device)
FIG. 5 is a flowchart showing the content of processing of image transmission by the navigation device. The navigation device 300 always measures the position by the GPS unit 315 or the like when the moving body moves (step S501). Then, for example, at a predetermined timing (for example, every minute), the road is photographed by the camera 317 (step S502). For example, by photographing a road ahead, a moving object on the road is photographed together with the road.

  The trigger (timing) for photographing the road with the camera 317 can be a request output from the server 400 to the navigation device 300 or an instruction from the user of the navigation device 300 or the like.

  Then, the navigation device 300 transmits the position information at the time of photographing to the server 400 together with the photographed image every time the image is photographed (step S503). In addition, the navigation device 300 may add a time to an image for each shooting, and transmit a plurality of images to the server 400 collectively at predetermined time intervals.

  The navigation device 300 repeatedly shoots an image as described above, and transmits the image to the server 400. Thus, the server 400 can collect images of a plurality of roads captured by the plurality of navigation devices 300.

(Traffic information generation processing by server)
FIG. 6 is a flowchart showing a process of generating traffic information by the server. First, the server 400 receives the image and the position information (imaging position) transmitted from the navigation device 300 (Step S601). Next, the speed and time of the moving object (navigation device 300) at the time of receiving the image are acquired (step S602).

  The server 400 may obtain the speed and time of the moving object from those transmitted by the navigation device 300, or may use those generated inside the server 400. When the time is generated on the server 400 side, the time inside the server 400 when the image is received is used as the time. For the movement of the moving object, a value obtained by calculating the speed of the moving object by calculation based on the amount of movement of the moving object (navigation device 300) in latitude and longitude and the required moving time is used.

  Next, the server 400 detects the vehicle, the traveling lane, and the number of lanes from the acquired image by the image processing of the image processing unit 101 (step S603). At this time, for example, the photographed image is converted into an ortho image, the position and the distance of the vehicle can be specified, and the number of vehicles per lane can be detected. In the ortho image, the width of the own lane is derived, and the number of lanes and the distance between vehicles on the traveling road are determined.

  Next, the server 400 associates the position information, the speed, the time, the number of vehicles by lane, and the own lane with each image (ID) acquired by the information combining unit 102, and stores the information in the storage unit 104 as traffic information. It is stored (step S604). The processing of steps S601 to S604 is performed every time an image is received from the navigation device 300.

(Example of traffic information)
FIG. 7 is a chart showing an example of the content of traffic information. FIG. 7A shows captured image processing information 701 obtained by performing image processing on one image transmitted from a certain user. The captured image processing information 701 includes lane information (the number of lanes), own lane information, and lane-specific vehicle information ID. In the illustrated example, the own vehicle is the first from the left (own lane information) of the three-lane road (lane information).

  Details of the lane-specific vehicle information ID in FIG. 7A are shown in 702 in FIG. As the lane-specific vehicle information ID 702, an ID is assigned to each image, and a position for each ID (a lane position, which is a lane position of a moving object existing in the image) obtained by the image processing, The following information is provided between the vehicles (the distance between the moving object existing in the image and the vehicle). In the illustrated example, when ID = 1, a moving object exists at a position 45 m ahead of the own vehicle position (lane 1) at a distance of 45 m, and at a position ahead of the own vehicle position (lane 3), the distance between the vehicle and the vehicle is 30 m and 60 m. Indicates that a moving object is present. In the illustrated example, of the three lanes, the position of the left lane is indicated by “1”, the position of the center lane is indicated by “2”, and the position of the right lane is indicated by “3”.

  The photographing condition information 703 shown in (c) of FIG. 7 includes (a) the photographed image processing information 701 of FIG. 7 and the photographing position (latitude and longitude in the illustrated example), speed, and time, which are conditions at the time of photographing. This is information associated with the shooting ID.

  FIG. 7D shows the traffic information 704. The photographing condition information 703 shown in FIG. 7C is accumulated for different places and times of the same user, and for different users. By increasing the number of lines of the traffic information 704, it is possible to construct a database of time-dependent own lane information, lane information, and lane-specific vehicle information ID (lane position, inter-vehicle) for a desired shooting position.

(Congestion prediction processing using traffic information)
FIG. 8 is a flowchart showing the process of congestion prediction using traffic information. First, the traffic information processing unit 103 of the server 400 classifies the traffic information 704 by position, date, and time zone (Step S801), and creates a statistical function for each classified data (Step S802). In this state, the traffic information processing unit 103 waits for input of a request condition included in the traffic jam prediction request from the navigation device 300 (step S803: No loop).

