JP2018017668A - Information processing device and information processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing device capable of achieving camera image positioning which can prevent an increase in positioning errors.SOLUTION: An information processing device 1 for identifying a location of a vehicle A comprises: a first input unit 1a which acquires image data from an on-vehicle camera which photographs a periphery of the vehicle A; a second input unit 1c which acquires GPS positioning data from a GPS receiver mounted on the vehicle A; a camera image positioning unit 1d which positions the location of the vehicle A on the basis of the image data; and a location determining unit 1e which determines the location of the vehicle A on the basis of positioning results of the camera image positioning unit 1d. When positioning accuracy of the camera image positioning unit 1d lowers, the location determining unit 1e corrects the positioning results of the camera image positioning unit 1d on the basis of the GPS positioning data and determines the location of the vehicle A.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus and an information processing program.

  In recent years, a positioning technique with a smaller positioning error has been demanded in order to realize an autonomous driving vehicle and a sophisticated vehicle navigation function.

  Against this background, various positioning technologies have been researched and developed, and one of them is to extract a target from an image of a landscape around the vehicle (hereinafter referred to as a “camera image”) taken by an in-vehicle camera. A technique for positioning the vehicle position based on the target (hereinafter referred to as “camera image positioning”) has attracted attention (for example, see Patent Document 1).

JP 2011-215056 A

  However, in the camera image positioning, there is a problem that the positioning accuracy decreases with the travel distance when an effective target for identifying the vehicle position is not extracted.

  When an effective target for identifying the vehicle position is no longer extracted, positioning is performed using a target that is difficult to identify the vehicle position, such as a distant target, or a vehicle speed sensor signal, etc. Since positioning is performed using, positioning error tends to increase. In particular, when there is no target around the vehicle that can specify an absolute position such as a traffic light, the current position is calculated based on the past position. Positioning error may increase.

  The present invention has been made in view of the above-described problems, and an object thereof is to provide an information processing apparatus and an information processing program for realizing camera image positioning that can prevent an increase in positioning error.

  The main present invention that solves the above-described problems is an information processing apparatus that identifies the position of a vehicle, and is mounted on the vehicle, a first input unit that acquires image data from an in-vehicle camera that captures the surroundings of the vehicle A second input unit that acquires GPS positioning data from the received GPS receiver, a camera image positioning unit that measures the position of the vehicle based on the image data, and a positioning result of the camera image positioning unit A position determination unit that determines the position of the vehicle, and the position determination unit, when the positioning accuracy of the camera image positioning unit decreases, the positioning result of the camera image positioning unit based on the GPS positioning data Is an information processing apparatus that determines the position of the vehicle.

  According to the information processing apparatus according to the present invention, it is possible to realize camera image positioning in which an increase in positioning error is suppressed.

The figure which shows an example of a structure of the vehicle which concerns on 1st Embodiment. The figure which shows an example of the operation | movement flow of the information processing apparatus which concerns on 1st Embodiment. The figure which shows an example of the operation | movement flow of the information processing apparatus which concerns on 1st Embodiment. The figure explaining the camera image positioning of the information processing apparatus which concerns on 1st Embodiment The figure explaining the camera image positioning of the information processing apparatus which concerns on 1st Embodiment The figure which shows an example of the operation | movement flow of the information processing apparatus which concerns on 2nd Embodiment.

(First embodiment)
Hereinafter, the configuration of the information processing apparatus according to the present embodiment will be described with reference to FIG.

  The information processing apparatus 1 according to the present embodiment is mounted on, for example, an automatic driving vehicle A (hereinafter abbreviated as “vehicle A”), and is used for specifying the vehicle position for automatic driving. However, the information processing apparatus 1 is not limited to the autonomous driving vehicle A but can be applied to any apparatus such as a car navigation apparatus.

  FIG. 1 is a diagram illustrating an example of a functional configuration of a vehicle A according to the present embodiment. The arrows in FIG. 1 represent signal paths.

  The vehicle A according to the present embodiment includes an information processing device 1, a storage device 2, an in-vehicle camera 3, various sensors 4, a GPS (Global Positioning System) receiver 5, and a vehicle ECU 6 (Electronic Control Unit).

