Vehicle control method and vehicle control system

Abstract

To provide a vehicle control method capable of determining the behavior of a target object in a dead angle area undetectable from any of an on-vehicle sensor and a road side sensor.SOLUTION: A blind spot area which is an area where an object cannot be detected by an object detection part and cannot be imaged by an imaging part on a lane on which vehicles travel and an opposite lane is specified (S202 in Fig. 4). Subsequently, based on the image acquired by the imaging unit, it is determined whether an oncoming car that moves in a direction opposite to the traveling direction of the car and enters the blind spot region is present on the opposite lane (S205 in FIG. 4). When it is determined that an oncoming car is present, the behavior of the oncoming car is determined (S205 in FIG. 4), and the running of the car is controlled on the basis of the determination result of the behavior of the oncoming car (S108 in FIG. 4).SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to a vehicle control method and a vehicle control system. [Background technology]

[0002] Conventionally, for example, a display control system has been proposed that has a display unit on each of the front, rear, left side, and right side of a vehicle, captures images of blind spots from the viewpoint of viewing each display unit with an on-board camera, and displays the captured images around the vehicle on the display unit (see, for example, Patent Document 1). In the display control system described in Patent Document 1, when there is a blind spot area that cannot be captured by the on-board camera, an image of a moving object in the blind spot area is generated based on infrastructure information acquired by an infrastructure camera placed on the road side, and the generated image is displayed on the display unit. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-161066 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the display control system described in Patent Document 1, for example, if the blind spot area of ​​the in-vehicle camera is also a blind spot area of ​​the infrastructure camera, it may not be possible to generate an image of a moving object (target object) in the blind spot area based on infrastructure information. The present disclosure aims to provide a vehicle control method and a vehicle control system that can determine the behavior of an object in a blind spot that cannot be detected by either an on-board sensor or a roadside sensor. [Means for solving the problem]

[0005] A vehicle control method according to one aspect of the present disclosure uses an object detection unit mounted on the vehicle to detect objects around the vehicle, and controls the vehicle's driving based on the detection results of the surrounding objects. Images of multiple areas of the road are acquired from multiple image capture units arranged on the roadside, and blind spot areas are identified on the lane in which the vehicle is driving and on the oncoming lane, which are areas in which the object detection unit cannot detect objects and which cannot be captured by the image capture units. Based on the acquired images, the method determines whether there is a target object on the oncoming lane that is moving in the opposite direction to the vehicle's direction of travel and entering the blind spot area. If it is determined that there is a target object, the method compares the elapsed time since the target object entered the blind spot area with a predetermined threshold time to determine the behavior of the target object, and controls the vehicle's driving based on the determination result of the target object's behavior.

[0006] Furthermore, a vehicle control system according to one aspect of the present disclosure includes an object detection unit mounted on a vehicle that detects objects around the vehicle; a driving control unit that controls the driving of the vehicle based on the detection results of the surrounding objects; an image acquisition unit that acquires images of multiple areas of the road from multiple image capture units arranged on the road side; a blind spot area identification unit that identifies blind spot areas on the lane in which the vehicle is driving and on the oncoming lane, which are areas where objects cannot be detected by the object detection unit and cannot be captured by the image capture units; and a vehicle behavior determination unit that determines, based on the images, whether there is a target object on the oncoming lane that is moving in the opposite direction to the vehicle's traveling direction and entering the blind spot area, and if it determines that there is a target object, compares the elapsed time since the target object entered the blind spot area with a predetermined threshold time to determine the behavior of the target object. When the determination result of the behavior of the target object is obtained, the driving control unit controls the driving of the vehicle based on the determination result of the behavior of the target object. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to provide a vehicle control method and a vehicle control system that can determine the behavior of an object in a blind spot that cannot be detected by either an on-board sensor or a roadside sensor. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram showing a schematic configuration of a vehicle control system according to an embodiment; [Figure 2] FIG. 2 is a diagram illustrating the operation of the vehicle control system. [Figure 3] FIG. 2 is a diagram illustrating the functional configuration of an information processing device and a vehicle control unit. [Figure 4] 4 is a flowchart showing the operation of a travel control unit and the like. [Figure 5] 10 is a flowchart showing the processing contents of a blind spot area determination process. [Figure 6] FIG. 2 is a diagram illustrating the operation of the vehicle control system. [Figure 7] FIG. 2 is a diagram illustrating the operation of the vehicle control system. [Figure 8] 4 is a flowchart showing the operation of a vehicle behavior determination unit and the like. [Figure 9] 4 is a flowchart showing the operation of a vehicle behavior determination unit and the like. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that the drawings are schematic and may differ from the actual embodiments. Furthermore, the embodiments of the present disclosure shown below are examples of devices and methods for embodying the technical ideas of the present disclosure, and the technical ideas of the present disclosure do not limit the structure, arrangement, etc. of the components to those described below. Various modifications can be made to the technical ideas of the present disclosure within the technical scope defined by the claims.

[0010] (composition) In this embodiment, as shown in Fig. 1, a case where the vehicle control method of the present disclosure is applied to a vehicle control system 1 that causes a vehicle C1 to perform autonomous driving using on-board sensors and roadside sensors is illustrated. Fig. 1 is a diagram showing a schematic configuration of the vehicle control system 1 according to this embodiment. The vehicle control system 1 includes a server device 10, a plurality of infrastructure devices 20 arranged on the road side, and an in-vehicle device 30 mounted on a vehicle C1. The server device 10 includes a communication unit 11, a vehicle information DB (database) 12, an image processing unit 13, an infrastructure DB 14, a high-precision map DB 15, and an information processing unit 16. The communication unit 11 is a wireless communication unit that provides a wireless communication function between the server device 10 and an external device. The communication method of the communication unit 11 may be, for example, wireless communication via a public mobile communication network, satellite communication, or road-to-vehicle communication. The server device 10 transmits and receives data to and from the vehicle control unit 37 of the in-vehicle device 30, the imaging unit 22 of the infrastructure device 20, etc. via the communication unit 11.