  If there is a request condition input (step S803: Yes), the traffic information processing unit 103 calculates a traffic jam occurrence value using a statistical function corresponding to the request condition (step S804). Then, the traffic information processing unit 103 determines whether the traffic jam occurrence value is high (positive value) (step S805). If the traffic jam occurrence value is higher than the predetermined value (step S805: Yes), the traffic information occurrence unit 103 determines this traffic jam occurrence value as a traffic jam. It is generated as prediction information and stored in the storage unit 104 (step S806). If the traffic jam occurrence value is low (step S805: No), it is determined that there is no traffic jam, and the current process ends.

  A specific example of the above processing will be described. In the above example, the occurrence of congestion is determined by comparing the congestion occurrence value with a predetermined threshold value as reliability. For example, a case will be described in which the traffic congestion prediction request condition transmitted (input) from the navigation device 300 specifies a left lane traffic volume, a right lane traffic volume, a date (day of the week), and a time zone.

  Note that the navigation device 300 transmits the captured image, and the server 400 analyzes the image to determine a left lane traffic volume, a right lane traffic volume, a date (day of the week), and a time zone. The date and time are determined based on the data reception time of the server. An example of the traffic volume is the number of vehicles per unit time.

  First, the traffic information processing unit 103 refers to the traffic information 704 corresponding to the date (day of the week) and the time zone specified from the storage unit 104. For example, reference is made to the traffic information 704 in which the data of the required condition is x road, Tuesday, and from 12:00 to 13:00.

Then, the traffic information processing unit 103 uses the statistical function fn relating to the occurrence of congestion and the required conditions X and Y as input values, and calculates the congestion probability using the following arithmetic expression.
fn (X, Y) = an (X) + bn (Y)
fn (xn, yn) = an (xn) + bn (yn)
Congestion occurrence value = max (1 / fn (| X-xn |, | Y-yn |))-tn

  Here, fn: statistical function (n = 0, 1,...) The statistical function fn is a function for comparing the past traffic congestion prediction data with the current traffic volume to obtain a traffic congestion occurrence value. X: left lane input traffic, Y: right lane input traffic, xn: left lane statistical traffic, yn: right lane statistical traffic, an: left lane prediction coefficient, bn: right lane prediction coefficient, tn: threshold Value. The traffic volume is obtained from the speed of the moving object at the time of image capturing and the number of the moving objects captured.

  When it is determined that traffic congestion has occurred on a certain road, the traffic congestion prediction data includes traffic information (for example, each lane) that goes back a predetermined time from the time at which the traffic congestion was determined on that road (the time to go back differs for each road). Statistics of traffic volume, speed and time). If this statistical data is significantly different from ordinary traffic information, it becomes traffic congestion prediction data on this road. However, there is a large number of prediction data for one road for each parameter such as date and time. The determination of the occurrence of traffic congestion may be made by the traffic congestion prediction device 100 of the system, or if the information is obtained from another external system, the traffic congestion may be determined when the distance between vehicles is narrow or when the speed is low. to decide.

  The statistical function fn has two features in the above example (two-lane road), such as "congestion occurs when the right lane is extremely crowded," or "congestion occurs thereafter when both right and left are partially crowded." In the case of a road with two roads, there are two congestion occurrence patterns, so that fn is n = 2. This feature is calculated from traffic congestion prediction data.

  The right lane input traffic volume is the traffic volume of the right lane calculated from the image captured by the navigation device 300, and FIG. 7B shows the lane-specific vehicle information ID 702 “1” (the road of the lane-specific photography ID “1” It is indicated by the number of rows at the position “3” in the three-lane road (that is, the number of vehicles existing in the right lane of the three-lane road). The left lane input traffic volume is indicated by the number of rows at the position “1” in the lane-specific vehicle information ID 702 “1” (that is, the number of vehicles existing in the left lane of the three-lane road) in FIG.

  The right (left) lane statistical traffic volume is a statistical value of the average or mode value of the traffic volume at the position “3” in the corresponding pattern in the traffic congestion prediction data. The right (left) lane prediction coefficient is a coefficient that weights the difference between the right (left) lane statistical traffic volume and the right lane input traffic volume. For example, if there is a pattern such as "congestion occurs after the right lane becomes extremely crowded" on the road, the right lane prediction coefficient is increased. As a result, the difference between the right lanes is largely reflected on the final traffic jam occurrence value.