  In the present embodiment, the information processing apparatus 1 is configured to identify the position of the vehicle A by performing data communication with the storage device 2, the in-vehicle camera 3, the various sensors 4, and the GPS receiver 5. Specifically, the information processing apparatus 1 acquires image data from the in-vehicle camera 3 and performs camera image positioning in order to determine the position of the vehicle A, and acquires GPS positioning data from the GPS receiver 5. Thus, the positioning result of the camera image positioning is corrected (details will be described later).

  The position data indicating the vehicle position specified by the information processing device 1 is transmitted to the vehicle ECU 6 and used for automatic driving control in the vehicle ECU 6, for example.

  The in-vehicle camera 3 is, for example, a visible light camera that captures the surroundings of the vehicle A (for example, the front outside the vehicle). The in-vehicle camera 3 is configured to include an image sensor such as a CMOS sensor, for example, and generates image data from an image signal for each pixel generated by the image sensor and transmits the image data to the information processing apparatus 1. The in-vehicle camera 3 transmits, for example, a moving image of the scenery around the vehicle A that changes sequentially to the information processing apparatus 1 as image data in units of frames.

  Of course, a plurality of in-vehicle cameras 3 may be attached to photograph a plurality of directions around the vehicle. The in-vehicle camera 3 is not limited to a visible light camera, and an infrared camera, a stereo camera, or the like may be used. The in-vehicle camera 3 may be a camera that continuously captures still images instead of moving images.

  The various sensors 4 are sensors that detect the behavior of the vehicle A, and include, for example, a vehicle speed sensor and a direction sensor. As the vehicle speed sensor, for example, a vehicle speed pulse sensor, an acceleration sensor, or the like that detects a rotation amount of a drive shaft, a wheel, or the like is used. Further, as the azimuth sensor, for example, a gyro sensor, a geomagnetic sensor, a rotation sensor for detecting the rotation of the handle, or the like is used. In addition to the above, various sensors that indicate the behavior of the vehicle A may be used.

  The GPS receiver 5 receives GPS signals from a plurality of GPS satellites, generates GPS positioning data indicating its own vehicle position, and transmits it to the information processing apparatus 1. For example, the GPS receiver 5 obtains its own vehicle position (for example, latitude and longitude) from the position of each GPS satellite included in the GPS signal and the transmission time (hereinafter also referred to as “satellite positioning”). The GPS receiver 5 may employ a differential GPS or the like that receives a pseudo distance correction signal from a ground reference station whose absolute position is known in addition to a GPS signal from a GPS satellite.

  However, satellite positioning using a GPS signal has a positioning error larger than that of camera image positioning, and the positioning error may occur as much as several meters. Therefore, the information processing apparatus 1 according to the present embodiment uses the GPS positioning data as an auxiliary role for correcting the positioning result of camera image positioning.

  The storage device 2 includes, for example, an HDD (Hard Disk Drive), a flash memory, and the like. The storage device 2 stores various types of data such as various processing programs executed by the information processing device 1, an image DB 2a, a map DB 2b, and the like. The data stored in the storage device 2 is used by being transferred to a RAM or the like of the information processing device 1, for example. Note that these data may be sequentially downloaded via the Internet line and stored in the storage device 2 in accordance with the position of the vehicle A and the user's operation.

  The image DB 2a is a database related to image data that stores an “image” of a target and the “coordinates” of the target in association with each other. The image DB 2a is referred to when a visual target is extracted from a camera image captured by the in-vehicle camera 3 in camera image positioning.

  The “image” stored in the image DB 2a is, for example, an image indicating the shape of each target such as a lane boundary line or a road surface structure, or a landscape image in units of frames including the target. In the image DB 2a, a camera image previously captured for reference in camera image positioning and a camera image captured by the in-vehicle camera 3 in the past (for example, several seconds before) are stored as data.

  The “image” stored in the image DB 2a can take various forms. For example, it may be an aerial image taken from the sky that makes it possible to guess a target shot in the camera image.

