JP2020193955A - Driving information provision system, on-vehicle device, and method for providing driving information - Google Patents

Abstract

To provide a driving information provision system which can acquire stop information and support driving at intersections.SOLUTION: The driving information provision system includes: a stop information acquiring unit for acquiring stop information when a vehicle stops, regarding an intersection where the vehicle enters a second road from a first road; and an information managing unit for storing the stop information acquired by the stop information acquiring unit in relation to link information of a road related to the intersection.SELECTED DRAWING: Figure 1

Description

The present invention generally relates to techniques that assist in driving a vehicle.

In recent years, in the car navigation (hereinafter referred to as "navigation") industry, a standard interface standard for providing various navigation data such as digital map data and position data to the ADAS (Advanced Driver Assistance System) unit has been established, and navigation has been established. The development of new functions that utilize data is active. As an example of a new function, there is a function to support driving at an intersection with poor visibility.

Regarding whether or not the road has poor visibility, the GPS (Global Positioning System) positioning result and the road type, road width, connection angle of multiple road links, number of intersections, curve curvature of map data near the direction of travel, It is disclosed that determination is made from altitude data, traveling locus, and the like (see Patent Document 1).

International Publication No. 2004/064007

It is desired to provide the ADAS unit with the exact distance to the entrance position of the intersection with poor visibility, in addition to the information on whether or not the intersection has poor visibility in the cooperation system between the navigation system and the ADAS unit. There is.

For example, it is considered to provide driving support related to an intersection by switching the navigation screen to an in-vehicle camera image immediately before the entrance of the intersection.

However, the navigation device described in Patent Document 1 does not store stop information (for example, position data of a stop line) in an intersection.

Moreover, in most of the current map data, the stop information in the intersection is not stored in the map data.

It should be noted that the above problems may occur at points other than intersections with poor visibility.

The present invention has been made in consideration of the above points, and an object of the present invention is to propose a driving information providing system or the like capable of acquiring stop information and providing driving support related to an intersection.

In order to solve such a problem, in the present invention, at an intersection where a vehicle enters a second road from a first road, a stop information acquisition unit that acquires stop information when the vehicle stops, and the stop information. An information management unit that stores the stop information acquired by the acquisition unit in association with the link information of the road related to the intersection is provided.

According to the present invention, driving support related to an intersection can be provided at an appropriate timing.

It is a figure which shows an example of the structure of the operation information providing system which concerns on 1st Embodiment. It is a figure which shows an example of the structure of an in-vehicle device. It is a figure which shows an example of the configuration of a server device. It is a figure which shows an example of the function of an in-vehicle device. It is a figure which shows an example of the function of a server device. It is a figure which shows an example of the personal event table included in the user information. It is a figure which shows an example of the flowchart which concerns the processing performed by an in-vehicle device. It is a figure which shows an example of the flowchart which concerns the processing performed by an in-vehicle device. It is a figure for demonstrating the approximate remaining distance. It is a figure which shows an example of the flowchart which concerns the processing performed by an in-vehicle device. It is a figure which shows an example of the flowchart which concerns the processing performed by a server apparatus. It is a figure for demonstrating the stop position. It is a figure which shows an example of the flowchart which concerns the processing performed by an in-vehicle device. It is a figure for demonstrating the detailed residual distance. It is a figure which shows an example of the flowchart which concerns the processing performed by an in-vehicle device. It is a figure which shows an example of the flowchart which concerns the processing performed by a server apparatus. It is a figure which shows an example of the flowchart which concerns the processing performed by an in-vehicle device. It is a figure for demonstrating locus information. It is a figure which shows an example of the flowchart which concerns the processing performed by an in-vehicle device. It is a figure which shows an example of the flowchart which concerns the processing performed by an in-vehicle device. It is a figure for demonstrating the determination of leaving. It is a figure which shows an example of the structure of the driving support system which concerns on the 2nd Embodiment. It is a figure which shows an example of the function of an in-vehicle device. It is a figure which shows an example of the function of the management server apparatus. It is a figure which shows an example of the function of the object detection server device. It is a figure for demonstrating one outline of the 2nd Embodiment. It is a figure which shows an example of the flowchart which concerns on a series of processing which concerns on the update of event information in a server device. It is a figure which shows an example of the flowchart which concerns a series of processing which concerns on the update of the event information in an in-vehicle device. It is a figure which shows an example of an event file. It is a figure which shows an example of the personal event table in a management server device. It is a figure which shows an example of the flowchart which concerns on the intersection determination processing. It is a figure which shows an example of the reliability determination policy. It is a figure which shows an example of the flowchart which concerns the processing including the imaging timing adjustment processing.

Hereinafter, some embodiments of the present invention will be described in detail with reference to the drawings.
(1) First Embodiment

The present embodiment relates to a technique for providing driving support related to an intersection at an appropriate timing. For example, in the driving information providing system of the present embodiment, driving support is provided when a vehicle approaches an intersection, when the vehicle enters the intersection, when the vehicle exits the intersection, and the like. This assists driving at intersections. The "driving support" may be to control a vehicle (specifically, for example, parts in the traveling system of the vehicle (for example, accelerator, brake, steering wheel, etc.)), or information related to an intersection (for example,). , The stop position related to the intersection, the trajectory in the intersection, the exit from the intersection) may be notified (for example, the driver, the pedestrian, another vehicle, etc.), or other support. Good. Further, "driving related to an intersection" means driving at an intersection and at least one of the vicinity of the intersection, specifically, driving when a vehicle approaches an intersection, driving when a vehicle enters an intersection, and driving. This is at least one of the driving when the vehicle exits the intersection.

In the following description, when the same type of elements are not distinguished, the common part (the part excluding the branch number) of the reference symbols including the branch number is used, and the same type of elements are distinguished and described. In some cases, a reference code containing the branch number may be used. For example, when the camera is described without any distinction, it is described as "camera 113", and when the individual cameras are described separately, the "front camera 113-1" and "rear camera 113-2" are described. May be described as.

Further, in the following description, for the sake of simplicity, the user and the vehicle are set to 1: 1. However, in reality, one user may use two or more vehicles, or a plurality of users may use the same vehicle. May be used. Therefore, in the following description, at least a part of the user-specific information may be read as the vehicle-specific information.

FIG. 1 is a diagram showing an example of the configuration of the operation information providing system 100.

The driving information providing system 100 provides various information to the user who is on the vehicle 110 and controls the driving of the vehicle 110 according to the traveling state of the vehicle 110. In the driving information providing system 100, the vehicle 110 and the server device 120 are connected to each other via the communication network 130.

The vehicle 110 includes an in-vehicle device 111, a communication terminal 112, a camera 113, a vehicle control device 114, and a sensor group 115. The in-vehicle device 111 and the communication terminal 112 are connected by wire or wirelessly.

The in-vehicle device 111 provides various information to the user (for example, the driver) of the vehicle 110 according to the traveling state of the vehicle 110. The in-vehicle device 111 includes a communication terminal 112 that communicates with the server device 120, a camera 113 that takes an image in response to an instruction from the in-vehicle device 111 (or a device different from the in-vehicle device 111), and the running of the vehicle 110. It is connected to a vehicle control device 114 that performs various processes and controls.

The communication terminal 112 wirelessly connects to the communication network 130 as needed under the control of the in-vehicle device 111. A server device 120 is connected to the communication network 130. That is, the in-vehicle device 111 can communicate with the server device 120 by connecting to the server device 120 via the communication terminal 112 and the communication network 130. When the communication terminal 112 and the communication line network 130 are wirelessly connected, a wireless base station (not shown) of the communication line network 130 is used. This wireless base station can wirelessly communicate with a communication terminal 112 in a predetermined communication area around it, and is installed in various places. The communication terminal 112 is, for example, a mobile phone or the like.

The vehicle 110 is a camera 113, for example, a front camera 113-1 mounted toward the front of the vehicle 110, a rear camera 113-2 mounted toward the rear of the vehicle 110, and a left side of the vehicle 110. It includes a left side camera 113-3 mounted toward the vehicle 110 and a right side camera 113-4 mounted toward the right side of the vehicle 110. Some of these cameras 113 may be absent, or some of these cameras 113 may be replaced or additionally equipped with another camera 113.

The vehicle control device 114 is one or more ECUs (Electronic Control Units). Various types of ECUs are mounted on the vehicle 110 according to the function of the vehicle control device 114, the control target, and the like. One or more ECUs include one or more ADAS units. The ADAS unit is an example of an advanced driver assistance system (ADAS) or an element thereof, for example, controlling a driving operation, calling attention to a user, and supporting comfortable driving.

The sensor group 115 is one or more sensors mounted on the vehicle 110, and is, for example, a gyro sensor, a vehicle speed sensor, or the like. Some sensors in the sensor group 115 may be provided in the vehicle-mounted device 111 in place of or in addition to the vehicle 110.

The server device 120 stores travel history information 322, user information 323 (see FIG. 3) and the like, which will be described later. By downloading and acquiring this information from the server device 120, the in-vehicle device 111 can estimate the traveling route of the vehicle 110 and provide the information to the user.

For example, when the server device 120 receives a delivery request for stop information transmitted from the in-vehicle device 111 via the communication terminal 112 and the communication network 130, the server device 120 extracts the stop information corresponding to the delivery request from the user information 323 and is in-vehicle. Deliver to device 111. The stop information includes position information indicating the position of the vehicle 110 when the vehicle 110 stops at the intersection, and directional information indicating the direction of the vehicle 110 when the vehicle 110 stops at the intersection. The in-vehicle device 111 can transmit the stop information received from the server device 120 to the ADAS unit, or provide the user with screen display, voice output, or the like.

The communication line network 130 is constructed by, for example, a mobile phone line network, the Internet, or the like.

Note that FIG. 1 shows an example in which one in-vehicle device 111 mounted on one vehicle 110 is connected to the server device 120, but in reality, the in-vehicle devices mounted on a large number of vehicles are respectively. It is connected to the server device 120, and each in-vehicle device provides information to each user. In the present embodiment, the operation will be described using one of the in-vehicle devices 111 as a typical example, but the same applies to other in-vehicle devices.

However, the configuration of the operation information providing system 100 is not limited to the above-described configuration. For example, the server device 120 may not be provided. In this case, the in-vehicle device 111 includes all or a part of the configuration of the server device 120.

FIG. 2 is a diagram showing an example of the configuration of the in-vehicle device 111.

The in-vehicle device 111 includes a control device 210, a storage device 220, a display device 230, an operation device 240, and a position detection device 250.

The control device 210 includes a CPU (Central Processing Unit) and the like (not shown), and performs various processes and calculations for operating the in-vehicle device 111.

The storage device 220 is composed of at least one of a ROM (Read Only Memory), a RAM (Random Access Memory), an HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, and the like. The storage device 220 stores various types of information.

For example, the storage device 220 stores a part or all of the program group 221 (one or more programs) executed by the control device 210.

Further, for example, the storage device 220 is a map including various information related to the map (for example, information such as road position, connection, shape, width, number of lanes, and information such as topography, city name, area name, etc.). Information 222 is stored. Specifically, the map information 222 includes information indicating a road network including a plurality of links corresponding to a plurality of roads and a plurality of nodes corresponding to a plurality of intersections, and information indicating the attributes of roads in the road network. And include. That is, the map information for displaying the map screen in the in-vehicle device 111 is stored in the storage device 220 as the map information 222. A road network is generally a graph represented by nodes and links, but in the information indicating the road network, each of the nodes and links may be represented by polygons.

Further, for example, the storage device 220 stores individual information 280 corresponding to the user separately from the map information 222. The individual information 280 includes, for example, a travel history table 223 representing the travel history of the vehicle 110 and a personal event table 224 relating to an event that has occurred for the user.

In the in-vehicle device 111, for example, the program group 221 stored in the ROM is expanded into the RAM and executed by the CPU to execute the function of the in-vehicle device 111 (for example, the communication control unit 401 and the interface described later shown in FIG. 4). Control unit 402, position acquisition unit 403, display control unit 404, vehicle information acquisition unit 405, route prediction unit 406, stop information acquisition unit 407, remaining distance calculation unit 408, trajectory information acquisition unit 409, exit information acquisition unit 410, information The providing unit 411 and the point determination unit 412) can be realized. The details of the function of the in-vehicle device 111 will be described later.

In addition, the function of the in-vehicle device 111 may be realized by, for example, the CPU reading the program group 221 stored in the ROM into the RAM and executing it (software), or hardware such as a dedicated circuit. It may be realized by a combination of software and hardware. Further, a part of the functions of the vehicle-mounted device 111 may be realized by another computer (for example, the server device 120) capable of communicating with the vehicle-mounted device 111.

The display device 230 is an example of an output device, and displays various images, videos, and the like according to the control of the display control unit 404 described later. The display device 230 is configured by using, for example, a liquid crystal display.

The operation device 240 is an example of an input device, receives an operation input from a user, and outputs operation information according to the content of the received operation to the control device 210. The operation device 240 is composed of, for example, a touch panel integrated with the display device 230, various switches, and the like. Further, the operation device 240 may receive an operation input by voice from the user.

The position detection device 250 detects the current position of the vehicle 110 and outputs the detected result to the control device 210. The position detection device 250 is, for example, a GPS sensor.

FIG. 3 is a diagram showing an example of the configuration of the server device 120.

The server device 120 includes a control device 310, a storage device 320, and a communication device 330.

The control device 310 includes a CPU (not shown), and performs various processes and calculations for operating the server device 120.

The storage device 320 is composed of at least one of a ROM, a RAM, an HDD, an SSD, a memory card, and the like. The storage device 320 stores various types of information.

For example, the storage device 320 stores a part or all of the program group 321 (one or more programs) executed by the control device 310.

Further, for example, the storage device 320 stores the travel history information 322 showing the travel history of a large number of vehicles including the vehicle 110 connected to the server device 120. The travel history information 322 may include, for example, a travel history table for each user.