  A specific example of the traffic congestion prediction will be described. The traffic congestion prediction device 100 states that, at time t on a certain road, the right lane is extremely crowded and the right and left lanes are slightly crowded in statistical data (data in the storage unit 104) for 30 minutes before traffic congestion occurs. Suppose there are two patterns. It can be seen that a sign of congestion appears on this road 30 minutes before. These two patterns are stored in the storage unit 104 as traffic congestion prediction data at t of this road.

  Then, it is assumed that the image is transmitted from the user of the navigation device 300 at time t. It is assumed that the traffic congestion prediction device 100 determines that the right lane is very crowded by image analysis of this image. It is assumed that the traffic congestion prediction device 100 is very similar to the “right lane is extremely crowded” pattern when the similarity to the traffic congestion prediction data is calculated by the statistical function for the image analysis result. In this case, the traffic information processing unit 103 of the traffic congestion prediction device 100 determines that a traffic congestion occurs 30 minutes after the image is transmitted, and instructs the traffic congestion information management unit 105 that the traffic will be congested after 30 minutes. Then output.

A specific example of calculation using the statistical function of the traffic congestion prediction device 100 will be described. Because this road has the following two patterns of traffic congestion forecast,
Pattern 1: "Congestion occurs when the right lane is extremely crowded"
Pattern 2: "Congestion occurs when both right and left lanes are slightly crowded"
Therefore, two statistical functions fn are prepared.
f1 (X, Y) = a1 (x1) + b1 (y1)
f2 (X, Y) = a2 (x2) + b1 (y2)

x1: Left lane traffic volume (average or mode) of predicted data of pattern 1 → Statistical traffic volume of left lane y1: Right lane traffic volume (average or mode) of predicted data of pattern 1
x2: Left lane traffic volume of the forecast data of pattern 2 (average or mode)
y2: Right lane traffic volume of pattern 2 forecast data (average or mode)
a1: weight of the left lane of pattern 1; b1: weight of the right lane of pattern 1 (in pattern 1, the value of a1 is increased and the value of b1 is reduced since we want to focus on only the right lane)
a2: weight of the left lane of pattern 2; b2: weight of the right lane of pattern 2 (a2 = b2 in pattern 2 because both lanes are to be noted)

Then, when the traffic congestion prediction information management unit 105 inputs each lane traffic volume X, Y,
1 / f1 (| x1-X |, | y1-Y |) and 1 / f2 (| x2-X |, | y2-Y |) are calculated. The larger value is adopted and compared with the threshold value tn. If it is larger than tn, traffic congestion prediction information is generated.

  The congestion prediction information management unit 105 stores and manages the congestion prediction information in the storage unit 104, and transmits the congestion prediction information to the navigation device 300 when a congestion prediction request is issued from the navigation device 300.

  If there is a request condition at the time of a traffic jam prediction request from the navigation device 300, for example, designation of weather or the like, the traffic information processing unit 103 refers to the traffic information 704 including this parameter. If the required conditions increase, it becomes possible to perform highly accurate traffic congestion prediction for the request.

  In the above processing example, the traffic jam prediction information is calculated after waiting for the traffic jam prediction request from the navigation device 300. However, the present invention is not limited to this. For example, the traffic information processing unit 103 may be configured to generate congestion prediction information for each position and time based on the traffic information 704 in advance. In this case, if there is a traffic jam prediction request from the navigation device 300, the traffic congestion prediction information of the corresponding position and time can be transmitted to the navigation device 300 immediately.

(About transmission of traffic congestion prediction request and traffic congestion prediction information)
FIG. 9 is a flowchart showing the processing contents from the traffic jam prediction request to the transmission of the traffic jam prediction information. First, the navigation device 300 transmits a congestion prediction request for a specified position or a specified range to the server 400 (step S901).

  The traffic congestion prediction information management unit 105 of the server 400 receives the traffic congestion prediction request (Step S902), and transmits (distributes) the traffic congestion prediction at the corresponding designated position or designated range to the navigation device 300 (Step S903).

  The navigation device 300 receives the traffic jam prediction information transmitted from the server 400 (step S904), and displays the traffic jam prediction information on the display unit (step S905).

  The traffic congestion prediction information management unit 105 of the server 400 may be configured to monitor whether or not a traffic congestion prediction change has occurred based on a possibility that the state of the traffic congestion may change over time after step S903. (Step S906). If there is no traffic congestion prediction change (step S906: No), the process ends. If traffic congestion prediction change occurs (step S906: Yes), the traffic congestion prediction information is calculated again in step S903. Send.