  In the image DB 2a, the “coordinates” associated with the target is, for example, a position based on a latitude / longitude or a predetermined position (for example, an intersection around the vehicle A). The “coordinates” are associated with, for example, a shooting position when a landscape including a visual target is shot.

  The “coordinates” associated with the visual target can take various forms. For example, the “coordinates” may be coordinates associated with each visual target. The “coordinates” may indicate the position where the visual target is present. The “coordinates” may be coordinates indicating an absolute position (for example, latitude and longitude) or coordinates indicating a relative position (for example, coordinates measured immediately before). In addition, the “coordinates” are coordinates associated only with the position in the vehicle width direction of the road (for example, a distance from the lane boundary line) or coordinates associated only with the position in the traveling direction of the road (for example, surroundings). Distance from the intersection).

  The map DB 2b is a database related to map data that stores a road map and coordinates of the road map in association with each other.

  The road map of the map DB 2b includes road information such as the position of an intersection, the position of a traffic light, and the number of lanes. The coordinates associated with the road map are positions based on, for example, latitude and longitude or a predetermined position (for example, an intersection around the vehicle A).

  The road map in the map DB 2b is referred to when extracting a reference object to be compared with a camera image in camera image positioning. In addition, the road map is also referred to when a travel route is specified during automatic driving.

  The information processing apparatus 1 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.

  As described above, the information processing device 1 controls the data by communicating with the storage device 2, the in-vehicle camera 3, the various sensors 4, and the GPS receiver 5, and based on the data received from these, Identify your vehicle position. Note that transmission / reception of signals between the information processing apparatus 1 and each unit is performed by, for example, a CAN (Controller Area Network) communication protocol system via a signal line.

  The information processing apparatus 1 includes an image signal input unit 1a (corresponding to a first input unit of the present invention), a sensor signal input unit 1b, a GPS signal input unit 1c (corresponding to a second input unit of the present invention), a camera image A positioning unit 1d and a position determining unit 1e are provided.

  The image signal input unit 1 a acquires image data generated by the in-vehicle camera 3. The image signal input unit 1a may acquire raw data of an image signal generated by the image sensor of the in-vehicle camera 3, or may acquire data that has been subjected to predetermined image correction processing, data compression processing, and the like. Also good. Further, the image signal input unit 1 a may acquire image data from the plurality of in-vehicle cameras 3.

  The sensor signal input unit 1b acquires sensor signals generated by the various sensors 4. The sensor signal input unit 1b may acquire low data of sensor signals generated by various sensors 4, or may acquire a signal whose level is determined by a comparison circuit or the like.

  The GPS signal input unit 1c acquires GPS positioning data generated by the GPS receiver 5. The GPS signal input unit 1c may acquire data that has been calculated based on the GPS signal, or may acquire raw data of GPS signals received from a plurality of GPS satellites. The GPS positioning data may include a traveling direction, a traveling speed, and the like.

  The camera image positioning unit 1d measures the own vehicle position based on the camera images around the vehicle A.

  The “own vehicle position” measured by the camera image positioning unit 1d may be coordinates such as latitude and longitude, or coordinates based on a predetermined position (for example, an intersection around the vehicle A). . In addition, the “own vehicle position” may have different reference positions in the vehicle width direction and the traveling direction. For example, the coordinates in the vehicle width direction are coordinates based on the lane boundary line of the road being traveled. The coordinates in the traveling direction may be coordinates based on the intersection where the vehicle A has passed.

  However, the camera image positioning unit 1d calculates the vehicle position in the vehicle width direction and the vehicle position in the traveling direction so as to be distinguishable.

  The position determining unit 1e determines the vehicle position based on the positioning result of the camera image positioning unit 1d. In addition, the position determination unit 1e obtains the positioning accuracy of the camera image positioning unit 1d, and when the positioning accuracy is lowered, the camera image positioning unit 1d uses the GPS positioning data acquired from the GPS receiver 5. Correct the positioning result.

  The image signal input unit 1a, the sensor signal input unit 1b, the GPS signal input unit 1c, the camera image positioning unit 1d, and the position determination unit 1e described above include, for example, a control program stored in a ROM, RAM, or the like by the CPU. This is realized by referring to the data. However, the function is not limited to processing by software, and can of course be realized by a dedicated hardware circuit.