[0011] The vehicle information DB12 stores information about the vehicle C1 (hereinafter also referred to as "vehicle information"). The vehicle information includes, for example, the departure point of the vehicle C1, the destination point, the route from the departure point to the destination point (hereinafter also referred to as "target route"), and the current position. The departure point and destination point are input into the vehicle C1 by the occupant and transmitted from the vehicle C1. The target route is set by the information processing unit 16 based on the departure point, the destination point, and the high-precision map DB15. The current position is detected by the self-position detection unit 34 of the vehicle C1 and transmitted from the vehicle C1. The image processing unit 13 performs image processing on the image acquired from the imaging unit 22 of the infrastructure device 20. In the image processing, vehicles, roads, etc. are detected from the image. The image processing unit 13 takes over the image processing when the information processing unit 16 needs to detect vehicles, roads, etc. from the image. The infrastructure DB 14 stores information (hereinafter also referred to as "infrastructure information") about the infrastructure device 20. The infrastructure information includes, for example, the location of the infrastructure device 20, the locations of the imaging areas A1 and A2 of the imaging unit 22 of the infrastructure device 20, and the location of a non-imaging area A3 (described later). The high-precision map DB 15 stores road map data for the area in which the vehicle control system 1 performs autonomous driving. As the road map data, for example, a navigation map that can be used to calculate a target route from the departure point to the destination point of the vehicle C1 can be used.

[0012] The information processing unit 16 is a computer device that processes information for the server device 10. The information processing unit 16 includes a processor 16a and peripheral components such as a storage device 16b that stores computer programs and the like. The processor 16a may be, for example, a CPU (Central Processing Unit) or an MPU. The storage device 16b may be, for example, a semiconductor storage device, a magnetic storage device, or an optical storage device. The storage device 16b may include memories such as a register, a cache memory, and a ROM and RAM used as a main storage device. Each function of the information processing unit 16 described below is realized, for example, by the processor 16a executing a computer program stored in the storage device 16b.

[0013] The infrastructure device 20 includes a communication unit 21 and an imaging unit 22 . The communication unit 21 is a wireless communication unit that provides a wireless communication function between the infrastructure device 20 (imaging unit 22) and an external device. The communication method of the communication unit 21 may be, for example, wireless communication via a public mobile communication network, satellite communication, or road-to-vehicle communication. The infrastructure device 20 (imaging unit 22) transmits and receives data to and from the information processing unit 16 of the server device 10, etc., via the communication unit 21. The imaging unit 22 captures an image of a predetermined imaging area on the road. Furthermore, the multiple imaging units 22 capture images of multiple areas A1 and A2 on the road (see FIG. 2). The imaging unit 22 may be, for example, a camera having a solid-state imaging element such as a CCD image sensor or a CMOS image sensor. The imaging areas A1 and A2 of the imaging unit 22 are determined by the position of the imaging unit 22, the focal length of the lens, the angle of view, and the vertical and horizontal angles of the optical axis of the lens. As shown in FIG. 2, the multiple imaging units 22 have a non-imaging area A3 that cannot be imaged by any of the imaging units 22. In FIG. 2, the non-imaging area A3 is an area on the road located between the imaging areas A1 and A2 of two adjacent imaging units 22 (the far-side imaging unit 221 and the near-side imaging unit 222). The far-side imaging unit 221 is an imaging unit that captures the imaging area A1 that is further back in the traveling direction of the vehicle C1 than the non-imaging area A3. The near side imaging unit 222 is an imaging unit that images an imaging area A2 that is closer to the vehicle C1 in the traveling direction than the non-imaging area A3. Data of the captured image (image data) is transmitted to the server device 10. Figure 2 is a diagram showing the operation of the vehicle control system 1.

[0014] The in-vehicle device 30 includes a communication unit 31 , an object detection unit 32 , a vehicle information detection unit 33 , a self-position detection unit 34 , a high-precision map DB 35 , an actuator 36 , and a vehicle control unit 37 . The communication unit 31 is a wireless communication unit that provides a wireless communication function between the vehicle C1 (vehicle control unit 37) and an external device. The communication method of the communication unit 31 may be, for example, wireless communication via a public mobile communication network, satellite communication, or road-to-vehicle communication. The vehicle C1 (vehicle control unit 37) transmits and receives data to and from the information processing unit 16 of the server device 10, etc., via the communication unit 31. The object detection unit 32 detects objects (e.g., vehicles, pedestrians, roads) around the vehicle C1. For example, a laser radar, millimeter wave radar, camera, or LIDAR mounted on the vehicle C1 can be used as the object detection unit 32. The object detection result is output to the vehicle control unit 37.

[0015] The vehicle information detection unit 33 detects various types of information (vehicle information) obtained from the vehicle C1. Examples of the vehicle information detection unit 33 that can be used include a vehicle speed sensor that detects the vehicle speed of the vehicle C1, a wheel speed sensor that detects the rotational speed of the wheels, a three-axis acceleration sensor that detects acceleration in three axes, a steering angle sensor that detects the steering angle of the steered wheels, a gyro sensor that detects angular velocity, a yaw rate sensor that detects yaw rate, an accelerator sensor that detects the accelerator opening, and a brake sensor that detects the braking amount. The information detection results (vehicle information) are output to the vehicle control unit 37. The self-position detection unit 34 detects the self-position of the vehicle C1. For example, a GPS receiver that receives radio waves from multiple navigation satellites to measure the current position of the vehicle C1 can be used as the self-position detection unit 34. Data on the self-position (position data) is output to the vehicle control unit 37. The high-precision map DB 35 stores road map data, which may be, for example, high-precision three-dimensional map data (such as HD maps) for autonomous vehicles.