Further, for example, the storage device 320 stores user information 323, which is information about the user of each in-vehicle device. The user information 323 includes, for example, a personal event table 600 for each user (see FIG. 6), as will be described later.

The control device 310, for example, expands the program group 321 stored in the ROM into the RAM and executes the functions of the server device 120 (for example, the communication control unit 501 and the distribution unit 502, which will be described later shown in FIG. 5). And the information management unit 503) can be realized. The details of these functions realized by the control device 310 will be described later.

In addition, the function of the server device 120 may be realized by, for example, the CPU reading the program group 321 stored in the ROM into the RAM and executing it (software), or hardware such as a dedicated circuit. It may be realized by a combination of software and hardware. Further, a part of the functions of the server device 120 may be realized by another computer (for example, an in-vehicle device 111) capable of communicating with the server device 120.

FIG. 4 is a diagram showing an example of the function of the in-vehicle device 111.

The in-vehicle device 111 includes a communication control unit 401, an interface control unit 402, a position acquisition unit 403, a display control unit 404, a vehicle information acquisition unit 405, a route prediction unit 406, a stop information acquisition unit 407, a remaining distance calculation unit 408, and a trajectory information. It includes an acquisition unit 409, an exit information acquisition unit 410, an information provision unit 411, and a point determination unit 412.

The communication control unit 401 controls the communication terminal 112 when the in-vehicle device 111 communicates with the server device 120 via the communication terminal 112 and the communication network 130. The in-vehicle device 111 can transmit and receive information to and from the server device 120 by controlling the communication terminal 112 using the communication control unit 401.

The interface control unit 402 performs interface control when the vehicle-mounted device 111 communicates with the camera 113, the vehicle control device 114, and the sensor group 115, respectively. The in-vehicle device 111 communicates with the camera 113, the vehicle control device 114, and the sensor group 115, respectively, by the interface control performed by the interface control unit 402, acquires an captured image output from the camera 113, and controls the vehicle. It is possible to give an operation instruction to the device 114, notify information, and obtain a value from the sensor group 115.

The position acquisition unit 403 acquires the position detection result of the vehicle 110 from the position detection device 250. Further, the position acquisition unit 403 obtains the traveling direction of the in-vehicle device 111 from the sensor value of the gyro sensor, and obtains the speed of the vehicle 110 from the sensor value of the vehicle speed sensor, thereby obtaining the position (position) obtained from the sensor value of the GPS sensor. The relative position (relative position) from the absolute position (absolute position indicated by the position detection result acquired from the detection device 250) is obtained. The calculation of the relative position is generally called dead reckoning, and is performed periodically (for example, every 0.1 sec).

Here, the position (dead reckoning position) of the vehicle 110 in which the relative position is added to the absolute position is a numerical position coordinate including an error, and therefore does not completely match the road position of the map information 222. Therefore, the position acquisition unit 403 determines which road in the map information 222 the dead reckoning position corresponds to. Such processing is generally called map matching, and is performed periodically (for example, every 1 sec).

In this way, the position acquisition unit 403 sets the position of the vehicle 110 (map matching position) when the dead reckoning position is placed on the road considered to be the most suitable among the roads on the map stored in the map information 222. obtain. It should be noted that even if the dead reckoning position actually obtained as the position coordinates is numerically deviated from the road portion on the map, the trajectory of the vehicle 110 displayed on the display device 230 can be obtained by performing map matching. , The movement is almost in line with the road shape on the map.

The display control unit 404 controls the display device 230 to display the map screen using the map information 222 stored in the storage device 220. Further, the display device 230 is controlled to display the stop information acquired from the server device 120, the image showing the surrounding environment of the vehicle 110 generated based on the captured image acquired from the camera 113, and the like. Further, the display control unit 404 calls the user to call attention by controlling the display device 230 to display the screen related to the intersection.

The vehicle information acquisition unit 405 acquires various vehicle information regarding the traveling state of the vehicle 110. The vehicle information acquired by the vehicle information acquisition unit 405 includes, for example, an captured image output from the camera 113, control information output from the vehicle control device 114, and the like. The vehicle information acquisition unit 405 can acquire these vehicle information via the interface control unit 402.

The route prediction unit 406 predicts the travel route that the vehicle 110 will travel based on at least the travel history table 223 of the map information 222 and the travel history table 223. In the travel history table 223, the history of the route that the vehicle 110 has traveled in the past is recorded for each link row. The route prediction unit 406 can estimate the destination aimed at by the user by referring to the travel history table 223, and can predict the travel route of the vehicle 110 from the current position to the destination.

From the map information 222, the point determination unit 412 determines whether or not there is an intersection where the vehicle 110 enters the second road from the first road.

The stop information acquisition unit 407 provides stop information when the vehicle 110 stops on the first road (for example, when the vehicle 110 stops at the intersection) with respect to the intersection where the vehicle 110 enters the second road from the first road. Information indicating the stop position indicating the position of the vehicle 110 and the stop direction which is the direction of the vehicle 110 when the vehicle 110 stops at the intersection) is acquired. In the present embodiment, a case where the first road type is a narrow road and the second road type is a wide road will be described as an example. However, it is not limited to the combination of these road types. The type of road may be a predetermined one or may be determined by the width of the road or the like.

In addition, in the present embodiment, as will be described later, regarding the intersection where the vehicle 110 enters the second road from the first road, the type of the first road is a narrow road and the second road. It is presumed that an intersection whose type is wide road is an intersection with poor visibility.

The remaining distance calculation unit 408 calculates the approximate remaining distance, which is the distance from the position of the vehicle 110 to the intersection, or the detailed remaining distance, which is the distance from the position of the vehicle 110 to the stop position before entering the intersection. For example, the remaining distance calculation unit 408 calculates the distance each time the position of the vehicle 110 is updated by dead reckoning.

The locus information acquisition unit 409 acquires the position of the vehicle 110 after the vehicle 110 has stopped at the intersection as locus information.

The exit information acquisition unit 410 determines whether or not the vehicle 110 has left the intersection, and when it is determined that the vehicle 110 has left the intersection, the exit information acquisition unit 410 acquires exit information indicating that the vehicle 110 has left the intersection.

The information providing unit 411 includes stop information acquired by the stop information acquisition unit 407, information indicating the distance calculated by the remaining distance calculation unit 408, trajectory information acquired by the trajectory information acquisition unit 409, and exit information acquisition unit. At least a part of the exit information and the like acquired by 410 is provided to the display device 230 through the display control unit 404, provided to the vehicle control device 114 through the interface control unit 402, and through the communication control unit 401. Do at least one of the provisions to the server device 120.

For example, the information providing unit 411 gives an operation instruction to the vehicle control device 114 based on the map information near the current position acquired from the map information 222, the vehicle information acquired by the vehicle information acquisition unit 405, and the like, and the vehicle 110 Control the running condition. The information providing unit 411 can give an operation instruction to the vehicle control device 114 via the interface control unit 402. Further, the automatic operation of the vehicle 110 may be realized by the operation of the information providing unit 411.

FIG. 5 is a diagram showing an example of the functions of the server device 120.

The server device 120 includes a communication control unit 501, a distribution unit 502, and an information management unit 503.

The communication control unit 501 implements communication control necessary for the server device 120 to communicate with the in-vehicle device 111 via the communication terminal 112 and the communication network 130. The communication control unit 501, for example, performs interface processing between the server device 120 and the communication network 130 in communication control.

The distribution unit 502 distributes the information recorded in the travel history information 322 and the user information 323 to the vehicle-mounted device 111 in response to the distribution request from the vehicle-mounted device 111. For example, when a request for distribution of stop information of the vehicle 110 is received from the in-vehicle device 111, the distribution unit 502 acquires the stop information of the vehicle 110 corresponding to the user of the vehicle 110 and the position of the vehicle 110 from the user information 323 and is in-vehicle. Deliver to device 111. When the distribution unit 502 distributes information to the in-vehicle device 111, the communication control unit 501 communicates between the server device 120 and the in-vehicle device 111.

The information management unit 503 manages the information stored in the storage device 320. For example, the information management unit 503 updates the travel history information 322, the user information 323, and the like based on the input information from the operator of the server device 120, the user of the vehicle 110, and the like.

For example, the information management unit 503 stores the stop information acquired by the stop information acquisition unit 407 in association with the link information of the road related to the intersection (for example, the identification information that can identify the link).

Further, for example, when the latest stop information of the vehicle 110 is transmitted from the in-vehicle device 111, the information management unit 503 updates the stop information of the user information 323 already stored based on the latest stop information. More specifically, when the information management unit 503 stores the stop information acquired by the stop information acquisition unit 407 in association with the link information, when one or more other stop information is stored for the link information. , All the stop information of the link information is filtered to remove noise, a representative value is calculated, and the calculated representative value is stored in association with the link information as stop information related to the intersection.

FIG. 6 is a diagram showing an example of the personal event table 600 included in the user information 323. The personal event table 600 is provided for each user, and in the personal event table 600, various information (event information) related to an individual that cannot be supplemented from the map information 222 is managed in association with the link information.

In the personal event table 600, event information (for example, EventID640, EventDATA650, etc.) is stored for each link information (for example, LinkID610, RoadType620, Direction630, etc.).

LinkID610 is identification information that can identify a link for showing an actually existing road on a map. RoadType 620 is information indicating the type of road (narrow road, wide road, etc.). The Direction 630 is information indicating the orientation of the vehicle 110 when map matching is performed. The EventID 640 is information that can identify the type of event that has occurred on the road (acquisition of stop information, acquisition of trajectory information, etc.). EventDATA650 refers to the position of the vehicle 110 when the vehicle 110 stops at an intersection with poor visibility (stop position), the orientation of the vehicle 110 when the vehicle 110 stops at an intersection with poor visibility (stop orientation), and the intersection with poor visibility. Data such as the route (trajectory) on which the vehicle 110 traveled, the position (exit position) where the vehicle 110 exited an intersection with poor visibility, the operation history of the operating device 240, the mode of the vehicle 110, the route on which the vehicle 110 traveled, and the like. ..

Next, the operation contents of the in-vehicle device 111 and the server device 120 when providing driving support related to an intersection will be described.

FIG. 7 is a diagram showing an example of a flowchart related to a process of calculating a link distance, which is a distance from a start point node of a link on a road on which a vehicle 110 is traveling to an intersection with poor visibility. The control device 210 of the in-vehicle device 111 executes, for example, the process shown in FIG. 7 at a predetermined process cycle.

In step S701, the vehicle-mounted device 111 acquires the predicted route. For example, the vehicle-mounted device 111 acquires a link from the current location (current position of the vehicle 110) to the destination (position that the vehicle 110 intends to aim at) from the map information 222. The predicted route may be a predicted route without inputting a destination.

In step S702, the in-vehicle device 111 determines whether or not the link can be acquired (whether or not there is a prediction route). When the in-vehicle device 111 determines that there is a predicted route, the process shifts to step S703, and when it is determined that there is no predicted route, the in-vehicle device 111 ends the process.

In step S703, the vehicle-mounted device 111 waits for the input of the map matching information. For example, the in-vehicle device 111 waits until the map matching position is calculated.

In step S704, the vehicle-mounted device 111 determines whether or not the map matching position has been updated. When it is determined that the map matching position has been updated, the in-vehicle device 111 shifts the process to step S705, and when it determines that the map matching position has not been updated, the in-vehicle device 111 ends the process.

In step S705, the vehicle-mounted device 111 determines whether or not the link has been changed. When it is determined that the link has been changed, the in-vehicle device 111 shifts the process to step S706, and when it determines that the link has not been changed, the in-vehicle device 111 ends the process.

In step S706, the vehicle-mounted device 111 sets the link offset. For example, the vehicle-mounted device 111 sets the start point node of the map-matched link as the link offset.

In step S707, the vehicle-mounted device 111 acquires an intersection with poor visibility on the predicted route. More specifically, the in-vehicle device 111 identifies a node (intersection node) in which the road type changes from a narrow road to a wide road as an intersection with poor visibility on the predicted route based on the map information 222, and sets the pair. Get all the links (narrow road links and wide road links).

In step S708, the vehicle-mounted device 111 determines whether or not an intersection with poor visibility can be acquired (whether or not there is an intersection with poor visibility). When the in-vehicle device 111 determines that there is an intersection with poor visibility, the process shifts to step S709, and when it is determined that there is no intersection with poor visibility, the in-vehicle device 111 ends the process.

In step S709, the vehicle-mounted device 111 calculates the distance (link distance) from the link offset to the intersection node.

FIG. 8 is a diagram showing an example of a flowchart related to a process of calculating an approximate remaining distance, which is an approximate distance from the current position of the vehicle 110 to an intersection with poor visibility. The control device 210 of the in-vehicle device 111 executes, for example, the process shown in FIG. 8 at a predetermined process cycle.

In step S801, the in-vehicle device 111 determines whether or not the link distance is calculated (set). When it is determined that the link distance is set, the in-vehicle device 111 shifts the process to step S802, and when it is determined that the link distance is not set, the in-vehicle device 111 ends the process.

In step S802, the vehicle-mounted device 111 waits for the input of dead reckoning information. For example, the vehicle-mounted device 111 waits until the dead reckoning position is calculated.

In step S803, the vehicle-mounted device 111 determines whether or not the dead reckoning position has been updated. When it is determined that the dead reckoning position has been updated, the in-vehicle device 111 shifts the process to step S804, and when it determines that the dead reckoning position has not been updated, the in-vehicle device 111 ends the process.

In step S804, the vehicle-mounted device 111 determines whether or not there is an intersection with poor visibility. When the in-vehicle device 111 determines that there is an intersection with poor visibility, the process shifts to step S805, and when it is determined that there is no intersection with poor visibility, the in-vehicle device 111 ends the process.

In step S805, the vehicle-mounted device 111 calculates the vehicle offset. More specifically, the in-vehicle device 111 calculates the relative distance between the map matching position and the dead reckoning position as a vehicle offset.