[Operation flow of information processing device]
Next, with reference to FIG. 2 to FIG. 5, an operation flow for the information processing apparatus 1 according to the present embodiment to specify the vehicle position will be described.

  2 and 3 are diagrams illustrating an example of an operation flow of the information processing apparatus 1 according to the present embodiment. 2 and 3 is executed by the information processing apparatus 1 in accordance with a computer program, for example. This operation flow is repeatedly executed by the information processing apparatus 1 when the vehicle A is operating, for example.

  4 and 5 are diagrams for describing camera image positioning of the information processing apparatus 1 according to the present embodiment.

  FIG. 4 is a schematic view of the vehicle A as viewed from above, and the camera image positioning unit 1d measures the position of the vehicle based on the camera image of the in-vehicle camera 3 that captures the front in the traveling direction of the vehicle. It shows how it is.

  In FIG. 4, M1 represents a road lane boundary line, and M2 represents a road stop line. As described above, the road stop line M2 is a target for specifying the position in the traveling direction, and the road lane boundary line M1 is a target for specifying the position in the vehicle width direction. In addition, R in FIG. 4 represents the measurement accuracy of the camera image positioning unit 1d, dx represents the measurement accuracy in the vehicle width direction, and dy represents the measurement accuracy in the traveling direction. “Positioning accuracy” means the magnitude of a positioning error included in the positioning result calculated by camera image positioning.

  FIG. 5 is a diagram illustrating the amount of decrease in the measurement accuracy dx in the vehicle width direction and the measurement accuracy dy in the travel direction when the vehicle A is traveling.

  Although details will be described later, in FIG. 5, the measurement accuracy dx in the vehicle width direction and the measurement in the traveling direction as the travel distance increases after the target for specifying the vehicle position is extracted. It shows that the accuracy dy decreases. The amount of decrease in measurement accuracy on the vertical axis in FIG. 5 is an index indicating the degree of decrease in measurement accuracy. For example, it is effective for specifying the position in the vehicle width direction and the traveling direction of the vehicle A. This is the distance traveled after a correct target is no longer extracted. In addition, the slopes of the decrease amounts of the positioning accuracy dy and dx in FIG. 5 differ depending on the shape of the road on which the vehicle A travels, the state of the target detected around the vehicle A, and the like.

  Hereinafter, processing in each step will be described according to the operation flow shown in FIGS.

  First, the camera image positioning unit 1d performs camera image positioning (step S1).

  In this camera image positioning process (see FIG. 3), the camera image positioning unit 1d first sets the estimated range of the vehicle position (step S1a).

  In step S1a, the camera image positioning unit 1d acquires data relating to the vehicle speed, the traveling direction, and the like from the various sensors 4 (vehicle speed sensor, azimuth sensor) via the sensor signal input unit 1b, for example, and based on the previous vehicle position. In addition, the estimated range of the vehicle position is set by autonomous navigation positioning.

  By executing step S1a, the camera image positioning unit 1d specifies image data of a target to be pattern-matched with the camera image from the image data stored in the image DB 2a.

  In step S1a, the method for setting the estimated range of the vehicle position is arbitrary, and the camera image positioning unit 1d may set based on GPS positioning data, map data in the map DB 2b, or the like.

  Next, the camera image positioning unit 1d acquires image data from the in-vehicle camera 3 via the image signal input unit 1a (step S1b).

  Next, the camera image positioning unit 1d performs edge detection processing, image feature point extraction processing, and the like on the image data acquired from the in-vehicle camera 3, and extracts a target from the camera image (step S1c).

  In step S1c, the camera image positioning unit 1d performs pattern matching using, for example, a known template matching method in order to collate image feature points of the camera image with the target image in the image DB 2a.

  In step S1c, a target is extracted from the camera image, and the position (two-dimensional coordinates) of the target in the camera image is obtained.

  Next, the camera image positioning unit 1d measures the position of the host vehicle from the position of the target in the camera image and the coordinates associated with the target in the image DB 2a (step S1d).