[0016] The actuator 36 includes a steering actuator, an accelerator opening actuator, and a brake control actuator. The steering actuator controls the steering direction and steering amount of the steering wheel of the vehicle C1. The accelerator opening actuator controls the accelerator opening of the vehicle C1. The brake control actuator controls the braking operation of the brake device of the vehicle C1. The actuator 36 operates the steering wheel, accelerator opening, and brake device of the vehicle C1 in response to control signals output from the vehicle control unit 37, causing the vehicle C1 to perform a predetermined vehicle behavior.

[0017] The vehicle control unit 37 is an electronic control unit mounted on the vehicle C1 and controls the driving of the vehicle C1. The vehicle control unit 37 includes a processor 36a and peripheral components such as a storage device 36b that stores computer programs and the like. The processor 36a may be, for example, a CPU or an MPU. The storage device 36b may be, for example, a semiconductor storage device, a magnetic storage device, or an optical storage device. The storage device 36b may include memories such as a register, a cache memory, and a ROM and RAM used as a main storage device. Each function of the vehicle control unit 37 described below is realized, for example, by the processor 36a executing a computer program stored in the storage device 36b.

[0018] Next, the functions of the information processing unit 16 and the vehicle control unit 37 will be described in detail. 3, the vehicle control unit 37 of the vehicle C1 (on-vehicle device 30) includes a traveling control unit 41 and a stop determination unit 42. FIG. 3 is a diagram showing the functional configuration of the information processing unit 16 and the vehicle control unit 37. The driving control unit 41 uses outputs from the object detection unit 32, the vehicle information detection unit 33, and the self-position detection unit 34, as well as road map data in the high-precision map DB 35, to start generating a control signal for the actuator 36 so that the vehicle C1 autonomously drives along the target route (S101 in FIG. 4). That is, the driving control unit 41 controls the driving of the vehicle C1 based on the object detection result by the object detection unit 32. As a result, the vehicle C1 starts autonomous driving from the starting point toward the target point. As the target route, for example, a target route set by the information processing unit 16 of the server device 10 and stored in the vehicle information DB 12 can be used. Here, in the autonomous driving, on a one-lane road, if another vehicle C3 parked on the road is present in the lane in which the vehicle C1 is driving (hereinafter also referred to as the "own lane"), the vehicle C1 will stray from the own lane into the oncoming lane and pass by the other vehicle C3 parked on the road. FIG. 4 is a flowchart showing the operation of the driving control unit 41 and the like.

[0019] When the traveling control unit 41 starts autonomous traveling, the vehicle stop determination unit 42 transmits the vehicle information detected by the vehicle information detection unit 33 and the self-position detected by the self-position detection unit 34 to the server device 10 (S102 in FIG. 4). Subsequently, the stop determination unit 42 receives information indicating the blind spot area Bs (hereinafter also referred to as "blind spot area information") transmitted from the server device 10 via the communication unit 31 (S103 in FIG. 4). Examples of the blind spot area information include the position and range of the blind spot area Bs. Examples of the blind spot area Bs include, as shown in FIG. 2, areas in the lane in which the vehicle C1 is traveling (the vehicle's own lane) and the oncoming lane, where the object detection unit 32 cannot detect an object and where the image capture unit 22 cannot capture an image. Examples of areas in which the object detection unit 32 cannot detect an object include areas in which an obstruction (such as another vehicle C3) exists between the vehicle C1 and the lane in which the vehicle C1 is traveling, making it impossible to detect an object due to the obstruction. Here, in this embodiment, as shown in Figure 2, a situation is assumed in which there is another vehicle C3 parked on the road in the lane in which vehicle C1 is traveling, and an example is given in which the area in which the other vehicle C3 exists and the area on the oncoming lane of that area are used as areas in which objects cannot be detected by the object detection unit 32.

[0020] Furthermore, based on the received blind spot area information, the vehicle stop determination unit 42 determines whether a blind spot area Bs exists in the oncoming lane of the vehicle C1 traveling on the target route (S104 in FIG. 4). If it is determined that a blind spot area Bs exists ("Yes" in S104 in FIG. 4), it determines whether the vehicle C1 has arrived in the space where the blind spot area Bs exists (hereinafter also referred to as the "target space") based on the vehicle's own position acquired by the vehicle's own position detection unit 34 (S105 in FIG. 4). If it is determined that the vehicle C1 has not arrived in the target space ("No" in S105 in FIG. 4), the above flow of S102 to S105 is repeated. If it is determined that the vehicle C1 has arrived at the target space while repeating the flow ("Yes" in S105 of FIG. 4), the vehicle stop determination unit 42 generates a control signal for the actuator 36 so that the vehicle C1 stops in front of the other vehicle C3 that is parked on the road in the own lane (temporary stopping space) (S106 of FIG. 4). In addition, a vehicle result waiting signal is transmitted to the server device 10 via the communication unit 31 (S106 of FIG. 4). As a result, the vehicle C1 temporarily suspends its autonomous traveling and waits for the determination result of the behavior of the oncoming vehicle C2 in the blind spot area Bs (hereinafter also referred to as the "behavior determination result") to be transmitted from the server device 10.