In step S806, the in-vehicle device 111 calculates the estimated remaining distance. More specifically, the in-vehicle device 111 calculates the approximate remaining distance by subtracting the vehicle offset from the link distance.

FIG. 9 is a diagram for explaining the approximate remaining distance. In FIG. 9, a case where the links of LinkIDs “1”, “10”, “3”, and “12” are acquired in step S701 as the links corresponding to the traveling route will be described as an example. In the following description, the link with LinkID "n" can be referred to as "link n". Further, the road corresponding to the link n can be referred to as "road n". Further, when the vehicle 110 enters the intersection and exits from the intersection, the road on the approach side of the intersection is referred to as an "approach road", the link corresponding to the approach road is referred to as an "approach link", and the exit side of the intersection is referred to. A road can be referred to as an "exit route", and a link corresponding to the exit route can be referred to as an "exit link". In this example, it is assumed that the approach road 3 is a narrow road as the approach link 3 is represented by a broken line, and the exit road 12 is a wide road as the exit link 12 is represented by a solid line. Therefore, the intersection corresponding to the node 901-2 connecting the link 3 to the link 12 is an intersection with poor visibility.

First, by the processing of FIG. 7, the distance from the start point node 901-1 of the link 1 to the node 901-2 which is the intersection node of the intersection with poor visibility, that is, from the intersection corresponding to the node 901-1 to the node 901-2 The distance 903 (link distance) to the intersection corresponding to is calculated.

Next, by the processing of FIG. 8, the distance 913 (relative distance) between the position 911 indicating the map matching position and the position 912 indicating the dead reckoning position is calculated, and the distance 903 (link distance) to the distance 913 (relative distance) are calculated. Is subtracted to calculate the approximate remaining distance.

FIG. 10 is a diagram showing an example of a flowchart related to a process of acquiring stop information related to an intersection with poor visibility. The control device 210 of the in-vehicle device 111 executes, for example, the process shown in FIG. 10 at a predetermined process cycle.

In step S1001, the vehicle-mounted device 111 determines whether or not the estimated remaining distance is equal to or less than a predetermined distance (for example, 50 m). The in-vehicle device 111 shifts the process to step S1002 when it is determined that the estimated remaining distance is not less than or equal to the predetermined distance, and ends the process when it is determined that the estimated remaining distance is not less than or equal to the predetermined distance.

In step S1002, the in-vehicle device 111 determines whether or not the road shape is straight. When the in-vehicle device 111 determines that the road shape is straight, the process proceeds to step S1003, and when the in-vehicle device 111 determines that the road shape is not straight, the process ends. For example, the in-vehicle device 111 determines that the road shape is straight when the added value of the directional difference of the link row to the intersection with poor visibility is equal to or less than a predetermined value.

According to this process, it is possible to reduce the possibility of acquiring inappropriate stop information in a road environment where roads are densely packed in a residential area or the like. Further, for example, it is a road for acquiring stop information even when the road on which the vehicle 110 is traveling cannot be specified because the roads are densely packed in a residential area or the like and map matching cannot be performed. Since it can be determined whether or not the vehicle has stopped, it is possible to avoid a situation in which stop information cannot be obtained.

In step S1003, the in-vehicle device 111 determines the stop of the vehicle 110. For example, the vehicle-mounted device 111 acquires the speed of the vehicle 110.

In step S1004, the vehicle-mounted device 111 determines whether or not the vehicle 110 has stopped (for example, whether or not the speed of the vehicle 110 has become "0"). When it is determined that the vehicle 110 has stopped, the in-vehicle device 111 shifts the process to step S1005, and when it determines that the vehicle 110 has not stopped, the in-vehicle device 111 ends the process.

In step S1005, the vehicle-mounted device 111 acquires stop information, which is information related to the stop of the vehicle 110. For example, the in-vehicle device 111 acquires the dead reckoning position when the vehicle 110 stops as a stop position related to an intersection with poor visibility, and acquires and acquires the direction of the vehicle 110 when the vehicle 110 stops as a stop direction. The stop position and stop direction are used as stop information.

In step S1006, the vehicle-mounted device 111 transmits a stop information writing request to the server device 120. For example, the stop information writing request includes a user ID that can identify the user of the vehicle 110, narrow road link information (LinkID, etc.), event information (Event ID indicating acquisition of stop information, and EventDATA including the acquired stop information. Etc.) are included.

FIG. 11 is a diagram showing an example of a flowchart related to a process in which the server device 120 stores stop information. The control device 310 of the server device 120 executes, for example, the process shown in FIG. 11 at a predetermined process cycle.

In step S1101, the server device 120 determines whether or not there is a request to write stop information. When the server device 120 determines that there is a stop information write request, it shifts the process to step S1102, and when it determines that there is no stop information write request, the server device 120 ends the process.

In step S1102, the server device 120 determines whether or not the stop information is already associated with the link from which the stop information of the write request has been acquired (whether or not there is a memory). When the server device 120 determines that there is a memory, the process is transferred to step S1103, and when it is determined that there is no memory, the server device 120 transfers the process to step S1104. For example, the server device 120 identifies the user information of the user of the vehicle 110 from the user information 323 based on the user ID of the write request, and in the specified user information, the write request in the link of the link ID of the write request. It is determined whether or not the stop information is stored in the EventDATA of the EventID event.

In step S1103, the server device 120 calculates the stop position (set value). For example, the server device 120 calculates a probable stop position as a set value using a statistical model. More specifically, the server device 120 performs filtering processing (clustering) on all the stop positions of the same link to remove noise and calculate a representative value (for example, an average value).

For example, when the vehicle 110 is traveling in a residential area and priority is given to pedestrians, the vehicle 110 may stop temporarily. Since this stop is not a stop related to an intersection with poor visibility, it is unnecessary data and becomes a factor of lowering the accuracy of the stop position related to the intersection with poor visibility. In this respect, in the vehicle 110, by performing clustering, it is possible to eliminate the data of such a temporary stop, and it is possible to improve the accuracy of the stop position related to the intersection with poor visibility.

The server device 120 also processes the stop direction in the same manner as the stop position.

In step S1104, the server device 120 performs storage processing. For example, the server device 120 stores (stores) write request stop information in association with link information. Further, for example, the server device 120 stores the acquired stop information or the calculated representative value in association with the link information (in the EventDATA of the eventID event of the write request in the LinkID link of the write request).

The process shown in FIG. 11 may be configured to be executed by the in-vehicle device 111. In this case, from the viewpoint of data capacity, the in-vehicle device 111 does not accumulate, for example, the stop information of the write request in association with the link information, and "value up to the previous time x 0.8 + value this time x 0.2". May be calculated to calculate the representative value.

FIG. 12 is a diagram for explaining a stop position.

Conventionally, the distance from the position of the vehicle 110 to the node 1201 at the intersection with poor visibility is calculated as the distance until the vehicle 110 stops (detailed remaining distance). That is, the conventional remaining distance includes the distance 1203 from the node 1201 to the actual stop line 1202 as an error. Here, the remaining distance expected from the ADAS unit is not the distance from the position of the vehicle 110 to the node 1201 at the intersection, but the distance from the position of the vehicle 110 to the stop line 1202.

In this regard, the vehicle 110 is provided to the ADAS unit by estimating the stop position of the vehicle 110 related to the intersection with poor visibility (for example, obtaining a representative value 1204 of the stop position) in order to reduce the above error. The accuracy of the information to be processed is improved.

As shown in FIG. 12, when a plurality of stop positions are stored, cluster 1205 is provided by clustering, and stop positions that become noise outside the cluster 1205 are eliminated. Subsequently, the representative value 1204 is calculated from the stop position in the cluster 1205.

FIG. 13 is a diagram showing an example of a flowchart related to the process of calculating the distance from the current position of the vehicle 110 to the stop position (including the case of the representative value). The control device 210 of the in-vehicle device 111 executes, for example, the process shown in FIG. 13 at a predetermined process cycle.

In step S1301, the vehicle-mounted device 111 acquires the predicted route. For example, the vehicle-mounted device 111 acquires a link from the current location to the destination from the map information 222.

In step S1302, the vehicle-mounted device 111 determines whether or not there is an intersection with poor visibility. When the in-vehicle device 111 determines that there is an intersection with poor visibility, the process shifts to step S1303, and when it is determined that there is no intersection with poor visibility, the in-vehicle device 111 ends the process.

The in-vehicle device 111 performs the same processing as in steps S702 and S707 in steps S1301 to S1302, but the description thereof will be omitted.

In step S1303, the in-vehicle device 111 acquires (requests) the stop position of the intersection with poor visibility from the server device 120. The in-vehicle device 111 is a server that can identify a user ID, link information of a narrow road at an intersection with poor visibility (for example, LinkID of a narrow road), and event information (for example, an event ID indicating acquisition of stop information). It is transmitted to the device 120. The server device 120 searches for the requested stop position from the user information 323, and transmits the search result to the in-vehicle device 111.

In step S1304, the in-vehicle device 111 determines whether or not there is a stop position at an intersection with poor visibility. When the in-vehicle device 111 determines that there is a stop position at an intersection with poor visibility, it shifts the process to step S1305, and when it determines that there is no stop position at the intersection with poor visibility, it shifts the process to step S1314.

In step S1305, the in-vehicle device 111 calculates the link distance and the vehicle offset to calculate the estimated remaining distance in the same manner as in the processes shown in FIGS. 7 and 8.

In step S1306, the in-vehicle device 111 determines whether or not the estimated remaining distance is within a predetermined distance (for example, 100 m). When the in-vehicle device 111 determines that the estimated remaining distance is within a predetermined distance, it shifts the process to step S1307, and when it determines that the estimated remaining distance is not within the predetermined distance, the in-vehicle device 111 ends the process.

In step S1307, the vehicle-mounted device 111 determines whether or not the dead reckoning position has been updated. When it is determined that the dead reckoning position has been updated, the in-vehicle device 111 shifts the process to step S1308, and when it determines that the dead reckoning position has not been updated, the in-vehicle device 111 ends the process.

In step S1308, the vehicle-mounted device 111 sets the dead reckoning position as the dead reckoning offset.

In step S1309, the vehicle-mounted device 111 calculates the distance (offset distance) from the dead reckoning offset to the stop position.

In step S1310, the vehicle-mounted device 111 determines whether or not the speed of the vehicle 110 has been received (measured). When the in-vehicle device 111 determines that the speed of the vehicle 110 has been received, it shifts the process to step S1311, and when it determines that the speed of the vehicle 110 has not been received, the in-vehicle device 111 ends the process.

In step S1311, the in-vehicle device 111 determines the distance (mileage) traveled by the vehicle 110 from the dead reckoning offset based on the received speed of the vehicle 110, the time when the dead reckoning position is acquired, and the current time. calculate.

In step S1312, the in-vehicle device 111 calculates the distance (detailed remaining distance) from the current position of the vehicle 110 to the stop position. More specifically, the in-vehicle device 111 calculates the detailed remaining distance by subtracting the mileage from the offset distance.

In step S1313, the in-vehicle device 111 provides the calculated detailed remaining distance to the ADAS unit, the display control unit 404, and the like. For example, when the vehicle-mounted device 111 transmits the detailed remaining distance to the ADAS unit, the ADAS unit slows down or stops the speed of the vehicle 110 based on the detailed remaining distance, considering the position where the vehicle stops at an intersection with poor visibility. Properly provide driving support for intersections with poor visibility, such as announcing that it must be done. Further, for example, when the in-vehicle device 111 transmits the detailed remaining distance to the display control unit 404, it is related to an intersection with poor visibility, such as emphasizing the stop line displayed on the navigation screen and displaying that the vehicle must stop. Properly provide driving support.

In step S1314, the in-vehicle device 111 performs stop information acquisition processing (processing of FIGS. 10 and 11).

FIG. 14 is a diagram for explaining the detailed remaining distance.

First, the offset distance 1403, which is the distance from the position 1401 indicating the dead reckoning position to the position 1402 indicating the stop position, is calculated. Subsequently, at the timing when the speed of the vehicle 110 is acquired, the mileage 1404 from the position 1401 is calculated based on the speed of the vehicle 110, and the mileage 1404 is subtracted from the offset distance 1403 to calculate the detailed remaining distance. To.

FIG. 15 is a diagram showing an example of a flowchart related to a process in which the vehicle-mounted device 111 acquires trajectory information. The control device 210 of the in-vehicle device 111 executes, for example, the process shown in FIG. 15 at a predetermined process cycle.

In step S1501, the in-vehicle device 111 determines whether or not the detailed remaining distance is within a predetermined distance (for example, 50 m). The in-vehicle device 111 shifts the process to step S1502 when it is determined that the detailed remaining distance is within a predetermined distance, and ends the process when it is determined that the detailed remaining distance is not within the predetermined distance.

In step S1502, the vehicle-mounted device 111 determines whether or not the vehicle 110 has stopped at an intersection with poor visibility. When it is determined that the vehicle 110 has stopped, the in-vehicle device 111 shifts the process to step S1503, and when it determines that the vehicle 110 has not stopped, the in-vehicle device 111 ends the process.

In step S1503, the vehicle-mounted device 111 determines whether or not the dead reckoning position has been updated. When it is determined that the dead reckoning position has been updated, the in-vehicle device 111 shifts the process to step S1504, and when it determines that the dead reckoning position has not been updated, the in-vehicle device 111 ends the process.

In step S1504, the vehicle-mounted device 111 records the dead reckoning position. In this way, the vehicle-mounted device 111 records the dead reckoning position every time the dead reckoning position is updated after the vehicle 110 stops at an intersection with poor visibility.

In step S1505, the vehicle-mounted device 111 determines whether or not the vehicle 110 has left an intersection with poor visibility. When it is determined that the vehicle 110 has exited the intersection with poor visibility, the in-vehicle device 111 shifts the process to step S1506, and ends the process when it is determined that the vehicle 110 has not exited the intersection with poor visibility. Whether or not the vehicle 110 has left an intersection with poor visibility can be determined by, for example, the processes shown in FIGS. 19 and 20.