  In step S1d, the camera image positioning unit 1d measures the position of the host vehicle from the positional relationship among a plurality of targets in the camera image, for example. For example, the camera image positioning unit 1d measures the vehicle position from the position M1 and the stop line M2 of the two lane boundary lines in the camera image (see FIG. 4).

  In step S1d, the camera image positioning unit 1d determines the position of the vehicle in the traveling direction and the vehicle in order to identify and correct the positioning result of the vehicle position in the vehicle width direction and the traveling direction (details will be described later). The width direction is also calculated. In addition, since the said calculation process in camera image positioning is a well-known method, detailed description here is abbreviate | omitted.

  The camera image positioning unit 1d performs autonomic navigation positioning based on detection signals from various sensors 4 (vehicle speed sensor and direction sensor) when the target is not extracted from the camera image. The vehicle position may be derived.

  Returning to FIG. 2, processing following the camera image positioning will be described.

  Next, the position determination part 1e determines whether the positioning accuracy of the camera image positioning part 1d has fallen (step S2). If the position determination unit 1e determines that the positioning accuracy by the camera image positioning unit 1d has not decreased (step S2: YES), the positioning result of the camera image positioning unit 1d is determined as it is as the own vehicle position ( Step S3).

  On the other hand, when the position determination unit 1e determines that the positioning accuracy by the camera image positioning unit 1d has been lowered (step S2: NO), the position determination unit 1e acquires GPS positioning data from the GPS receiver 5 via the GPS signal input unit 1c. (Step S4). And the position determination part 1e correct | amends the positioning result of the said camera image positioning part 1d based on the said GPS positioning data, and determines as a own vehicle position (step S5).

  More specifically, in step S2, the position determination unit 1e identifies the positioning accuracy based on the camera image positioning related to the traveling direction of the vehicle A and the positioning accuracy based on the camera image positioning related to the vehicle width direction, and at least the traveling of the vehicle A The positioning accuracy by the camera image positioning related to the direction is obtained. Specifically, for example, the position determination unit 1e monitors the target extracted by the camera image positioning unit 1d and the time when the target is extracted, and obtains the positioning accuracy by the camera image positioning.

  If it is determined in step S2 that the positioning accuracy dy related to the traveling direction has decreased (step S2: NO), the position determination unit 1e corrects the position using, for example, GPS positioning data related to the traveling direction. (Step S5). Specifically, the position determination unit 1e converts, for example, the vehicle position indicated by the GPS positioning data into the traveling direction and the vehicle width direction of the vehicle A, and the positioning result relating to the traveling direction indicated by the camera image positioning unit 1d. Is replaced by the position in the traveling direction indicated by the GPS positioning data.

  Here, the process for determining the positioning accuracy of the camera image positioning unit 1d in step S2 and the process for correcting the positioning result of the camera image positioning unit 1d in step S5 will be described.

  FIG. 5 shows temporal changes in positioning accuracy due to camera image positioning, and shows the positioning accuracy of camera image positioning separately for the traveling direction and the vehicle width direction.

  As shown in FIG. 5, in camera image positioning, if an effective target for identifying the vehicle position is not extracted, the positioning accuracy decreases with the travel distance.

  In camera image positioning, depending on the type of “target”, the positioning accuracy for specifying the position differs between the traveling direction of the vehicle A and the vehicle width direction, and the position of the traveling direction of the vehicle A is specified. And a target effective for specifying the position of the vehicle A in the vehicle width direction. For example, effective targets for specifying the position in the traveling direction include, for example, stop lines, road markings, traffic lights, street lights, telephone poles, pedestrian crossings, zebra zones, and the like. Targets that are effective in specifying the position in the vehicle width direction include road lane boundaries, guardrails, curbs, and the like.

  The positioning accuracy dy related to the traveling direction decreases with the traveling distance when an effective target such as a stop line or a traffic light is no longer extracted for specifying the position in the traveling direction of the vehicle A. In this state, the camera image positioning unit 1d derives the position in the traveling direction based on a target (for example, a guardrail) that is difficult to specify the position in the traveling direction or a target far away. That is, the positioning error of the camera image positioning increases, and the calculation error accumulates, so that the positioning error may increase.