[0021] Furthermore, when the vehicle C1 is stopped by the vehicle stop determination unit 42, the traveling control unit 41 receives the behavior determination result transmitted from the server device 10 via the communication unit 31 (S107 in FIG. 4). Furthermore, when the behavior determination result is received (i.e., when the determination result of the behavior of the oncoming vehicle C2 is obtained), the traveling control unit 41 determines whether the oncoming vehicle C2 is present in the blind spot area Bs based on the received behavior determination result. If it determines that the oncoming vehicle C2 is not present, the traveling control unit 41 resumes generating a control signal for the actuator 36 so that the autonomous traveling from the starting point toward the destination point is resumed (S108 in FIG. 4). That is, the traveling control unit 41 controls the traveling of the vehicle C1 based on the determination result of the behavior of the oncoming vehicle C2 obtained from the server device 10. As a result, the vehicle C1 starts traveling from just before the other vehicle C3 (the temporary stopping space) and resumes autonomous traveling from the starting point toward the destination point. At this time, the vehicle C1 strays from its own lane into the oncoming lane and passes by the other vehicle C3 parked on the road in its own lane. If it is determined that an oncoming vehicle C2 is present in the blind spot area Bs, the occupants of the vehicle C1 may be notified of this and visually urged to drive.

[0022] Furthermore, when autonomous traveling is resumed, the traveling control unit 41 determines whether the vehicle C1 has arrived at the destination point based on the self-position detected by the self-position detection unit 34 (S109 in FIG. 4). If it is determined that the vehicle C1 has not arrived at the destination point ("No" in S109 in FIG. 4), the flow of S102 to S109 described above is repeated. If the vehicle C1 arrives at the destination point while repeating the flow ("Yes" in S109 in FIG. 4), the autonomous traveling of the vehicle C1 is terminated.

[0023] In addition, as shown in FIG. 3, the information processing unit 16 of the server device 10 includes a blind spot area identification unit 51 (broadly speaking, an "image acquisition unit" or "blind spot area identification unit") and a vehicle behavior determination unit 52 (broadly speaking, an "image acquisition unit" or "vehicle behavior determination unit"). The blind spot area identification unit 51 receives vehicle information transmitted from the vehicle C1 via the communication unit 11 (S201 in FIG. 4). The blind spot area identification unit 51 also determines whether there is a blind spot area Bs within the lane in which the vehicle C1 is traveling (the vehicle's own lane) and the area on the opposite lane along the target route (S202 in FIG. 4). That is, the blind spot area Bs is identified within the area on the vehicle's own lane and the area on the opposite lane. To identify the blind spot area Bs, as shown in FIGS. 2, 6, and 7, among multiple non-image capture areas A3 that cannot be captured by the image capture unit 22, the non-image capture area A3 that overlaps with an area on the vehicle's own lane where another vehicle C3 parked on the road is present is identified as the blind spot area Bs. To identify the blind spot area Bs, the latest images of multiple areas of the road are acquired from the multiple image capture units 22, and the acquired images are processed by the image processing unit 13 to detect the other vehicle C3 parked on the road. If the blind spot area identification unit 51 determines that there is no blind spot area Bs ("No" in S202 of FIG. 4), it repeats the flow from S201 to S202. If another vehicle C3 parks on the road while repeating the flow, the blind spot area identification unit 51 determines that there is a blind spot area Bs ("Yes" in S202 of FIG. 4) and transmits blind spot area information to the vehicle C1 (S203 of FIG. 4).

[0024] After the blind spot area identification unit 51 transmits the blind spot area information, the vehicle behavior determination unit 52 acquires the latest images of multiple areas of the road from the multiple image capture units 22 and determines, based on the acquired images, whether there is a space in front of the vehicle C1 where the vehicle C1 can temporarily stop (hereinafter also referred to as a "temporary stopping space") (S204 in FIG. 4). If it is determined that there is a temporary stopping space ("Yes" in S204 in FIG. 4), the vehicle behavior determination unit 52 executes a blind spot area determination process (S205 in FIG. 4) to determine whether an oncoming vehicle C2 traveling in the blind spot area Bs is present based on images acquired from the infrastructure device 20 (the rear-side image capture unit 201 and the front-side image capture unit 202). In the blind spot area determination process, as shown in FIG. 6, if it detects that the oncoming vehicle C2 has entered the blind spot area Bs ("Yes" in S301 in FIG. 5), the calculation process continues until the oncoming vehicle C2 leaves the blind spot area Bs and passes the vehicle C1. That is, the blind spot area determination process ends only when it is determined that no oncoming vehicle C2 is present in the blind spot area Bs. The blind spot area determination process will be described in detail later.

[0025] Furthermore, after the blind spot area determination process is completed (i.e., after it is determined that no oncoming vehicle C2 is traveling within the blind spot area Bs), the vehicle behavior determination unit 52 determines whether or not it has received a vehicle result waiting signal transmitted from the vehicle C1 via the communication unit 11 (S206 in FIG. 4). If it is determined that no vehicle result waiting signal has been received ("No" in S206 in FIG. 4), the above flow of S202 to S206 is repeated. As a result, the blind spot area determination process is repeated until the vehicle C1 stops in front of the other vehicle C3 that is parked on the road (in the temporary stopping space), and the determination result (that no oncoming vehicle C2 is traveling within the blind spot area Bs) is updated. While this update of the determination result is repeated, when the vehicle C1 stops in front of the other vehicle C3 that is parked on the road (in the temporary stopping space) and the vehicle C1 transmits a vehicle result waiting signal, the vehicle behavior determination unit 52 determines that the vehicle result waiting signal has been received ("Yes" in S206 of FIG. 4), and transmits the determination result obtained in the blind spot area determination process (i.e., the determination result that the oncoming vehicle C2 traveling in the blind spot area Bs is not present) to the vehicle C1 (S207 of FIG. 4). As a result, as described above, the vehicle C1 starts from the stopped state and resumes autonomous driving from the starting point to the destination point.