(About traffic jam)
FIG. 10 is an explanatory diagram showing a state of occurrence of natural congestion. As shown in FIG. 10A, as the number of vehicles of a moving body that travels increases, the distance between the moving bodies decreases. Next, as shown in FIG. 10B, when the speed of some of the moving bodies 1001 decreases, the succeeding moving bodies 1011 and 1012 step on the brakes one after another to reduce the speed so as not to collide. As a result, as shown in FIG. 10C, the moving body 1021 that stops completely appears, and the following moving bodies 1031, 1032, 1033, and 1034 also stop one after another, and a natural traffic jam occurs.

(About traffic congestion forecast)
The traffic congestion prediction according to the embodiment refers to a captured image of the navigation device 300 and a past database (traffic information 704) in that, as the number of traveling moving objects increases, the distance between vehicles decreases. To predict. The server 400 refers to the past traffic information 704 corresponding to the request condition, and determines which of the conditions (a) to (c) corresponds to the natural traffic congestion illustrated in FIG. 10. And transmits to the navigation device 300 traffic congestion prediction information corresponding to the requested date and time included in the traffic congestion prediction request.

  In addition, how the traffic congestion changes after the request time (for example, when the request is a time corresponding to FIG. 9A, natural traffic congestion occurs as shown in FIG. 9C after 10 minutes, for example) Can be transmitted to the navigation device 300 as traffic jam prediction information.

(About application of traffic congestion prediction information to route search)
When the above-described congestion prediction information indicates that there is a high possibility of occurrence of congestion (congestion occurrence value is high), the navigation device 300 assigns the congestion prediction information to the corresponding road on the congestion candidate route, and I can guide you.

  The navigation device 300 according to the embodiment performs a route search in consideration of the above-described traffic congestion prediction information. As a result, since the average travel time of the road (link) where traffic congestion is expected is long, a route that avoids this traffic congestion point is searched.

  However, in the route search using the traffic congestion prediction information, whether or not there is an actual traffic congestion at the corresponding place is determined at the predicted time. Therefore, there may be a case where the predicted congestion does not occur (no congestion occurs) at the time of the prediction. In such a case, when the prediction time has been reached, the navigation device 300 re-searches the route and does not use the traffic jam prediction information used last time.

  The route search is not limited to being performed by the navigation device 300, but may be performed by the server 400. The server 400 may acquire position information such as the current position and the destination of the navigation device 300 and perform a route search including other search conditions such as time.

  In the above embodiment, the traffic number is detected by performing image processing on the number of lanes, the number of vehicles, the distance between vehicles, and the like from the captured image. For example, when there is a guidance sign indicating that construction is in progress on the lane of the road in the captured image, there is a possibility that sudden congestion may occur due to the construction. In addition, a vehicle type (bus, police car), pedestrian crossing, and the like that can be a cause of traffic congestion can also be used as parameters.

  Therefore, the accuracy of the traffic information 704 can be improved by statistically processing the common points and differences between the captured images themselves before and after the occurrence of traffic congestion.

  Further, in the above embodiment, the traffic congestion prediction device 100 such as a server performs the traffic congestion prediction. However, the traffic congestion prediction is performed by a certain car navigation device or a terminal device 110 such as a personal computer. May be transmitted to the other terminal device 110 that has requested.

  The method related to traffic congestion prediction described in the present embodiment can be realized by executing a prepared program on a computer such as a personal computer or a workstation. This program is recorded on a computer-readable recording medium such as a hard disk, a flexible disk, a CD-ROM, an MO, and a DVD, and is executed by being read from the recording medium by the computer. This program may be a transmission medium that can be distributed via a network such as the Internet.

REFERENCE SIGNS LIST 100 traffic congestion prediction device 101 image processing unit 102 information combining unit 103 traffic information processing unit 104 storage unit 105 traffic congestion prediction information management unit 110 terminal device 111 imaging unit 112 positioning unit 113 processing unit

Claims (1)

An acquisition unit that acquires an image of a moving object on a road and position information indicating a position where the moving object is photographed,
An image processing unit that extracts traffic information that is information on a moving object present in the image,
Using the traffic information extracted by the image processing unit, a traffic information processing unit that calculates information related to traffic congestion prediction on the road corresponding to the position where the image was captured,
Traffic congestion prediction system characterized by having.

Images