  Similarly, the positioning accuracy dx in the vehicle width direction also decreases with the travel distance when an effective target for identifying the position of the vehicle A in the vehicle width direction is not extracted. However, the positioning accuracy dx in the vehicle width direction has a feature that the lane boundary line of the roadway that is effective as a visual target for specifying the position in the vehicle width direction is always detected during traveling, and thus is difficult to decrease.

  The inventors according to the present application consider that the degradation characteristics of the positioning accuracy in the camera image positioning are different between the traveling direction of the vehicle A and the vehicle width direction as shown in FIG. It was conceived that an increase in positioning error can be prevented by identifying and handling these. That is, the information processing apparatus 1 according to the present embodiment, unlike general satellite positioning considered only by latitude and longitude, always identifies the traveling accuracy of the vehicle A and the vehicle width direction to determine the positioning accuracy and the vehicle position. calculate.

  On the other hand, unlike satellite image positioning, satellite positioning based on GPS signals can always measure an absolute position. Therefore, in satellite positioning, the measurement accuracy is relatively constant, and the positioning error does not increase excessively. In other words, under the situation where the positioning accuracy of the camera image positioning is lowered, the positioning accuracy can be maintained higher by using the satellite positioning than by using the camera image positioning.

  For this reason, the position determination unit 1e obtains the positioning accuracy of the camera image positioning by identifying the traveling direction and the vehicle width direction, and if one positioning accuracy falls below the threshold level, Only the positioning result on the lowered side is corrected based on this. Accordingly, for example, even when only the positioning accuracy in the traveling direction is lowered, the traveling accuracy can be continued based on the camera image positioning with respect to the positioning accuracy in the vehicle width direction.

  More preferably, the position determination unit 1e preferably corrects the positioning result of the camera image positioning after further improving the positioning accuracy of the GPS positioning data by map matching using the map DB 2b.

  And the position determination part 1e outputs the data which concern on the own vehicle position determined in this way with respect to vehicle ECU6 which performs automatic driving | operation, for example (step S6). By repeatedly executing such processing, the information processing apparatus 1 causes the vehicle ECU 6 of the vehicle A to recognize its own vehicle position.

  As described above, according to the information processing apparatus 1 according to the present embodiment, the positioning accuracy of the camera image positioning is monitored, and when the positioning accuracy of the camera image positioning decreases, the positioning result of the camera image positioning is corrected by the satellite positioning. It is configured to do. Therefore, the information processing apparatus 1 can realize camera image positioning in which an increase in positioning error is suppressed.

  In particular, according to the information processing apparatus 1 according to the present embodiment, when the positioning accuracy related to the traveling direction of the vehicle A is identified from the positioning accuracy related to the vehicle width direction, and the positioning accuracy related to the traveling direction of the vehicle decreases. Is configured to correct the positioning result related to the traveling direction of the vehicle based on the GPS positioning data. Therefore, the information processing apparatus 1 can continue the camera image positioning with a small positioning error for the position in the vehicle width direction even when the positioning accuracy in the traveling direction is lowered.

  In the above-described embodiment, the aspect of correcting the positioning error related to the traveling direction of the vehicle A is shown. However, when the positioning error related to the vehicle width direction of the vehicle A increases, the positioning error related to the vehicle A It is good also as a structure which correct | amends also about a positioning error.

  In the above embodiment, as a method for obtaining the positioning accuracy dy, dx, the mode of calculating the travel distance after the effective target is not extracted for specifying the position is shown, but it is obtained by other methods. Of course, it may be. For example, you may use the elapsed time after an effective target is no longer extracted in order to specify the position of the vehicle A in the running direction. Further, based on the road information and the like in the map DB 2b, the distance at which the target is not extracted on the map may be calculated.

(Second Embodiment)
Next, the information processing apparatus 1 according to the second embodiment will be described with reference to FIG.

  FIG. 6 is a diagram illustrating an example of an operation flow of the information processing apparatus 1 according to the present embodiment.