[0026] Next, a detailed description will be given of the blind spot area determination process executed by the information processing unit 16. During the execution of the blind spot area determination process, the vehicle behavior determination unit 52 acquires the latest images from the imaging unit 22 in sequence. In the blind spot area determination process, the vehicle behavior determination unit 52 determines, based on an image acquired from the imaging unit 22, whether or not there is an object (hereinafter also referred to as a "target object") in the oncoming lane of the lane in which the vehicle C1 is traveling (the lane in which the vehicle C1 is traveling) that is moving in the opposite direction to the traveling direction of the vehicle C1 and entering the blind spot area Bs (S301 in FIG. 5). In this embodiment, a case is exemplified in which it is determined whether or not there is an oncoming vehicle C2 traveling in the oncoming lane as the target object. In FIG. 2, it is determined, based on an image acquired from the far side imaging unit 201, whether or not there is an oncoming vehicle C2 entering the blind spot area Bs from the imaging area A1 of the far side imaging unit 201. FIG. 5 is a flowchart showing the processing contents of the blind spot area determination process. If the vehicle behavior determination unit 52 determines that the oncoming vehicle C2 does not exist ("No" in S301 of FIG. 5), it determines that the oncoming vehicle C2 is not traveling in the blind spot area Bs, and proceeds to S206 of FIG. 4. On the other hand, if it determines that the oncoming vehicle C2 is present ("Yes" in S301 of FIG. 5), it determines whether the oncoming vehicle C2 has passed the vehicle C1 based on the acquired image (S302 of FIG. 5). In FIG. 2, it determines whether the oncoming vehicle C2 has passed the vehicle C1 based on the image acquired from the front-side imaging unit 202. If the vehicle behavior determination unit 52 determines that the oncoming vehicle C2 has passed the vehicle C1 ("Yes" in S302 of FIG. 5), it determines that the oncoming vehicle C2 is not traveling in the blind spot area Bs, and proceeds to S206 of FIG. 4. When the process proceeds to S302 from S307, S308, S311, S316, S317, or S322 (described later), S302 in FIG. 5 repeatedly determines whether the oncoming vehicle C2 has passed beside the vehicle C1, and after determining that the oncoming vehicle C2 has passed, the process proceeds to S206 in FIG. 4.

[0027] On the other hand, when the vehicle behavior determination unit 52 determines that the oncoming vehicle C2 has not passed by the vehicle C1 ( "No" in S302 of FIG. 5), as shown in FIGS. 2, 6, and 7, it determines whether the length L1 of the column of oncoming vehicles C2 continuously entering the blind spot area Bs is greater than or equal to the length L2 of the blind spot area Bs (S303 in FIG. 5). Examples of the "column of oncoming vehicles C2 continuously entering the blind spot area Bs" include a column of oncoming vehicles C2 where the time interval when the oncoming vehicle C2 enters the blind spot area Bs is within a predetermined time (for example, 3 seconds). Also, as a method for determining whether the length L1 of the vehicle column is greater than or equal to the length L2 of the blind spot area Bs (L1≥L2), for example, it is determined whether a part of the vehicle column is captured in the images of the two imaging areas A1 and A2 sandwiching the non-imaging area A3. When it is determined that a part of the vehicle column is captured (for example, the rear side of the vehicle column is captured in the imaging area A1 and the front side of the vehicle column is captured in the imaging area A2), a method of determining that L1≥L2 can be adopted. And when it is determined that the length L1 of the vehicle column is shorter than the length L2 of the blind spot area Bs (L1<L2) ( "No" in S303 of FIG. 5), based on the image acquired from the imaging unit 22, the number of oncoming vehicles C2 continuously entering the blind spot area Bs is detected, and it is determined whether the oncoming vehicle C2 is one vehicle as shown in FIGS. 2, 6, and 7 (S304 in FIG. 5). In FIGS. 2, 6, and 7, based on the image acquired from the rear imaging unit 201, it is determined whether the oncoming vehicle C2 that has entered the blind spot area Bs from the imaging area A1 of the rear imaging unit 201 is one vehicle. And when the vehicle behavior determination unit 52 determines that the oncoming vehicle C2 is one vehicle ( "Yes" in S304 of FIG. 5), it determines whether the oncoming vehicle C2 that has entered the blind spot area Bs has exited the blind spot area Bs (S305 in FIG. 5). In FIG. 2, based on the image acquired from the front imaging unit 202, it is determined whether there is an oncoming vehicle C2 that has exited the blind spot area Bs into the imaging area A2. And when it is determined that the oncoming vehicle C2 has exited ( "Yes" in S305 of FIG. 5), it is determined that there is no traveling vehicle within the blind spot area Bs (S307 in FIG. 5), and the process proceeds to S206 in FIG. 4.

[0028] On the other hand, when the vehicle behavior determination unit 52 determines that the oncoming vehicle C2 has not exited the blind spot area Bs ("No" in S305 of FIG. 5), it determines whether the elapsed time Te since the oncoming vehicle C2 entered the blind spot area Bs has exceeded a predetermined threshold time Tth (S306 of FIG. 5). The threshold time Tth can be set, for example, by measuring the time required for a vehicle (any vehicle) to pass through the non-image capture area A3 (hereinafter also referred to as "passing time To") based on images of multiple time ranges acquired by the image capture unit 22 (S401 of FIG. 8), and then performing statistical processing on the multiple measured passing times To to set the threshold time Tth (S402 of FIG. 8). In this case, the passing time To may be measured by identifying the same vehicle from images of the two image capture areas A1 and A2 sandwiching the non-image capture area A3, and measuring the time from when the identified vehicle disappears from one image (the image of image capture area A1) to when it reappears in the other image (the image of image capture area A2). Furthermore, in measuring the passing time To, a vehicle that passes through the non-image capture area A3 without stopping may be identified, and the time required for the identified vehicle to pass through the non-image capture area A3 (passing time To) may be measured. The measured passing time To may also be accumulated for each road environment including time of day and weather, as shown in FIG. 8. In FIG. 8, the passing time To is accumulated in the storage device 16b of the server device 10. In this case, statistical processing may be performed on the accumulated passing time To for each environmental condition to calculate an average passing time Tave, and the calculated average passing time Tave may be used as the threshold time Tth for each environmental condition. FIG. 8 is a flowchart showing the operation of the vehicle behavior determination unit 52 and the like.