In step S1506, the vehicle-mounted device 111 finishes recording the dead reckoning position.

In step S1507, the vehicle-mounted device 111 transmits a locus information writing request to the server device 120. For example, in the request for writing track information, a user ID that can identify the user of the vehicle 110, wide road link information (LinkID, etc.), event information (Event ID indicating acquisition of track information, Event DATA including acquired track information) Etc.) are included.

FIG. 16 is a diagram showing an example of a flowchart related to a process in which the server device 120 stores locus information. The control device 310 of the server device 120 executes, for example, the process shown in FIG. 16 at a predetermined process cycle.

In step S1601, the server device 120 determines whether or not the writing class of the locus information has been received. When it is determined that the locus information writing class has been received, the server device 120 shifts the process to step S1602, and when it is determined that the locus information writing class has not been received, the server device 120 ends the process.

In step S1602, the server device 120 determines whether or not the locus information is already associated with the link from which the locus information of the write request has been acquired (whether or not there is memory). When the server device 120 determines that there is a memory, the process is transferred to step S1603, and when it is determined that there is no memory, the server device 120 shifts the process to step S1604. For example, the server device 120 identifies the user information of the user of the vehicle 110 from the user information 323 based on the user ID of the write request, and in the specified user information, the write request in the link of the link ID of the write request. It is determined whether or not the trajectory information is stored in the EventDATA of the EventID event.

In step S1603, the server device 120 calculates the locus information. For example, the server device 120 uses a statistical method (eg, regression analysis) to identify probable trajectory information. The process shown in FIG. 16 may be configured to be performed by the in-vehicle device 111. When the in-vehicle device 111 is used, from the viewpoint of hardware resources, for example, the in-vehicle device 111 may clear the locus information and store the locus information of the write request (hold the latest locus information).

In step S1604, the server device 120 performs storage processing. For example, the server device 120 stores (stores) the locus information of the write request in association with the link information. Further, for example, the server device 120 stores the acquired locus information or the calculated locus information in association with the link information (in the event DATA of the event ID event of the write request in the link of the link ID of the write request).

FIG. 17 is a diagram showing an example of a flowchart related to a process in which the vehicle-mounted device 111 calculates a distance and a direction from the current position of the vehicle 110 to the trajectory information. The control device 210 of the in-vehicle device 111 executes, for example, the process shown in FIG. 17 at a predetermined process cycle.

In step S1701, the in-vehicle device 111 determines whether or not the detailed remaining distance is within a predetermined distance (for example, 100 m). The in-vehicle device 111 shifts the process to step S1702 when it is determined that the detailed remaining distance is within a predetermined distance, and ends the process when it is determined that the detailed remaining distance is not within the predetermined distance.

In step S1702, the in-vehicle device 111 calculates the distance (trajectory distance) and the direction (trajectory direction) from the current position of the vehicle 110 to the locus information. More specifically, the in-vehicle device 111 acquires (requests) locus information of an intersection with poor visibility from the server device 120. The in-vehicle device 111 is a server that can identify a user ID, link information of a wide road at an intersection with poor visibility (for example, LinkID of a wide road), and event information (for example, Event ID indicating acquisition of trajectory information). It is transmitted to the device 120. The server device 120 searches for the requested trajectory information from the user information 323, and transmits the search result to the in-vehicle device 111. The in-vehicle device 111 receives the search result, calculates the distance between the current position of the vehicle 110 and the position where the recording of the locus information is started as the locus distance, and records the locus information from the current position of the vehicle 110. The direction to the position where is started is calculated as the trajectory direction.

In step S1703, the in-vehicle device 111 provides the calculated locus distance and locus direction to the ADAS unit, the display control unit 404, and the like. For example, by providing the locus position to the ADAS unit, it becomes possible to provide driving support related to an intersection with poor visibility, such as controlling the speed of the vehicle 110 when the vehicle 110 is passing through the intersection. Further, for example, by providing the locus position to the display control unit 404, it becomes possible to provide driving support related to an intersection with poor visibility, such as displaying a traveling route, a radius of curvature, etc. on the navigation screen.

FIG. 18 is a diagram for explaining trajectory information.

As shown in FIG. 18, from the entrance point 1801 to the exit point 1802 of the intersection with poor visibility, the dead reckoning position is acquired as the locus 1803 of the vehicle 110 every time the dead reckoning position is updated.

FIG. 19 is a diagram showing an example of a flowchart related to a process in which the in-vehicle device 111 calculates a reference directional difference. The control device 210 of the in-vehicle device 111 executes, for example, the process shown in FIG. 19 at a predetermined process cycle.

In step S1901, the in-vehicle device 111 determines whether or not the detailed remaining distance is within a predetermined distance (for example, 50 m). When the in-vehicle device 111 determines that the detailed remaining distance is within a predetermined distance, the process shifts to step S1902, and when it is determined that the detailed remaining distance is not within the predetermined distance, the in-vehicle device 111 ends the process.

In step S1902, the in-vehicle device 111 determines the stop of the vehicle 110. For example, the vehicle-mounted device 111 acquires the speed of the vehicle 110.

In step S1903, the vehicle-mounted device 111 determines whether or not the vehicle 110 has stopped (for example, whether or not the speed of the vehicle 110 has become "0"). When it is determined that the vehicle 110 has stopped, the in-vehicle device 111 shifts the process to step S1904, and when it determines that the vehicle 110 has not stopped, the in-vehicle device 111 ends the process.

In step S1904, the vehicle-mounted device 111 acquires the dead reckoning position and the direction (hereinafter, referred to as the direction A) when the vehicle 110 is stopped.

In step S1905, the in-vehicle device 111 acquires the direction of the exit link (hereinafter, referred to as direction B).

In step S1906, the vehicle-mounted device 111 calculates the reference directional difference (| directional A-direction B |).

FIG. 20 is a diagram showing an example of a flowchart related to a process in which the in-vehicle device 111 determines the exit from an intersection having poor visibility. The control device 210 of the in-vehicle device 111 executes, for example, the process shown in FIG. 20 at a predetermined process cycle.

In step S2001, the vehicle-mounted device 111 determines whether or not the dead reckoning position has been updated. When it is determined that the dead reckoning position has been updated, the in-vehicle device 111 shifts the process to step S2002, and when it determines that the dead reckoning position has not been updated, the in-vehicle device 111 ends the process.

In step S2002, the in-vehicle device 111 determines whether or not the reference directional difference is calculated. When the in-vehicle device 111 determines that the reference directional difference is calculated, the process is transferred to step S2003, and when it is determined that the reference directional difference is not calculated, the in-vehicle device 111 ends the process.

In step S2003, the vehicle-mounted device 111 acquires the current direction of the vehicle 110 (hereinafter, referred to as direction C).

In step S2004, whether or not the in-vehicle device 111 satisfies a predetermined condition (| direction B-direction C | ≤ α × reference direction difference) (whether or not the direction C and the direction of the exit road match). To judge. When it is determined that the predetermined condition is satisfied, the in-vehicle device 111 shifts the process to step S2005, and when it is determined that the predetermined condition is not satisfied, the in-vehicle device 111 ends the process. In addition, α is a predetermined coefficient (for example, 0.3).

In step S2005, the in-vehicle device 111 determines that the direction C and the direction of the exit road match.

In step S2006, the in-vehicle device 111 determines the passage of the stop position. For example, the stop position of an intersection with poor visibility is acquired (requested) from the server device 120.

In step S2007, the in-vehicle device 111 determines whether or not the vehicle has passed the stop position. When the in-vehicle device 111 determines that the stop position has been passed, the process proceeds to step S2008, and when it is determined that the stop position has not been passed, the in-vehicle device 111 ends the process.

In step S2008, the vehicle-mounted device 111 acquires exit information indicating that the vehicle has exited from an intersection with poor visibility.

In step S2009, the in-vehicle device 111 transmits the exit information to the ADAS unit or the like. For example, by providing the exit information to the ADAS unit, it becomes possible to end the driving support related to the intersection with poor visibility at an appropriate timing.

FIG. 21 is a diagram for explaining the determination of exit.

Conventionally, it is determined whether or not an intersection with poor visibility has been exited when map matching is performed. Map matching is performed at predetermined intervals (for example, 1 second), but in the vicinity of an intersection where a plurality of roads intersect, near an intersection where roads are dense, etc., it is determined which road the vehicle 110 is to be matched with. It may not be possible, and map matching may not be possible until the vehicle 110 has traveled several tens of meters (for example, 50 m). In such a case, the timing of notifying the ADAS unit of the instruction to end the driving support related to the intersection with poor visibility is delayed.

In this regard, the vehicle 110 is involved in an intersection with poor visibility by determining whether or not the vehicle 110 has exited the intersection with poor visibility by using the direction of the vehicle 110 at the time of dead reckoning after entering the intersection with poor visibility. The driving support is terminated promptly.

As shown in FIG. 21, when the vehicle 110 is stopped, the direction 2101 (direction A) of the vehicle 110 is acquired. The directional 2102 (direction C) of the vehicle 110 is acquired each time the dead reckoning position is updated until the vehicle 110 exits an intersection with poor visibility. When the direction 2101, the direction 2102, and the direction 2103 (direction B) of the road to be exited satisfy the predetermined conditions, it is determined that the vehicle 110 has left the intersection with poor visibility.

It should be noted that the driving information providing system 100 does not exclude the determination method in which (| direction B-direction C |) ≤ 30 degrees is determined. However, in this determination method, when the approach road and the exit road have an acute angle, the condition is already satisfied when the vehicle 110 stops at the position of the stop line, and it is erroneously determined that the vehicle 110 has left. It ends up. Therefore, even with such a determination method, when it is determined that the approach road and the exit road have an acute angle, it is preferable to make a judgment using a predetermined condition.

According to the present embodiment, since the stop information related to the intersection is acquired, the driving support related to the intersection can be provided at an appropriate timing.
(2) Second embodiment

In the first embodiment, the intersection connecting the narrow road to the wide road is an intersection with poor visibility, but in the second embodiment, the intersection connecting the narrow road to the wide road is a narrow road to the wide road. It is a candidate intersection that is a candidate for an intersection that connects to. Whether the candidate intersection is an intersection with poor visibility or an ordinary intersection (an intersection other than an intersection with poor visibility) is determined based on the recognition result of the image captured for the candidate intersection.

Hereinafter, the second embodiment will be described in detail. At that time, the differences from the first embodiment will be mainly described, and the common points with the first embodiment will be omitted or simplified.

FIG. 22 is a diagram showing an example of the configuration of the driving support system according to the second embodiment.

The vehicle 110 includes an in-vehicle device 2211 in place of the in-vehicle device 111. The in-vehicle device 2211 captures an image of the candidate intersection determined from the map information 222, and determines whether or not the candidate intersection is an intersection with poor visibility based on the recognition result of the captured image.

The management server device 2220 and the object detection server device 2230 are connected to the communication network 130 instead of the server device 120. The management server device 2220 is a device that manages information stored in the vehicle-mounted device 2211, and communicates with the vehicle-mounted device 2211 and the object detection server device 2230. The object detection server device 2230 is a device that recognizes an image of the captured image and communicates with the management server device 2220. The management server device 2220 and the object detection server device 2230 may be integrated devices. Further, the configuration of the management server device 2220 may be the same as that of the server device 120. Further, at least one of the functions of the management server device 2220 or at least one of the functions of the object detection server device 2230 may be realized on a computing resource pool such as a cloud platform.

In the present embodiment, for example, the following processing is performed. That is, the in-vehicle device 2211 transmits image data indicating the captured image to the management server device 2220. The management server device 2220 stores the image data and transmits the image data to the object detection server device 2230. The object detection server device 2230 performs image recognition including determination of whether or not a predetermined type of object is reflected in the image indicated by the image data. The object detection server device 2230 returns the recognition result information indicating the result of the image recognition to the management server device 2220. The management server device 2220 stores the recognition result information and transmits the recognition result information to the in-vehicle device 2211. As a result, the in-vehicle device 2211 can know the result of image recognition of the captured image.

FIG. 23 is a diagram showing an example of the function of the in-vehicle device 2211.

In addition to the functions 401 to 410 and 412 in the first embodiment, the in-vehicle device 2211 includes an information providing unit 2301 that provides the vehicle control device 114 with information indicating reliability, which will be described later, and a LinkID (an example of link information). It is provided with an information management unit 2302 that associates event information with the camera 113 and an imaging unit 2303 that captures images with the camera 113.

In FIG. 23, the functions 405 to 410, 412, 2301 and 2302 can be the support control unit 2300. The imaging unit 2303 may operate in response to a request from the support control unit 2300. The position acquisition unit 403 performs dead reckoning and map matching. In the present embodiment, the position acquisition unit 403 and the support control unit 2300 cooperate with each other, and the support control unit 2300 appropriately executes the image pickup unit 2303 in the cooperation to realize the driving support. Each time the position acquisition unit 403 acquires the vehicle position, information indicating the acquired vehicle position is provided to the support control unit 2300. The position acquisition unit 403 may be included in the support control unit 2300.

Some of the functions described in the first embodiment (for example, stop information acquisition unit 407) may be omitted.

FIG. 24 is a diagram showing an example of the functions of the management server device 2220.

The management server device 2220 includes a communication control unit 2401, a distribution unit 2402, and an information management unit 2403.

The communication control unit 2401 implements communication control necessary for communicating with the in-vehicle device 2211 and the object detection server device 2230.

In response to the event file request from the in-vehicle device 2211, the distribution unit 2402 generates an event file corresponding to the user of the in-vehicle device 2211 from the personal event table 600 corresponding to the user, and generates the generated event file in the in-vehicle device. It will be delivered to 2211. In addition, the distribution unit 2402 transmits the image data from the in-vehicle device 2211 to the object detection server device 2230.