  The information processing apparatus 1 according to the present embodiment corrects the positioning result of the camera image positioning unit 1d based on the positioning accuracy of the GPS positioning data when the positioning accuracy of the camera image positioning unit 1d decreases (step S2). This is different from the first embodiment in that a process for determining whether or not (step S4a) is performed. In addition, description is abbreviate | omitted about the structure which is common in 1st Embodiment (Hereafter, it is the same also about other embodiment.).

  Since satellite positioning can measure an absolute position based on a GPS signal, the measurement accuracy is relatively constant. However, even with satellite positioning, the measurement accuracy may temporarily decrease under the geometrical arrangement relationship of a plurality of satellites or in an environment where the vehicle A is surrounded by a building.

  The position determination unit 1e according to the present embodiment determines the positioning accuracy of the GPS positioning data based on, for example, DOP information (Dilution of Precision) included in the GPS signal and the signal strength of the GPS signal (Step S4a). The DOP information is information indicating the positioning accuracy determined depending on the geometrical arrangement relationship of a plurality of satellites.

  Then, when the positioning accuracy of the GPS positioning data is equal to or higher than a predetermined level (step S4a: YES), the position determination unit 1e performs a correction process based on the GPS positioning data in step S5 as in the first embodiment. On the other hand, when the positioning accuracy of the GPS positioning data is lower than the predetermined level (step S4a: NO), the position determination unit 1e performs the correction process based on the GPS positioning data without performing the correction process based on the GPS positioning data 1d. The positioning result is determined as it is as the own vehicle position (step S3).

  In the present embodiment, a correspondence relationship between the positioning accuracy of the GPS positioning data and the positioning accuracy of the camera image positioning unit 1d is set in advance, and the position determination unit 1e compares the positioning accuracy to determine the GPS positioning. It is desirable to determine whether to perform correction processing based on data.

  As described above, according to the information processing apparatus 1 according to the present embodiment, the positioning result of the camera image positioning is corrected in consideration of the positioning accuracy of the GPS positioning data. Therefore, the information processing apparatus 1 according to the present embodiment corrects the positioning result of the camera image positioning and increases the positioning error of the camera image positioning on the contrary in a situation where the positioning accuracy of the GPS positioning data is lowered. It can be avoided.

(Other embodiments)
The present invention is not limited to the above embodiment, and various modifications can be considered.

  In the above embodiment, as an example of the configuration of the information processing apparatus 1, the functions of the camera image positioning unit 1d, the position determination unit 1e, and the like are described as being realized by one computer, but may be realized by a plurality of computers. Of course it is good. For example, the function of the camera image positioning unit 1d may be realized by performing calculation processing by distributing a plurality of computers in order to reduce the processing load.

  In the above embodiment, as an example of the configuration of the information processing apparatus 1, the processing of the camera image positioning unit 1d and the position determination unit 1e is shown as being executed in a series of flows. The units may be executed in parallel.

  At least the following matters will become apparent from the description of this specification and the accompanying drawings.

  An information processing apparatus 1 that identifies the position of the vehicle A, which includes a first input unit 1a that acquires image data from an in-vehicle camera that captures the periphery of the vehicle A, and a GPS receiver that is mounted on the vehicle A. Based on the second input unit 1c for acquiring GPS positioning data, the camera image positioning unit 1d for positioning the position of the vehicle A based on the image data, and the positioning result of the camera image positioning unit 1d, A position determination unit 1e for determining the position of the vehicle A. When the positioning accuracy of the camera image positioning unit 1d is lowered, the position determination unit 1e is based on the GPS positioning data and the camera image positioning unit 1d. An information processing apparatus 1 that corrects the positioning result and determines the position of the vehicle A is disclosed.

  According to the information processing apparatus 1, the positioning accuracy of the camera image positioning is monitored, and when the positioning accuracy of the camera image positioning is lowered, the positioning result of the camera image positioning is corrected by satellite positioning. It is possible to realize camera image positioning in which an increase in error is suppressed.

  In the information processing apparatus 1, when the positioning accuracy dy of the camera image positioning unit 1d related to the traveling direction of the vehicle A is lowered, the position determining unit 1e is configured to perform the camera image positioning unit based on the GPS positioning data. The position of the vehicle A may be determined by correcting the positioning result related to the traveling direction of the vehicle 1d.