[0029] If the vehicle behavior determination unit 52 determines that the elapsed time Te has not exceeded the threshold time Tth (Te≦Tth), it repeats the flow of S305 to S306 described above (S306 “No” in FIG. 6). If it determines that the threshold time Tth has been exceeded (Te>Tth) while repeating the flow (S306 “Yes” in FIG. 5), the vehicle behavior determination unit 52 determines that the oncoming vehicle C2 that entered the blind spot area Bs has stopped in the blind spot area Bs, determines that there is no other vehicle C3 traveling in the blind spot area Bs (S307 in FIG. 5), and after determining that the last oncoming vehicle C2 has passed the vehicle C1 (S302 “Yes” in FIG. 5), the process proceeds to S206 in FIG. 4.

[0030] On the other hand, as shown in Fig. 6, when the vehicle behavior determination unit 52 determines that there are multiple oncoming vehicles C2 consecutively entering the blind spot area Bs (S304 "No" in Fig. 5), it determines whether all of the oncoming vehicles C2 (all vehicles) have exited the blind spot area Bs (S308 in Fig. 5). In Fig. 6, it determines whether all of the oncoming vehicles C2 (all vehicles) have exited the blind spot area Bs into the imaging area A2 based on the image acquired from the front-side imaging unit 202. Then, when it determines that all vehicles have exited the blind spot area Bs (S308 "Yes" in Fig. 5), it determines that the last oncoming vehicle C2 has passed the vehicle C1 (S302 "Yes" in Fig. 5), and then proceeds to S206 in Fig. 4.

[0031] On the other hand, if the vehicle behavior determination unit 52 determines that one of the oncoming vehicles C2 has not yet left the blind spot Bs ("No" in S308 of FIG. 5), it determines whether any of the oncoming vehicles C2 have left the blind spot Bs (S309 of FIG. 5). If it determines that none of the oncoming vehicles C2 have left the blind spot Bs ("No" in S309 of FIG. 5), it determines whether the elapsed time Te since the leading oncoming vehicle C2 entered the blind spot Bs has exceeded the threshold time Tth (S310 of FIG. 5). If it determines that the elapsed time Te has not exceeded the threshold time Tth (Te≦Tth), it repeats the above-described flow of S308 to S310 ("No" in S310 of FIG. 5). While repeating the flow, if it is determined that the threshold time Tth has been exceeded (Te>Tth) ("Yes" in S310 of Figure 5), it is determined that all of the multiple oncoming vehicles C2 that entered the blind spot area Bs have stopped within the blind spot area Bs, and it is determined that there are no moving vehicles within the blind spot area Bs (S311 of Figure 5).After it is determined that the last oncoming vehicle C2 has passed vehicle C1 ("Yes" in S302 of Figure 5), the process proceeds to S206 of Figure 4.

[0032] Meanwhile, the vehicle behavior determination unit 52 determines whether another oncoming vehicle C2 (hereinafter also referred to as a "second oncoming vehicle") that was traveling behind one of the multiple oncoming vehicles C2 (hereinafter referred to as a "first oncoming vehicle") when the oncoming vehicle C2 entered the blind spot area Bs has exited the blind spot area Bs before the first oncoming vehicle (S312 in FIG. 5). If it is determined that the second oncoming vehicle has exited the blind spot area Bs before the first oncoming vehicle ("Yes" in S312 in FIG. 5), it determines that the first oncoming vehicle has stopped in the blind spot area Bs, and excludes the first oncoming vehicle from the multiple oncoming vehicles C2 that have entered the blind spot area Bs (i.e., the oncoming vehicles C2 to be monitored) (S313 in FIG. 5).

[0033] Furthermore, after determining that the first oncoming vehicle has stopped in the blind spot area Bs, the vehicle behavior determination unit 52 determines whether only the leading oncoming vehicle C2 (hereinafter also referred to as the "front oncoming vehicle") among the multiple oncoming vehicles C2 has exited the blind spot area Bs (S314 in FIG. 5). That is, the vehicle behavior determination unit 52 determines whether the oncoming vehicle C2 traveling behind the leading oncoming vehicle (hereinafter also referred to as the "rear oncoming vehicle") has exited the blind spot area Bs. If the vehicle behavior determination unit 52 determines that only the leading oncoming vehicle has exited the blind spot area Bs ("Yes" in S314 in FIG. 5), the vehicle behavior determination unit 52 determines whether the elapsed time Te since the leading oncoming vehicle C2 entered the blind spot area Bs has exceeded the threshold time Tth (Te>Tth) (S315 in FIG. 5).