The information management unit 2403 saves the image data from the in-vehicle device 2211 and saves the recognition result information from the object detection server device 2230.

FIG. 25 is a diagram showing an example of the function of the object detection server device 2230.

The object detection server device 2230 includes a communication control unit 2501 and an image recognition unit 2502.

The communication control unit 2501 executes the communication control necessary for communicating with the management server device 2220.

The image recognition unit 2502 performs image recognition of the image indicated by the image data from the management server device 2220, and returns a return value including the recognition result information indicating the result of the image recognition to the management server device 2220.

FIG. 26 is a diagram for explaining an outline of the present embodiment. In FIG. 26, as in FIG. 9, the link corresponding to the narrow road is represented by a broken line, and the link corresponding to the wide road is represented by a solid line. Further, in FIG. 26, among the acquired vehicle positions 2603-1 to 2603-7, the vehicle positions 2603-1 and 2603-7 are map matching positions, respectively, and the vehicle positions 2603 to 2603-6 are. Each is a dead reckoning position.

The point determination unit 412 determines from the map information 222 whether or not there is a candidate intersection (candidate for an intersection with poor visibility). Here, the intersection corresponding to the node 2601-2 connecting the link 3 to the link 12 (the intersection connecting the narrow road 3 to the wide road 12) is a candidate intersection.

When it is determined that the candidate intersection exists and the vehicle 110 is determined to approach the candidate intersection, the imaging unit 2303 captures an image with at least the camera 113-1 of the cameras 113-1 to 113-4. As a result, an image of at least the front side of the vehicle (an example of at least a part of the circumference of the vehicle 110) is captured. Image data indicating the image is sent from the in-vehicle device 2211 to the object detection server device 2230 through the management server device 2220, and image recognition of the image indicated by the image data is performed by the object detection server device 2230. The recognition result information indicating the result of the image recognition is sent to the management server device 2220, and the event information including the recognition result information is sent from the management server device 2220 to the in-vehicle device 2211. The information management unit 2302 associates the event information with the LinkID of the target link, which is a link corresponding to the point related to the imaging of the image.

Here, the "linkID of the target link" is the LinkID acquired in the map matching in one comparative example. The navigation system (for example, the position acquisition unit 403) generally performs a process of map matching and dead reckoning, but since the route on which the vehicle 110 actually travels is unknown (for example, a destination is input and a route to the destination is searched for). Even if this is done, the vehicle 110 does not always travel according to the searched route), because the LinkID is generally not acquired by any process other than map matching. However, map matching is not always performed (or succeeded) depending on the road environment in which the vehicle 110 is traveling. For example, in FIG. 26, when the vehicle 110 travels on those roads in the order of wide road 1 → narrow road 10 → narrow road 3 → wide road 12, the road environment including the narrow road 10 and the narrow road 3 is a road. Due to the dense environment, it happens that map matching was performed only on road 1 and road 12. In this case, even if the image is captured on the narrow road 3, the recently acquired LinkID is "1" because the road for which map matching has been performed recently is the wide road 1, and therefore, in one comparative example, The event information including the information indicating the recognition result of the captured image is associated with the LinkID "1". Therefore, the correct event information is not associated with the LinkID "3", and the incorrect event information is associated with the LinkID "1", so that appropriate driving support may not be provided on the narrow road 3 and the wide road 1.

In the present embodiment, the imaging is automatically performed without any instruction from the user as described above, but instead or in addition, the imaging instruction is received from the user via the operation device 260 and responds to the operation instruction. May be done. In this case, the point as the vehicle position when the operation instruction is received from the user and the image is taken, or the point determined based on the vehicle position (for example, the closest point from the vehicle position along the vehicle traveling direction). The intersection) may be a point related to imaging. As a result, the user can expect to receive driving support suitable for the point when traveling at the same point at a later date. As described above, even if the imaging is performed in response to the imaging instruction from the user, the problem that the event information is not associated with the appropriate LinkID may occur in one comparative example.

Therefore, in the present embodiment, the traveling route predicted by the route prediction unit 406 is used. Specifically, the route prediction unit 406 predicts the travel route of the vehicle 110 based on the individual information 280 including the travel history table 223 showing the history of the links corresponding to the roads on which the vehicle 110 has traveled in the past. In FIG. 26, reference numeral 2604 is assumed to be a predicted route (predicted traveling route). In this case, the target link (link corresponding to the point related to imaging) is a link included in the prediction route 2604 to which the point related to imaging belongs, or a link included in the prediction route 2604 and connected to the point, and the vehicle 110 enters the point. This is the link corresponding to the previous road. That is, it is possible to specify the LinkID of the link corresponding to the road belonging to the predicted route 2604. When the point involved in imaging is a candidate intersection corresponding to node 2601-2, the LinkID of the target link is "3".

Further, in the present embodiment, the remaining distance calculated by the remaining distance calculation unit 408 is also used. Specifically, when it is determined that the candidate intersection exists, the remaining distance calculation unit 408 periodically or aperiodically calculates the remaining distance, which is the distance from the recently acquired vehicle position to the reference point according to the candidate intersection. calculate. When the remaining distance is less than the predetermined distance, the information management unit 2302 predicts that the vehicle 110 is on the narrow road 3 connected to the candidate intersection, and links the event information to the LinkID "3".

As described above, according to the present embodiment, it is possible to predict that the vehicle 110 is traveling on the approach road 3 in front of the candidate intersection even if the map matching does not occur on the narrow road 3. Therefore, it is possible to associate the LinkID "3" corresponding to the predicted narrow road 3 with event information including information indicating the recognition result of the image captured for the narrow road 3. As a result, the information providing unit 2301 can provide one or more ADAS units with information suitable for the road environment, and therefore can reduce the possibility that driving support suitable for the road environment is not provided. ..

FIG. 27 is a diagram showing an example of a flowchart related to a series of processes related to updating event information in the management server device 2220. The series of processes may be performed periodically or aperiodically.

In step S2701, the route prediction unit 406 acquires the predicted route. Specifically, the route prediction unit 406 predicts the travel route of the vehicle 110 based on the individual information 280 (for example, the travel history table 223). In the prediction of the traveling route, the map information 222 may be referred to in addition to the individual information 280. The traveling route may be predicted each time the vehicle 110 passes through the intersection, or may be predicted each time the vehicle 110 deviates from the predicted route.

In step S2702, the point determination unit 412 determines from the map information 222 whether or not one or more candidate intersections exist on the predicted route. If there is no candidate intersection on the predicted route, the process ends. When there is one or more candidate intersections on the predicted route, steps S2703 to S2710 are performed for the candidate intersection closest to the current vehicle position along the predicted route.

In step S2703, the information management unit 2302 identifies an approach link leading to the candidate intersection. In step S2704, the information management unit 2302 acquires the event information associated with the LinkID of the entry link. In step S2705, the information management unit 2302 determines from the acquired event information whether or not the candidate intersection is sufficiently recognized by the outside world. In addition, "sufficient external recognition" means that the result of image recognition of the captured image of the candidate intersection is sufficiently reliable, for example, at least one of the following is satisfied.
-The Probability value described later in EventDATA is a certain value or more.
-The time from the current time to the LastDate value described later is less than a certain value.
-The ratio of the DetectCount value described later to the CaptureCount value described later is a certain value or more.

If sufficient external recognition is made for the candidate intersection, the process ends.

On the other hand, when the candidate intersection is not sufficiently recognized as the outside world, the candidate intersection is imaged in order to increase the amount and accuracy of the recognition of the outside world for the candidate intersection. At that time, the imaging start timing and the imaging end timing are controlled.

The control of the imaging start timing is as follows, for example. That is, in step S2706, the remaining distance calculation unit 408 calculates the remaining distance L. In step S2707, the information management unit 2302 determines whether L <Th _L. Th _L is a threshold value of the remaining distance L (threshold value corresponding to the imaging start timing). When L ≧ Th _L , the process returns to step S2706. That is, the calculation of the remaining distance L is performed periodically or aperiodically until L <Th _L. For L <Th _L, in step S2708, the information management unit 2302, the image capturing unit 2303, an imaging start instruction LinkID an instruction associated of entering link identified in and step S2703 the instruction to start imaging Send. The method of calculating the remaining distance L follows the first embodiment. That is, when there is stop information for the candidate intersection, the remaining distance L is the distance from the vehicle position recently acquired by the position acquisition unit 403 to the stop position in front of the candidate intersection. When there is no stop information for the candidate intersection, the remaining distance L is the distance from the vehicle position recently acquired by the position acquisition unit 403 to the candidate intersection.

In step S2711, the imaging unit 2303 receives the imaging start instruction and starts imaging in response to the imaging start instruction. Specifically, in step S2712, the imaging unit 2303 captures an image with at least the camera 113-1 of the cameras 113-1 to 113-4. In step S2713, the imaging unit 2303 transmits to the management server device 2220 a set of image data indicating the captured image and a LinkID associated with the imaging start instruction. In step S2714, the imaging unit 2303 determines whether or not a certain period of time has elapsed from step S2712. When a certain time has elapsed, step S2712 is performed. That is, the imaging unit 2303 repeats steps S2712 and S2713 periodically or aperiodically until it receives the imaging end instruction described later.

Each time the image data and LinkID are transmitted by the image pickup unit 2303, the following processing is performed. That is, in step S2721, in the management server device 2220, the communication control unit 2401 receives the image data and the LinkID, and the information management unit 2403 stores the received image data and the LinkID. Specifically, for example, the information management unit 2403 specifies the personal event table 600 corresponding to the user from the user information 323, and among the specified personal event table 600, the event DATA 650 corresponding to the received LinkID receives the data. Link image data. In this way, image data for the LinkID is stored in the management server device 2220. In step S2722, the distribution unit 2402 transmits the received image data and the LinkID to the object detection server device 2230. In step S2731, in the object detection server device 2230, the communication control unit 2501 receives the image data and the LinkID, and the image recognition unit 2502 performs image recognition of the image indicated by the received image data. In step S2732, the image recognition unit 2502 returns a return value including the recognition result information indicating the result of the image recognition and the LinkID received from the management server device 2220 to the management server device 2220. The recognition result information includes a value indicating the type of the object recognized as being reflected in the image and a probability value which is a value indicating the possibility that the recognition is correct. In step S2723, in the management server device 2220, the communication control unit 2401 receives the return value, and the information management unit 2403 determines whether or not P ≧ Th _P. P is the probability value in the received return value. Th _P is a threshold value for the probability value. When P ≧ Th _P , in step S2724, the information management unit 2403 associates the recognition result information in the return value with the LinkID included in the return value. Specifically, for example, the information management unit 2403 specifies the personal event table 600 corresponding to the user from the user information 323, and among the specified personal event table 600, the EventDATA650 corresponding to the LinkID included in the return value. The recognition result information included in the return value is reflected in. If P <Th _P , step S2724 is skipped. As a result, it can be expected that the information indicating the image recognition result having a low probability value (that is, low reliability) is reflected in the EventDATA650, and as a result, the reliability of the EventDATA650 is lowered.

By the way, in the in-vehicle device 2211, the imaging end timing is controlled after the imaging start instruction is transmitted. The control of the imaging end timing is as follows, for example. That is, in step S2709, the information management unit 2302 determines whether or not the exit information acquisition unit 410 has specified that the vehicle 110 has exited from the candidate intersection. When it is specified that the vehicle 110 has left the candidate intersection, in step S2710, the information management unit 2302 instructs the imaging unit 2303 to end the imaging and the LinkID of the approach link is associated with the imaging end. Send instructions.

In step S2715, the imaging unit 2303 receives the imaging end instruction and responds to the imaging end instruction to end the imaging.

In FIG. 27, the period from step S2708 to step S2710 is a period during which imaging is performed periodically or aperiodically. The information management unit 2302 stops the image pickup by the image pickup unit 2303 while it is determined that the vehicle 110 is stopped during the period in which the image pickup is performed periodically or aperiodically. For example, when the information management unit 2302 determines that the vehicle 110 is stopped (for example, when it is determined that the acquired vehicle positions are the same for a certain period of time), the information management unit 2302 issues an imaging stop instruction to the imaging unit 2303. When it is determined that the vehicle 110 has started to move (for example, when it is determined that the acquired vehicle position is different from the vehicle position acquired immediately before), the imaging restart instruction is transmitted to the imaging unit 2303. As a result, it is possible to avoid repeated imaging of the same image.

According to FIG. 27, the imaging unit 2303 performs imaging periodically or aperiodically from the reception of the imaging start instruction to the reception of the imaging end instruction, but instead, the information management unit 2302 uses the information management unit 2302. By transmitting the imaging instruction to the imaging unit 2303 periodically or aperiodically, the imaging unit 2303 may perform imaging periodically or aperiodically.

Further, according to FIG. 27, the imaging unit 2303 transmits image data to the management server device 2220 each time an image is taken, but instead, each time an image is taken x times (x is an integer of 2 or more). Every time T (T is, for example, twice or more the imaging cycle), or when an imaging end instruction is received, image data indicating two or more untransmitted captured images is transmitted to the management server device 2220. May be good. In this case, the management server device 2220 may store the image data and transmit the image data to the object detection server device 2230. Even if the object detection server device 2230 performs image recognition for each of the two or more images indicated by the image data, and returns the recognition result information indicating the result of each image recognition of the two or more images to the management server device 2220. Good. The management server device 2220 may reflect the recognition result information of the two or more images in the EventDATA650 corresponding to the LinkID of the entry link.

FIG. 28 is a diagram showing an example of a flowchart related to a series of processes related to updating event information in the in-vehicle device 2211. The series of processes may be performed periodically or aperiodically.

In step S2801, the information providing unit 2302 determines whether or not the processing start time is the event acquisition timing (timing to acquire the event file from the management server device 2220). For example, the event acquisition timing may be any of the following.
-When the power of the in-vehicle device 2211 is turned on.
-When it is specified that the eventDATA corresponding to the LinkID of the entry link does not include the recognition result information (for example, the RoadObject value, the Probability value, and the LastDate value described later).