  According to the information processing apparatus 1, even when the positioning accuracy in the traveling direction is lowered, camera image positioning with a small positioning error can be continued for the position in the vehicle width direction.

  In the information processing apparatus 1, the position determination unit 1 e is set to at least one of a time and a distance when the camera image positioning unit 1 d does not extract an effective target for specifying the position of the vehicle A in the traveling direction. Based on this, the positioning accuracy of the camera image positioning unit 1d related to the traveling direction of the vehicle A may be identified.

  In the information processing apparatus 1, when the positioning accuracy of the camera image positioning unit 1d is lowered and the positioning accuracy of the GPS positioning data is higher than a predetermined level, the position determination unit 1e is based on the GPS positioning data. Then, the positioning result of the camera image positioning unit 1d may be corrected.

  According to the information processing apparatus 1, it is possible to correct the positioning result of the camera image positioning and avoid the situation where the positioning error of the camera image positioning increases conversely in a situation where the positioning accuracy of the GPS positioning data is lowered. it can.

  An information processing program for specifying the position of the vehicle A, wherein the computer acquires image data from an in-vehicle camera that captures the surroundings of the vehicle A, and GPS positioning data from a GPS receiver mounted on the vehicle A , A process of positioning the position of the vehicle A based on the image data, a process of determining the position of the vehicle A based on the positioning result of the camera image positioning unit 1d, and the image Disclosed is an information processing program that executes a process of correcting the positioning result of the camera image positioning unit 1d based on the GPS positioning data and determining the position of the vehicle A when the positioning accuracy based on the data is reduced. To do.

  As mentioned above, although the specific example of this invention was demonstrated in detail, these are only illustrations and do not limit a claim. The technology described in the claims includes various modifications and changes of the specific examples illustrated above.

  The information processing apparatus according to the present disclosure can be suitably used for camera image positioning.

DESCRIPTION OF SYMBOLS 1 Information processing apparatus 2 Memory | storage device 3 Car-mounted camera 4 Various sensors 5 GPS receiver 6 Vehicle ECU

Claims (5)

An information processing device for identifying the position of a vehicle,
A first input unit that obtains image data from an in-vehicle camera that captures the periphery of the vehicle;
A second input unit for acquiring GPS positioning data from a GPS receiver mounted on the vehicle;
Based on the image data, a camera image positioning unit that measures the position of the vehicle;
A position determining unit that determines the position of the vehicle based on the positioning result of the camera image positioning unit;
With
The position determining unit corrects the positioning result of the camera image positioning unit based on the GPS positioning data and determines the position of the vehicle when the positioning accuracy of the camera image positioning unit decreases. When the positioning accuracy of the camera image positioning unit related to the traveling direction of the vehicle decreases, the position determining unit obtains a positioning result related to the traveling direction of the vehicle of the camera image positioning unit based on the GPS positioning data. The information processing apparatus according to claim 1, wherein the position of the vehicle is determined by correction. The position determination unit relates to the traveling direction of the vehicle based on at least one of a time and a distance during which the camera image positioning unit does not extract an effective target for specifying the position of the traveling direction of the vehicle. The information processing apparatus according to claim 2, wherein the positioning accuracy of the camera image positioning unit is identified. When the positioning accuracy of the GPS positioning data is higher than a predetermined level when the positioning accuracy of the camera image positioning unit is lowered,
The information processing apparatus according to claim 1, wherein a positioning result of the camera image positioning unit is corrected based on the GPS positioning data. An information processing program for identifying the position of a vehicle,
On the computer,
Processing to acquire image data from an in-vehicle camera that captures the surroundings of the vehicle;
Processing for obtaining GPS positioning data from a GPS receiver mounted on the vehicle;
Based on the image data, a process of positioning the vehicle;
Based on the positioning result of the camera image positioning unit, the process of determining the position of the vehicle,
When the positioning accuracy based on the image data is lowered, correcting the positioning result of the camera image positioning unit based on the GPS positioning data, and determining the position of the vehicle;
Information processing program that executes

Images