[0034] If the vehicle behavior determination unit 52 determines that the elapsed time Te has not exceeded the threshold time Tth (Te≦Tth), it repeats the flow of S314 to S315 described above (S315 “No” in FIG. 6). If it determines that the threshold time Tth has been exceeded (Te>Tth) while repeating the flow (S315 “Yes” in FIG. 5), the vehicle behavior determination unit 52 determines that all oncoming vehicles behind (all vehicles) have stopped in the blind spot area Bs, determines that no running vehicles exist in the blind spot area Bs (S316 in FIG. 5), and determines that the last oncoming vehicle C2 of the oncoming vehicles ahead has passed vehicle C1 (S302 “Yes” in FIG. 5), and then proceeds to S206 in FIG. 4. 5, the behavior of the oncoming vehicle C2 (target object) is determined by comparing the elapsed time Te since the oncoming vehicle C2 (target object) entered the blind spot area Bs with a predetermined threshold time Tth. Also, by comparing the elapsed time Te with the threshold time Tth, it is determined whether the oncoming vehicle C2 has stopped in the blind spot area Bs, as a determination of the behavior of the target object.

[0035] On the other hand, as shown in FIG. 7, when the vehicle behavior determination unit 52 determines that the length L1 of the train of multiple oncoming vehicles C2 continuously entering the blind spot area Bs is equal to or greater than the length L2 of the blind spot area Bs (L1≧L2) ("Yes" in S303 of FIG. 5), the vehicle behavior determination unit 52 determines whether all of the oncoming vehicles C2 (all vehicles) have exited the blind spot area Bs (S317 of FIG. 5). In FIG. 7, the vehicle behavior determination unit 52 determines whether all of the oncoming vehicles C2 (all vehicles) have exited the blind spot area Bs into the image capture area A2 based on the image acquired from the front-side image capture unit 202. Then, when the vehicle behavior determination unit 52 determines that all vehicles have exited the blind spot area Bs ("Yes" in S317 of FIG. 5), the vehicle behavior determination unit 52 determines that the last oncoming vehicle C2 has passed the vehicle C1 ("Yes" in S302 of FIG. 5), and then proceeds to S206 of FIG. 4.

[0036] On the other hand, if the vehicle behavior determination unit 52 determines that one of the multiple oncoming vehicles C2 has not yet exited the blind spot Bs ("No" in S317 of FIG. 5), it determines whether another oncoming vehicle C2 (a second oncoming vehicle) that was traveling behind one of the oncoming vehicles C2 (a first oncoming vehicle) in the line of vehicles when the oncoming vehicle C2 entered the blind spot Bs has exited the blind spot Bs before the first oncoming vehicle (S318 of FIG. 5). If it determines that the second oncoming vehicle has exited the blind spot Bs before the first oncoming vehicle ("Yes" in S318 of FIG. 5), it determines that the first oncoming vehicle has stopped in the blind spot Bs, and excludes the first oncoming vehicle from the multiple oncoming vehicles C2 that have entered the blind spot Bs (oncoming vehicles C2 to be monitored) (S319 of FIG. 5).

[0037] After determining that the first oncoming vehicle has stopped in the blind spot Bs, the vehicle behavior determination unit 52 determines whether only the leading oncoming vehicle C2 (the oncoming vehicle ahead) among the multiple oncoming vehicles C2 (the oncoming vehicles C2 in the vehicle line) has exited the blind spot Bs (S320 in FIG. 5). That is, the vehicle behavior determination unit 52 determines whether the oncoming vehicle C2 (the oncoming vehicle behind the leading oncoming vehicle) traveling behind the leading oncoming vehicle has exited the blind spot Bs. If the vehicle behavior determination unit 52 determines that only the leading oncoming vehicle has exited the blind spot Bs (S320 "Yes" in FIG. 5), the vehicle behavior determination unit 52 determines whether the elapsed time Te since the leading oncoming vehicle C2 entered the blind spot Bs has exceeded the threshold time Tth (S321 in FIG. 5). If the vehicle behavior determination unit 52 determines that the elapsed time Te has not exceeded the threshold time Tth (Te≦Tth), the vehicle behavior determination unit 52 repeats the above-described flow of S320 to S321 (S321 "No" in FIG. 6). While repeating the flow, if it is determined that the threshold time Tth has been exceeded (Te>Tth) ("Yes" in S321 of FIG. 5), the vehicle behavior determination unit 52 determines that all oncoming vehicles (all vehicles) from behind have stopped within the blind spot area Bs, determines that there are no moving vehicles within the blind spot area Bs (S322 of FIG. 5), and after determining that the last oncoming vehicle C2 from the oncoming vehicles ahead has passed vehicle C1 ("Yes" in S302 of FIG. 5), the process proceeds to S206 of FIG. 4.

[0038] (Effects of this embodiment) (1) In this embodiment, a blind spot Bs is identified on the lane in which the vehicle C1 is traveling and on the oncoming lane, which is an area in which the object detection unit 32 cannot detect an object and which cannot be captured by the image capture unit 22 (S202 in FIG. 4). Next, based on the image acquired by the image capture unit 22, it is determined whether an object (target object; oncoming vehicle C2) is present on the oncoming lane, moving in the opposite direction to the traveling direction of the vehicle C1 and entering the blind spot Bs (S301 in FIG. 5). If it is determined that the target object (oncoming vehicle C2) is present ("Yes" in S301 in FIG. 5), the behavior of the target object is determined by comparing the elapsed time Te since the target object (oncoming vehicle C2) entered the blind spot Bs with a predetermined threshold time Tth (S306, S311, S315, S322 in FIG. 5). Based on the determination result of the behavior of the target object, the traveling of the vehicle C1 is controlled (S108 in FIG. 4). This makes it possible to determine the behavior of a moving object (oncoming vehicle C2) in the blind spot area Bs that cannot be detected by either the object detection unit 32 (vehicle-mounted sensor) or the roadside sensor (imaging unit 22).