When the processing start time is the event acquisition timing, in step S2802, the information providing unit 2302 transmits the event file request to the management server device 2220.

In step S2811, the distribution unit 2402 of the management server device 2611 responds to the event file request and generates the event file 2800 based on the personal event table 600 corresponding to the user of the in-vehicle device 2211 of the transmission source. In step S2812, the distribution unit 2402 transmits the generated event file 2800 to the in-vehicle device 2211.

In step S2803, in the in-vehicle device 2211, the information management unit 2302 determines whether or not there is valid data in the event file 2800 from the management server device 2220 (an example of "valid data" will be described later). If there is valid data, in step S2804, the information management unit 2302 reflects the valid data in the record having the LinkID corresponding to the valid data in the personal event table 224. As a result, valid data in the event information in the event file 2800 is associated with the LinkID.

FIG. 29 is a diagram showing an example of the event file 2800.

Event file 2800 has an information set 2901. One information set 2901 corresponds to one imaging period (period from the start to the end of imaging) related to one LinkID. Therefore, for example, when traveling on the same approach road a plurality of times, a plurality of information sets 2901 exist for the LinkID corresponding to the approach road. Hereinafter, one information set 2901 will be taken as an example. At that time, the LinkID corresponding to the information set 2901 is referred to as "target LinkID" in the description of FIG. 29, and the imaging period corresponding to the information set 2901 is referred to as "target imaging period" in the description of FIG. 29.

The information set 2901 includes a DirectedObject and a CaptureInfo. And include.

The DirectedObject is information about an object (object reflected in the image) detected from the image recognized by the image recognition of the image captured in the target imaging period with respect to the road (and the intersection) corresponding to the target LinkID. Information items of values (information) included in the DirectedObject include, for example, MaxProbability, ObjectName, and DetectCount.

MaxProbability is an information item in which the largest probability value among the return values (return values from the object detection server device 2230) related to the image captured in the target imaging period corresponding to the target LinkID is set.

ObjectName is an information item in which a value indicating the type of the detected object is set. There are "StopSign" and "Signal" as the value of ObjectName. “StopSign” means a paused object. The pause object may be a sign installed near the stop position defined near the intersection (for example, a sign indicating a pause defined by national laws and regulations) or drawn on the road. It may be a mark or a character string (for example, a mark indicating a stop position or a character string "stop"). "Signal" means a predetermined type of traffic light (for example, a traffic light other than a traffic light as an exception such as a one-signal constantly blinking signal and a night blinking signal). In the present embodiment, the object types that can be detected are "StopSign" and "Signal", but in addition to these, other types of objects may be detected. For example, from the images of the left side camera 113-3 and the right side camera 113-4, a shielding object which is an object higher than a predetermined height (for example, a height defined as the position of the user's eyes) is detected. May be good. In this case, for example, the candidate intersection may be determined to be an intersection with poor visibility in place of or in addition to the presence of "StopSign".

The DetectorCount is an information item in which a value indicating the number of images in which an object of the type indicated by the ObjectName value associated with the target LinkID among the images captured during the target imaging period is detected is set. Note that "object detected" means that the probability value of the detected object in the return value from the object detection server device 2230 is Th _P or more, as will be described later.

CaptureInfo. Is information on imaging during the target imaging period for roads (and intersections) corresponding to the target LinkID. CaptureInfo. Information items of the value (information) included in the above include, for example, RoadType, LinkID, CaptureCount, DirectedStartTiming, DetectedEndTiming, CaptureDate and Direction. Since RoadType, LinkID, and Direction have already been explained, the description thereof will be omitted.

The CaptureCount is an information item in which a value indicating the number of images taken in the target imaging period with respect to the target LinkID is set.

The Directed Start Timing is the number of captured images when the probability value of the image captured during the target imaging period reaches n times or more (n is a natural number) from a value less than the first threshold value (for example, Th _P ) to the first threshold value or more. This is an information item for which the indicated value is set. The Directed End Timing is the number of captured images when the probability value of the image captured during the target imaging period reaches m times or more (m is a natural number) from a value equal to or higher than the second threshold value (for example, Th _P ) to less than the second threshold value. This is an information item for which the indicated value is set. The second threshold value is the same as or different from the first threshold value. Further, the value of m is the same as or different from the value of n. For the sake of simplicity, let n = m = 1. The probability value typically increases as the vehicle approaches the candidate intersection and decreases as it moves away from the candidate intersection.

CaptureDate is an information item in which a value indicating the date of imaging is set. The value of CaptureDate is expressed by the date, but may be expressed in more detail such as the year, month, day, hour, minute, and second instead.

An example of the "valid data" described in FIG. 28 of the event file 2800 is an information set 2901 that satisfies the following for a LinkID.
-The CaptureDate value is the same as or newer than the LastDate value described later included in the EventDATA in the personal event table 224 of the in-vehicle device 2211.

FIG. 30 is a diagram showing an example of the personal event table 600 in the management server device 2220.

For the same user, the personal event table 600 in the management server device 2220 is the same as or newer than the personal event table 224 in the in-vehicle device 2211. In other words, the event file 2800 based on the personal event table 600 in the management server device 2220 is appropriately reflected in the personal event table 224 in the in-vehicle device 2211, so that the personal event table 224 in the in-vehicle device 2211 is in the latest state. It becomes.

In the personal event table 600, the EventID 640 depends on the type of object detected as a result of image recognition. For example, "12001" is assigned when the RoadObject value is "Signal". Further, for example, "12002" is assigned when the RoadObject value is "StopSign".

In the personal event table 600, as the information item of the value (information) included in the EventDATA650, for example, there are RoadObject, Probability, LastDate, DetectCount and CaptureCount. Hereinafter, one LinkID will be taken as an example (“target LinkID” in the description of FIG. 30).

The RoadObject is an information item in which a value indicating the type of the detected object is set for the target LinkID. There are "StopSign" and "Signal" as the value of RoadObject. “StopSign” and “Signal” are as described with reference to FIG. The RoadOject value is set in the event file 2800 as the ObjectName value.

Probability is an information item in which the probability value is set for the target LinkID. The probability value here is an average value of the probability values obtained from the return value from the object detection server device 2230 for the target LinkID (for example, in particular, the above-mentioned probability value of Th _P or higher).

LastDate is an information item in which a value indicating the latest date of imaging is set for the target LinkID. The value of LastDate is expressed by the year, month, day, but instead, it may be expressed in more detail such as year, month, day, hour, minute, and second. The LastDate value is set in the event file 2800 as the CaptureDate value.

The DetectorCount is an information item in which a value indicating the cumulative total of images in which an object of the type indicated by the RoadObject value is detected for the target LinkID is set. The value of DetectorCount is incremented by the information management unit 2403 when the probability value in the return value from the object detection server device 2230 for the object is Th _P or more.

The CaptureCount is an information item in which a value indicating the cumulative total of images captured with respect to the target LinkID is set. The CaptureCount value is incremented by the information management unit 2403 according to the number of images indicated by the image data when the image data associated with the target LinkID is received from the in-vehicle device 2211 and the image data is saved.

At least a portion of the personal event table 600 may be updated based on at least a portion of the personal event table 600 corresponding to one or more other users. For example, for the target LinkID, statistics of event information (EventID 640 and EventDATA650) of all users may be acquired, and the statistics may be reflected in the event information of each user. In this case, even at an intersection with poor visibility for the first time for a certain user, the event information based on the event information corresponding to another user is linked to the LinkID corresponding to the approach road, so that the first outlook It can be expected that appropriate driving support can be obtained even at bad intersections.

The event file 2800 illustrated in FIG. 29 is generated based on the personal event table 600 as described above in the management server device 2220, and the personal event table 224 in the in-vehicle device 2211 is updated to the latest state based on the event file 2800. (For example, the DetectCount value and the CaptureCount value in the information set 2901 in the event file 2800 are added to the DetectCount value and the CaptureCount value in the EventDATA corresponding to the LinkID in the information set 2901). As a result, in the in-vehicle device 2211, the LinkID of the approach link is associated with event information including the recognition result information of the image captured for the approach link. Based on the personal event table 224, the intersection determination process is performed in the in-vehicle device 2211.

FIG. 31 is a diagram showing an example of a flowchart related to the intersection determination process.

In steps S3101 to S3104, the same processing as in steps S2701 to S2704 shown in FIG. 27 is performed. The intersection determination process may be performed periodically or aperiodically (for example, in parallel) independently of the process shown in FIG. 27, or may be performed as a part of the process shown in FIG. 27. Good. In the latter case, for example, when steps S2701 to S2704 shown in FIG. 27 are performed and it is determined in step S2705 that sufficient outside world recognition is performed for the candidate intersection, the processes after step S3105 are performed. You may.

In step S3105, the information management unit 2302 determines whether or not the object type "StopSign" is associated with the entry link from the Event ID or RoadObject value corresponding to the entry link.

When the object type "StopSign" is associated with the entry link, in step S3106, the information management unit 2302 determines the candidate intersection as an intersection with poor visibility and determines the reliability. The reliability determination policy will be described later with reference to FIG.

When the object type "StopSign" is not associated with the entry link, in step S3107, the information management unit 2302 determines whether or not the object type "Signal" is associated with the entry link.

When the object type "Signal" is associated with the entry link, in step S3108, the information management unit 2302 determines that the candidate intersection is a normal intersection.

When the object type "Signal" is not associated with the entry link, in step S3109, the information management unit 2302 determines the candidate intersection as an intersection with poor visibility and determines the reliability.

Information indicating whether the candidate intersection is an intersection with poor visibility or a normal intersection, and information indicating the reliability determined when the candidate intersection is determined to be an intersection with poor visibility are provided in the personal event table 224. It may be stored in the EventDATA (EventDATA corresponding to the entry link) in. When the EventDATA contains information indicating that the candidate intersection is determined to be a normal intersection, or when the candidate intersection is determined to be an intersection with poor visibility and the determined reliability is equal to or higher than a predetermined value, FIG. 27. In step S2705 of the above, it may be determined that sufficient recognition of the outside world is performed.

FIG. 32 is a diagram showing an example of the reliability determination policy.

"Reliability" is a value provided for an intersection with poor visibility and means the certainty that the intersection has poor visibility. Information indicating the reliability is transmitted to one or more ADAS units by the information providing unit 2301. Upon receiving the information, the ADAS unit provides driving support for an intersection with poor visibility according to the reliability indicated by the information. What kind of driving assistance is provided at what reliability may depend on the ADAS unit (for example, when the reliability is a certain value or more, a predetermined driving assistance may be provided). Further, for example, the information indicating the reliability may be transmitted immediately after the reliability is determined, or may be transmitted when the reliability is determined and the remaining distance becomes a predetermined distance or less. In addition, the reliability may be expressed by other kinds of codes such as alphabets in place of or in addition to numbers.

In the example of FIG. 32, the larger the numerical value as the reliability, the higher the reliability. The reliability determination policy illustrated in FIG. 32 may be stored in the in-vehicle device 2211 as information (for example, a file), or may be used as a program based on the information management unit 2302, which is an example of a function for determining reliability. It may be described.

As a determination factor of the reliability, for example, there is at least one of the presence / absence of stop information, the presence / absence of recognition result information, the number of days elapsed from the LastDate value, and the DetectCount value. That is, the reliability depends on the amount of learning about the intersection with poor visibility (for example, the magnitude of the DetectCount value) and the freshness of the information (for example, the number of days elapsed from the LastDate value). For example, driving assistance may not be provided because the reliability has dropped below a certain value, or driving assistance may be provided because the reliability has increased above a certain value. The importance of the deciding factor depends on the deciding factor. An example of the importance of the determinant is as follows.

That is, in the present embodiment, the importance of the determinant of the presence / absence of recognition result information is the highest. If there is recognition result information (specifically, if there is an object type "StopSign"), the reliability is high. If there is no recognition result information, the reliability is low.

The determinant, the number of days elapsed from the LastDate value, is the second most important. When there is recognition result information, the reliability is higher if the number of days elapsed from the LastDate value is short (for example, if it is less than a certain value).

The determinant factor called the DetectCount value is the third most important. If there is recognition result information and the number of days elapsed from the LastDate value is short, and if the DetectorCount value is large (for example, if it is a certain value or more), the reliability is even higher.

The deciding factor of the presence or absence of stop information is the least important. If there is no recognition result information and there is no stop information, the reliability is lower. On the other hand, when there is recognition result information, the number of days elapsed from the LastDate value is short, and the DetectorCount value is large, the reliability is higher if there is stop information.

Since the reliability that the candidate intersection is an intersection with poor visibility is determined according to the reliability determination policy as described above and the driving support is provided according to the reliability, appropriate driving support can be expected for the candidate intersection.

By the way, in the present embodiment, as shown in FIG. 27, imaging is performed periodically or aperiodically from the start of imaging to the end of imaging. Since the installation position of a predetermined type of object such as a pause object or a traffic light differs depending on the candidate intersection, in order to increase the certainty of capturing the predetermined type of object at any candidate intersection, the imaging period (start of imaging) is required. It is conceivable to set the period from to the end) to start relatively early and end relatively late. However, if such a setting is made, the imaging start timing may be too early or the imaging end timing may be too late depending on the candidate intersection. Then, the number of images is unnecessarily large, and as a result, the amount of data may be unnecessarily large.

Therefore, in the present embodiment, the imaging timing adjustment process is performed. Specifically, the threshold value Th _L for the remaining distance L, which is an example of the parameter value that affects the imaging start timing, and α, which is an example of the parameter value that affects the imaging end timing (used in the exit determination and the reference orientation difference). At least one of the coefficients) is adjusted. The adjustment is based on at least one of the Detected Start Timing and the Detected End Timing included in each information set 2901 in the event file 2800. The Directed Start Timing and the Directed End Timing are specified by the information management unit 2403 of the management server device 2220 from the return value (return value from the object detection server device 2230) for each image captured during the imaging period.

FIG. 33 is a diagram showing an example of a flowchart related to the process including the image pickup timing adjustment process. The processing is performed, for example, periodically or aperiodically (for example, when the event file 2800 is acquired). Further, the processing is performed, for example, for each candidate intersection (for example, for each candidate intersection specified for the predicted route). In the description of FIG. 33, one candidate intersection is taken as an example (“target intersection” in the description of FIG. 33). Further, in the following description, the information set 2901-1 of FIG. 29 will be referred to as appropriate. In the description of FIG. 33, the parameter values such as the DetectCount value and the CaptureCount value are values in the information set 2901-1. Further, "imaging timing adjustment processing" is a general term for imaging start timing processing and imaging end timing adjustment processing.

In step S3301, the information management unit 2302 calculates the effective ratio K for the target intersection. The “effective ratio” is the ratio of the number of images in which a predetermined type of object is detected to the total number of captured images, specifically, the DetectCount value / CaptureCount value. For example, according to the information set 2901-1, for LinkID "198", K = 56/112 = 0.5.

In step S3302, the information management unit 2302 determines whether or not the effective ratio K is equal to or less than a predetermined threshold value Th _K. When the effective ratio is small, there is a lot of useless imaging, and therefore at least one adjustment of the imaging start timing and the imaging end timing is preferable. For example, when Th _K = 0.6, K ≦ Th _K for LinkID “198”.

When K ≦ Th _K , at least one of the image pickup start timing adjustment process including step S3303 and step S3304 and the image pickup end timing adjustment process including step S3305 and step S3306 is performed.

The imaging start timing adjustment process is as follows.

That is, in step S3303, the information management unit 2302 calculates the start timing detection rate X. The "start timing detection rate" means that the probability value of the number of images captured during the imaging period is changed from a value less than 0.7 (specific example of Th _P described above) to a value of 0.7 or more during the imaging period. The ratio of the number of captured images when the image is reached, specifically, the Detected Start Timing value / Capture Count value. For LinkID "198", X = 40/112≈0.36. This means that about 36% of the images captured during the imaging period are useless.

Therefore, in step S3304, the information management unit 2302 adjusts the threshold value Th _L for the remaining distance L, which is an example of the parameter value affecting the imaging start timing, based on the start timing detection rate X. Specifically, the information management unit 2302 calculates Th _L = Th _L * (1-X). When Th _L before adjustment is "30", for LinkID "198", Th _L after adjustment is 30 * (1-0.36) = 19.2. As a result, the remaining distance L reaches Th _L later than before the adjustment, and therefore the start of imaging is also delayed, and as a result, wasteful imaging can be reduced. The adjusted Th _L "19.2" is stored in the EventDATA (EventDATA in the in-vehicle device 2211) corresponding to the LinkID "198" by the information management unit 2302.

On the other hand, the imaging end timing adjustment process is as follows.

That is, in step S3305, the information management unit 2302 calculates the end timing detection rate Y. The "end timing detection rate" is a value obtained from a value of 0.7 (specific example of Th _P described above) or more to a value of less than 0.7 with respect to the number of images captured during the imaging period. The ratio of the number of captured images when the image is reached, specifically, the DetectedEndTiming value / CaptureCount value. For LinkID "198", X = 100/112≈0.89. This means that 1-0.89 = 11% of the images captured during the imaging period is useless imaging.

Therefore, in step S3306, the information management unit 2302 adjusts α, which is an example of the parameter value affecting the imaging end timing, based on the end timing detection rate Y. Specifically, the information management unit 2302 calculates α = α + (1-Y). When α before adjustment is “0.3”, for LinkID “198”, α after adjustment is 0.3 + (1-0.89) = 0.41. As a result, the | directional B-direction C | ≤ α × reference directional difference is reached earlier than before the adjustment, and therefore the imaging is completed earlier, and as a result, unnecessary imaging can be reduced. it can. The adjusted α "0.41" is stored in the EventDATA (EventDATA in the in-vehicle device 2211) corresponding to the LinkID "198" by the information management unit 2302.

As described above, at least one of the imaging start timing and the imaging end timing is optimized for each candidate intersection. This reduces unnecessary imaging, and as a result, it can be expected to reduce the amount of data.

The above is the description of the second embodiment. In the present embodiment, the start timing and end timing of driving support for an intersection with poor visibility (a candidate intersection in which a stop object is detected, or a candidate intersection in which neither a stop object nor a predetermined type of traffic light is detected). May be the same as or different from the start timing and end timing of imaging for the candidate intersection.
(3) Summary

In the above-described embodiment, the case where the present invention is applied to the driving information providing system has been described, but the present invention is not limited to this, and is widely applied to various other systems, devices, methods, and programs. Can be applied.

In the embodiments described above, the "vehicle" is typically an automobile.

In the embodiments described above, the "storage device" is at least one (typically at least memory) of a memory and a persistent storage device.

Further, in the above-described embodiment, the "memory" is one or more memory devices, and typically may be a main storage device. At least one memory device in the memory may be a volatile memory device or a non-volatile memory device.

Further, in the above-described embodiment, the "permanent storage device" is one or more permanent storage devices. Persistent storage devices are typically non-volatile storage devices (eg, auxiliary storage devices), specifically HDDs or SSDs.

Further, in the above-described embodiment, the "control device" is a processor, specifically, one or more processor devices. The at least one processor device is typically a microprocessor such as a CPU, but may be another type of processor device such as a GPU (Graphics Processing Unit). At least one processor device may be single-core or multi-core. At least one processor device may be a processor device in a broad sense such as a hardware circuit (for example, FPGA (Field-Programmable Gate Array) or ASIC (Application Specific Integrated Circuit)) that performs a part or all of processing.

Further, in the above-described embodiment, each table is an example of information, and one table may be divided into two or more tables, or all or a part of two or more tables may be one table. There may be. Further, in the above-described embodiment, at least a part of the information may be information of any structure (for example, structured data or unstructured data), or a neural network that generates an output for an input. It may be a learning model such as a network.

Further, in the above-described embodiment, the function is described by the expression "kkk unit", but the function may be realized by executing one or more computer programs by a control device (processor). It may be implemented by one or more hardware circuits (eg FPGA or ASIC) or a combination thereof. When the function is realized by executing one or more programs by the control device, the function is at least one of the control devices because the predetermined processing is appropriately performed by using the storage device and / or the communication device or the like. It may be a part. The process described with the function as the subject may be a process performed by a control device or a device having the control device. The program may be installed from the program source. The program source may be, for example, a program distribution computer or a computer-readable recording medium (eg, a non-temporary recording medium). The description of each function is an example, and a plurality of functions may be combined into one function, or one function may be divided into a plurality of functions.

Further, in the above description, information such as programs, tables, and files related to each function can be placed in a memory, a storage device such as a hard disk or SSD, or a recording medium such as an IC card, SD card, or DVD. ..
(3-1) Summary of the first embodiment

The first embodiment can be summarized as follows, for example.

An intersection in which a driving information providing system (for example, driving information providing system 100) is used and a vehicle (for example, vehicle 110) enters a second road (for example, a wide road) from a first road (for example, a narrow road). (For example, at an intersection with poor visibility), a stop information acquisition unit (for example, stop information acquisition unit 407) that acquires stop information (for example, stop position, stop direction) when the vehicle stops, and the stop information acquisition unit. The stop information acquired by the department may be the link information of the road related to the intersection (for example, the link information of the first road, the link information of the second road, or the intersection. It is characterized by including an information management unit (for example, information management unit 503) that is associated with and stores link information of other roads related to the above.

According to the above configuration, the stop information at the time of stopping at the intersection is stored in association with the link information. Therefore, for example, the stop information, the information of the distance to the intersection calculated from the stop information, etc. are stored in the advanced driver assistance system (advanced driver assistance system). For example, by providing it to the ADAS unit), it becomes possible to support the driving operation related to the intersection and avoid the accident related to the intersection. In addition, for example, by providing stop information or the like to an output device (for example, display device 230, speaker, or other output device), a stop line displayed on the navigation screen is used to announce that the vehicle must be stopped. By emphasizing, it will be possible to call attention to the driver at the intersection and support comfortable driving.

The timing of providing stop information and the like to the advanced driver assistance system and the like is not limited, but it may be when the in-vehicle device predicts the traveling route and detects the intersection, or the vehicle may detect the intersection. It may be when a predetermined distance is reached from, or it may be at another timing.

Based on map information (for example, map information 222) including information that can identify the type of road, the stop information acquisition unit determines whether or not the shape of the road from the position of the vehicle to the intersection is straight. When the determination is made and it is determined that the vehicle is straight, the stop information is acquired (see, for example, FIG. 10).

According to the above configuration, it is possible to reduce the possibility of acquiring inappropriate stop information in a road environment where roads are dense, for example, in a residential area. In addition, for example, even if the road on which the vehicle is traveling cannot be identified because the roads are densely packed in a residential area and map matching cannot be performed, is the road for obtaining stop information? Since it is possible to determine whether or not the vehicle has stopped, it is possible to avoid a situation in which stop information cannot be obtained.

The stop information acquisition unit is based on map information (for example, map information 222) including information that can identify the type of road, the first road is a narrow road, and the second road is a wide road. When it is detected, it is presumed that the intersection has poor visibility, and the stop information when the vehicle stops is acquired for the intersection with poor visibility (see FIGS. 7, 8 and 10). It is characterized by that.

According to the above configuration, for example, stop information related to an intersection with poor visibility can be transmitted to an advanced driver assistance system or the like, so that driving support related to an intersection with poor visibility can be provided.

When the information management unit stores the stop information acquired by the stop information acquisition unit in association with the link information, if one or more other stop information is stored for the link information, the stop information is stopped. Filtering processing is performed on the information and the other stop information to remove noise, a representative value is calculated, and the calculated representative value is stored in association with the link information as stop information related to the intersection (for example). , See FIG. 11).

In the above configuration, for example, the stop information is further enhanced by eliminating the stop information that becomes noise when the vehicle is paused due to passing by another vehicle or when the vehicle is paused to ensure the safety of pedestrians. Since it can be made accurate, it becomes possible to provide driving assistance related to intersections at a more appropriate timing.

The stop information includes position information indicating a position when the vehicle is stopped, and a remaining distance calculation unit (for example, a remaining distance calculation unit 408) that calculates the distance from the position of the vehicle to the position of the stop information. ), And an information providing unit (for example, information providing unit 411) that transmits information indicating the above distance calculated by the remaining distance calculating unit to an advanced driver assistance system (for example, ADAS unit). And.

According to the above configuration, for example, by providing the advanced driver assistance system with the distance from the position of the vehicle to the position of the stop information, the warning sound for decelerating the speed of the vehicle in consideration of the stop position at the intersection is emitted. It will be possible to appropriately provide driving support related to intersections, such as outputting.

The remaining distance calculation unit is characterized in that the distance is calculated each time the position of the vehicle is updated by dead reckoning (for example, FIG. 13).

According to the above configuration, for example, a more accurate distance from the position of the vehicle to the position of the stop information can be transmitted to the advanced driver assistance system, so that the driving assistance related to the intersection can be performed at a more appropriate timing. Will be.

A locus information acquisition unit (for example, a locus information acquisition unit 409) that acquires the position of the vehicle after the vehicle has stopped at the intersection is provided, and the information management unit is acquired by the locus information acquisition unit. The locus information is associated with the link information of the road related to the intersection and stored (for example, see FIG. 16).

In the above configuration, trajectory information related to the intersection is acquired. Therefore, for example, by providing the trajectory information to the advanced driver assistance system, the speed of the vehicle when the vehicle is passing through the intersection can be controlled at the intersection. You will be able to provide driving support involved. In addition, by displaying the traveling route, radius of curvature, etc. on the navigation screen, it becomes possible to provide driving support related to the intersection.

When it is determined whether or not the vehicle has left the intersection and it is determined that the vehicle has left the intersection, an exit information acquisition unit (for example, an exit information acquisition unit) that acquires exit information indicating that the vehicle has left the intersection. , Exit information acquisition unit 410), and an information providing unit (for example, information providing unit 411) that transmits the exit information acquired by the exit information acquisition unit to an advanced driver assistance system (for example, ADAS unit). , Characterized by.

According to the above configuration, by providing the advanced driver assistance system with exit information indicating that the vehicle has left the intersection, the driving support related to the intersection by the advanced driver assistance system can be terminated at an appropriate timing. Become.

The exit information acquisition unit determines whether or not the vehicle has exited the intersection based on the direction when the vehicle stopped, the direction of the link of the second road, and the current direction of the vehicle. To judge.

According to the above configuration, for example, even when the approach road and the exit road have an acute angle, it is erroneously determined that the vehicle has left the intersection when the vehicle stops at the position of the stop line. It can be avoided.
(3-2) Summary of the second embodiment

The second embodiment can be summarized as follows, for example.

Based on map information 222 including information indicating a road network including a plurality of links corresponding to a plurality of roads and a plurality of nodes corresponding to a plurality of intersections and information indicating the attributes of roads in the road network. The vehicle-mounted device 2211 that navigates the vehicle 110 includes an imaging unit 2303 and a support control unit 2300. The image pickup unit 2303 captures an image of at least a part of the surroundings of the vehicle 110. The support control unit 2300 links supplementary information, which is information including recognition result information indicating the result of image recognition of the captured image, to the link information of the target link, which is a link corresponding to the point related to the imaging of the image. wear. The supplementary information may be event information including the event ID and event DATA, or may be information associated with the link information in the map information 222 in place of or in addition to the event information.

According to this configuration, at least a part around the vehicle 110 is imaged. As a result, regarding the points involved in the imaging, the road environment that cannot be specified from the map information 222 can be understood from the image recognition result of the captured image. By associating the link information of the target link corresponding to the point related to imaging with supplementary information including recognition result information indicating the result of the image recognition, appropriate driving support for the point is appropriate based on the supplementary information. Improves sex. That is, it is possible to reduce the possibility that driving support suitable for the road environment is not provided. Reduces the possibility that driving support will not be provided even though it is preferable to provide driving support suitable for the road environment at the site, and the possibility that driving support will be provided even though driving support is unnecessary. can do.

The support control unit 2300 predicts the travel route of the vehicle 110 based on the individual information 280 including the travel history table 223 showing the history of the links corresponding to the roads on which the vehicle 110 has traveled in the past. The navigation is performed using the vehicle position acquired according to at least one of map matching and dead reckoning based on the map information 222. The target link corresponds to a link included in the predicted route (predicted traveling route) to which a point related to image imaging belongs, or a road included in the predicted route connected to the point and before the vehicle 110 enters the point. This is the link you made. The link information of the target link is the link information of at least one of the map information 222 and the individual information 280.

According to this configuration, since there is a prediction route, it is possible to predict that the vehicle 110 is traveling on the target road even if map matching does not occur on the target road (road corresponding to the target link). .. Therefore, it is possible to link the link information of the target link with supplementary information including information indicating the recognition result of the image captured for the target road.

The support control unit 2300 determines from the map information 222 whether or not a candidate point that is a candidate for the corresponding point exists on the predicted route. When it is determined that the candidate point exists and the vehicle 110 is determined to approach the candidate point, the imaging unit 2303 captures an image of at least a part of the surroundings of the vehicle 110.

According to this configuration, a candidate point can be specified based on the predicted route and the map information 222, and imaging can be performed on the specified candidate point without any instruction from the user.

When it is determined that the candidate point exists, the support control unit 2300 periodically or aperiodically determines the remaining distance L (for example, the approximate remaining distance) which is the distance from the recently acquired vehicle position to the reference point according to the candidate point. Or the detailed remaining distance) is calculated. Imaging is performed when the remaining distance L is less than the predetermined distance Th _L.

According to this configuration, imaging can be started at an appropriate timing.

The candidate point is a candidate intersection that connects a narrow road to a wide road and is a candidate for an intersection with poor visibility, and the reference points that follow the candidate point are the candidate intersection and the narrow road before entering the candidate intersection. It is one of the stop positions which are the stops positions in. When there is stop information indicating the stop position, the remaining distance L is the distance from the recently acquired vehicle position to the stop position (for example, the detailed remaining distance).

According to this configuration, the accuracy of the calculated remaining distance L is improved.

In addition, the support control unit 2300 indicates a stop position that is a position stopped on the narrow road before entering the candidate intersection when the road shape from the recently acquired vehicle position to the candidate intersection on the narrow road is straight. Get stop information.

This configuration reduces the possibility of obtaining inappropriate stop information in a road environment where it is not always possible to obtain appropriate stop information for all target intersections due to the high density of target intersections. it can.

The supplementary information includes the stop information when the stop information is acquired, in addition to the recognition result information. The vehicle 110 includes one or more ADAS units that operate according to the reliability when the information indicating the reliability is received. The support control unit 2300 determines the reliability that the candidate intersection is an intersection with poor visibility based on the supplementary information linked to the link information of the link corresponding to the narrow road, and determines the reliability indicating the reliability. Send to at least one of one or more ADAS units.

According to this configuration, it is expected that the reliability of the information transmitted to the ADAS unit is high, and therefore appropriate driving support is expected. This also applies to cases where stop information is not acquired. This is because the reliability is determined based on other information elements of the supplementary information.

The support control unit 2300 determines whether or not the point related to imaging is the corresponding point, depending on whether or not the recognition result information includes information indicating that a predetermined type of object is captured.

According to this configuration, the road environment at the point related to imaging is determined from the type of object shown in the image, so it can be expected that the determination is highly accurate, and therefore appropriate driving support can be provided. Be expected.

When the point is a candidate intersection and the recognition result information includes information indicating that the paused object is captured, the support control unit 2300 determines that the candidate intersection is an intersection with poor visibility.

According to this configuration, it is highly possible that the candidate intersection is an intersection with poor visibility.

When the recognition result information includes information indicating that the pause object is not shown but the predetermined type of traffic light is not shown, the support control unit 2300 determines that the candidate intersection is an intersection with poor visibility.

According to this configuration, it is not likely that the candidate intersection is an intersection with poor visibility compared to the case where the pause object is shown, but the visibility is poor because the specified type of traffic light is not shown. Driving assistance for an intersection may be a preferred intersection. It is determined that such an intersection is also an intersection with poor visibility.

When the recognition result information includes information indicating that a predetermined type of traffic light is captured, the support control unit 2300 determines that the candidate intersection is a normal intersection. When the candidate intersection is determined to be a normal intersection, the support control unit 2300 does not transmit information related to the intersection with poor visibility about the candidate intersection to one or more ADAS units.

According to this configuration, it is possible to avoid providing driving support for an intersection with poor visibility even for an intersection where driving is performed according to a predetermined type of traffic light.

Support control after a predetermined type of parameter value (for example, remaining distance L) for the vehicle 110 reaches a threshold value (for example, Th _L ) defined that the vehicle 110 has approached an example (for example, a candidate intersection) of a point related to imaging. According to one or more instructions from the unit 2300, the imaging unit 2303 is adapted to perform imaging periodically or aperiodically. For each captured image, the return value (an example of information indicating the result of image recognition of the image) is a determination of whether or not a predetermined type of object (for example, a pause object or a predetermined type of traffic light) is captured. The information indicating the result and the information indicating the possibility that the determination is correct (for example, the probability value) are included. The support control unit 2300 executes the imaging start timing adjustment process. In the imaging start timing adjustment process, the number of images captured from the start of imaging to the end of imaging at the above point (for example, the CaptureCount value) and a predetermined type of object may be captured at the point after the start of imaging this time. The above threshold value (for example, Th _L ) is based on the number of captured images (for example, Detected Start Timing value) when the sex (for example, the probability value) reaches a predetermined rate (for example, Th _P ) or more n times (n is a natural number). ) Is changed to a value that is slower until a predetermined type of parameter value is reached (for example, Th _L is reduced).

According to this configuration, the imaging start timing can be appropriately delayed based on the ratio of the images captured from the start of imaging to the end of imaging that can be regarded as wasted.

The support control unit 2300 has the number of images captured from the start of imaging to the end of imaging at the above points (for example, the CaptureCount value) and the number of images determined to capture a predetermined type of object at the points. When the value (for example, effective ratio K) obtained based on (for example, the DetectCount value) is equal to or less than a predetermined value (for example, Th _K ), the image pickup start timing adjustment process is executed.

According to this configuration, when the ratio of valid images (images in which a predetermined type of object is detected) among the images captured during the imaging period is small, in other words, when there is a lot of waste, the imaging start timing adjustment process is performed. Will be done. Therefore, the execution frequency of the imaging start timing adjustment process can be made appropriate.

1 from the support control unit 2300 until a predetermined type of parameter value (for example, | direction B-direction C |) for the vehicle 110 reaches a threshold value (for example, α × reference direction difference) defined as the vehicle 110 has left. According to the above instructions, the imaging unit 2303 is adapted to perform imaging periodically or aperiodically. The support control unit 2300 executes the imaging end timing adjustment process. In the imaging end timing adjustment process, the number of images captured from the start of imaging to the end of imaging for a point (for example, the CaptureCount value) and the possibility that the imaging is started this time for the point and a predetermined type of object is captured (for example). , Probability value) reaches the predetermined rate (for example, Th _P ) or more and less than the predetermined rate m times or more (m is a natural number), based on the number of captured images (for example, the DetectedEndTiming value). Th _L ) is a process of changing (for example, increasing α) to a value that is faster until a predetermined type of parameter value is reached.

According to this configuration, the imaging end timing can be appropriately advanced based on the ratio of the images captured from the start of imaging to the end of imaging that can be regarded as wasted.

The support control unit 2300 has the number of images captured from the start of imaging to the end of imaging at the above points (for example, the CaptureCount value) and the number of images determined to capture a predetermined type of object at the points. When the value (for example, effective ratio K) obtained based on (for example, the VectorCount value) is equal to or less than a predetermined value (for example, Th _K ), the imaging end timing adjustment process is executed.

According to this configuration, when the ratio of valid images (images in which a predetermined type of object is detected) is small among the images captured during the imaging period, in other words, when there is a lot of waste, the imaging end timing adjustment process is performed. Will be done. Therefore, the execution frequency of the imaging end timing adjustment process can be made appropriate.

The support control unit 2300 stops imaging by the imaging unit 2303 while it is determined that the vehicle 110 is stopped during the imaging period.

Since there is no change in the image even if the imaging is repeated while the image is stopped, unnecessary imaging can be avoided according to this configuration.

When image recognition of an image captured by an image pickup unit of a vehicle other than the vehicle 110 is performed for the target link, the supplementary information associated with the link information of the target link is provided by the image pickup unit of the other vehicle. Recognition result information indicating the result of image recognition of the captured image may be reflected.

According to this configuration, even at the first point for a certain user, the link information of the target link is associated with supplementary information based on the supplementary information corresponding to another user, so that the first point is appropriate. It can be expected that various driving support can be obtained.

Any part of the functions of the in-vehicle device 2211 may be provided in the management server device 2220, at least a part of the functions of the management server device 2220 may be provided in the in-vehicle device 2211, or the object detection server. At least some of the functions of the device 2230 may be provided in the in-vehicle device 2211. For example, instead of the vehicle-mounted device 2211 storing at least one of the travel history table 223 and the personal event table 224, the management server device 2220 may store at least one of the travel history table and the personal event table. Further, various processes (for example, at least one of the process of identifying a candidate intersection from the map information 222, the process shown in FIG. 31, and the process shown in FIG. 33) are performed by the management server device instead of the in-vehicle device 2211. 2230 may go. The driver assistance system 2200 may be composed of the vehicle-mounted device 2211 and / or the management server device 2220 of the vehicle-mounted device 2211, the management server device 2220, and the object detection server device 2230. For example, the driving support system 2200 has an image acquisition unit that acquires image data indicating an image captured at least a part of the surroundings of the vehicle 110, and a target link that is a link corresponding to a point related to the imaging of the image. The support control unit 2300 is provided with supplementary information that is information including recognition result information indicating the result of image recognition of the captured image to the link information of. The image acquisition unit may be at least one of the image pickup unit 2303 and the information management unit 2403 that receives and stores the image data from the in-vehicle device 2211.

Further, the above-described configuration may be appropriately changed, rearranged, combined, or omitted as long as it does not exceed the gist of the present invention.

100 ... Driving information providing system, 110 ... Vehicle, 111 ... In-vehicle device, 120 ... Server device.

Claims (11)

With respect to an intersection where a vehicle enters a second road from a first road, a stop information acquisition unit that acquires stop information when the vehicle stops, and a stop information acquisition unit.
An information management unit that stores the stop information acquired by the stop information acquisition unit in association with link information of a road related to the intersection, and an information management unit.
A driving information providing system characterized by being equipped with. The stop information acquisition unit determines whether or not the shape of the road from the position of the vehicle to the intersection is straight based on the map information including the information that can identify the type of the road, and determines that the road is straight. If it is determined, the stop information is acquired.
The driving information providing system according to claim 1. When the stop information acquisition unit detects that the first road is a narrow road and the second road is a wide road based on map information including information that can identify the type of the road, It is estimated that the intersection is an intersection with poor visibility, and stop information when the vehicle stops is acquired for the intersection with poor visibility.
The driving information providing system according to claim 1 or 2. When the information management unit stores the stop information acquired by the stop information acquisition unit in association with the link information, if one or more other stop information is stored for the link information, the stop information is stopped. Filtering processing is performed on the information and the other stop information to remove noise, a representative value is calculated, and the calculated representative value is stored in association with the link information as stop information related to the intersection.
The driving information providing system according to any one of claims 1 to 3, wherein the driving information providing system is characterized. The stop information includes position information indicating the position when the vehicle is stopped.
The remaining distance calculation unit that calculates the distance from the position of the vehicle to the position of the stop information,
An information providing unit that transmits information indicating the distance calculated by the remaining distance calculation unit to the advanced driver assistance system, and an information providing unit.
The driving information providing system according to any one of claims 1 to 4, wherein the driving information providing system is provided. The remaining distance calculation unit calculates the distance each time the position of the vehicle is updated by dead reckoning.
The driving information providing system according to claim 5. A locus information acquisition unit that acquires the position of the vehicle after the vehicle has stopped at the intersection as locus information is provided.
The information management unit stores the locus information acquired by the locus information acquisition unit in association with the link information of the road related to the intersection.
The driving information providing system according to any one of claims 1 to 6, wherein the driving information providing system is characterized. An exit information acquisition unit that determines whether or not the vehicle has exited the intersection, and when it is determined that the vehicle has exited the intersection, acquires exit information indicating that the vehicle has exited the intersection.
An information providing unit that transmits the exit information acquired by the exit information acquisition unit to the advanced driver assistance system, and an information providing unit.
The driving information providing system according to any one of claims 1 to 7, wherein the driving information providing system is provided. The exit information acquisition unit determines whether or not the vehicle has left the intersection based on the direction when the vehicle is stopped, the direction of the link of the second road, and the current direction of the vehicle. To judge,
The driving information providing system according to claim 8. With respect to an intersection where a vehicle enters a second road from a first road, a stop information acquisition unit that acquires stop information when the vehicle stops, and a stop information acquisition unit.
An information management unit that stores the stop information acquired by the stop information acquisition unit in association with link information of a road related to the intersection, and an information management unit.
An in-vehicle device characterized by being provided with. The first step in which the stop information acquisition unit acquires stop information when the vehicle stops at an intersection where the vehicle enters the second road from the first road, and
The second step in which the information management unit stores the stop information acquired by the stop information acquisition unit in association with the link information of the road related to the intersection, and
A method of providing driving information, which is characterized in that.

Images