[0039] For example, if the road on which vehicle C1 is traveling has the following conditions: the average distance between intersections is 141 m, the speed limit is 30 mph (32 km / h), the infrastructure device 20 is installed near the intersection, and the imaging range of the imaging unit 22 is 50 m, the time required for oncoming vehicle C2 to pass through blind spot area Bs is 4.66 seconds. Therefore, the threshold time Tth is 4.66 seconds. Therefore, for example, if oncoming vehicle C2 is stopped in blind spot area Bs, the vehicle control system 1 of this embodiment can determine that oncoming vehicle C2 has stopped 4.66 seconds after entering blind spot area Bs. In contrast, as a comparative example, consider a configuration in which it is determined that the oncoming vehicle C2 has stopped in the blind spot area Bs when five seconds have elapsed since the threshold time Tth elapsed. In this case, it is determined that the oncoming vehicle C2 has stopped 9.66 seconds after the oncoming vehicle C2 enters the blind spot area Bs. Therefore, according to the vehicle control system 1 of this embodiment, the time required to determine whether the oncoming vehicle C2 has stopped can be reduced by 52% (=1-4.66 / 9.66) compared to the comparative example.

[0040] (2) In addition, when identifying the blind spot area Bs, the non-image capture area A3 that overlaps with an area where another parked vehicle C3 is present on the lane in which the vehicle C1 is traveling is identified as the blind spot area Bs, out of multiple non-image capture areas A3 that cannot be captured by the image capture unit 22. This makes it possible to prevent the vehicle C1 from interfering with the oncoming vehicle C2 when passing by the other parked vehicle C3.

[0041] (3) Furthermore, by comparing the elapsed time Te with the threshold time Tth, the behavior of the target object (oncoming vehicle C2) is determined by determining whether the oncoming vehicle C2 has stopped in the blind spot area Bs (S307 in FIG. 5). This makes it possible to determine whether the oncoming vehicle C2 is traveling in the blind spot area Bs.

[0042] (4) In this embodiment, the number of oncoming vehicles C2 continuously entering the blind spot area Bs is detected based on images acquired from the image capture unit 22. If only one oncoming vehicle C2 is detected ("Yes" in S304 of FIG. 5) and the oncoming vehicle C2 has not yet exited the blind spot area Bs ("No" in S305 of FIG. 5), it is determined whether the elapsed time Te since the oncoming vehicle C2 entered the blind spot area Bs exceeds a threshold time Tth (S306 of FIG. 5). If it is determined that the threshold time Tth has been exceeded, it is determined that the oncoming vehicle C2 has stopped in the blind spot area Bs (S307 of FIG. 5). Here, as a comparative example, consider a configuration in which, after the vehicle C1 is stopped, the vehicle C1 waits until the oncoming vehicle C2 passes through (exits) the blind spot area Bs, and the vehicle C1 starts moving after it is detected that the oncoming vehicle C2 has exited the blind spot area Bs. With this configuration, if an oncoming vehicle C2 stops in the blind spot area Bs, it may not be possible to detect that the oncoming vehicle C2 has left the blind spot area Bs, and the vehicle C1 may not be able to start moving. In contrast, in this embodiment, when an oncoming vehicle C2 passes through the blind spot area Bs, if the elapsed time Te from when the oncoming vehicle C2 entered the blind spot area Bs to when the oncoming vehicle C2 left the blind spot area Bs is longer than the threshold time Tth (for example, if it is much longer than the time it takes a typical vehicle to pass through the blind spot area Bs), it is determined that the oncoming vehicle C2 has stopped in the blind spot area Bs. Therefore, the vehicle C1 can start moving based on the determination result that the oncoming vehicle C2 has stopped in the blind spot area Bs, that is, based on the determination result that there is no oncoming vehicle C2 moving in the blind spot area Bs.

[0043] (5) Furthermore, based on the image acquired from the imaging unit 22, the number of oncoming vehicles C2 continuously entering the blind spot area Bs is detected. If there are multiple oncoming vehicles C2 detected (S304 "No" in FIG. 5), the length of the line of oncoming vehicles C2 is shorter than the length of the blind spot area Bs (S303 "No" in FIG. 5), and none of the multiple oncoming vehicles C2 have exited the blind spot area Bs (S309 "No" in FIG. 5), it is determined whether the elapsed time Te since the leading oncoming vehicle C2 entered the blind spot area Bs has exceeded a threshold time Tth (S310 in FIG. 5). If it is determined that the threshold time Tth has been exceeded, it is determined that all of the multiple oncoming vehicles C2 have stopped in the blind spot area Bs (S311 in FIG. 5). As a result, when multiple oncoming vehicles C2 pass through the blind spot area Bs, if the elapsed time Te since the leading oncoming vehicle C2 entered the blind spot area Bs is longer than the threshold time Tth (for example, if it is much longer than the time it takes for a typical vehicle to pass through the blind spot area Bs), it is determined that all of the oncoming vehicles C2 have stopped in the blind spot area Bs. Therefore, the vehicle C1 can start moving based on the determination result that all of the oncoming vehicles C2 have stopped in the blind spot area Bs, that is, the determination result that there are no oncoming vehicles C2 moving in the blind spot area Bs.

[0044] (6) Furthermore, based on the images acquired from the imaging unit 22, the number of oncoming vehicles C2 continuously entering the blind spot area Bs is detected. If there are multiple oncoming vehicles C2 detected (S304 "No" in FIG. 5) and the length of the line of vehicles formed by the oncoming vehicles C2 is shorter than the length of the blind spot area Bs (S303 "No" in FIG. 5), it is determined whether another oncoming vehicle C2 (second oncoming vehicle) that was traveling behind one of the multiple oncoming vehicles C2 (first oncoming vehicle) at the time of entering the blind spot area Bs has exited the blind spot area Bs before the first oncoming vehicle (S312 in FIG. 5). If it is determined that the second oncoming vehicle has exited the blind spot area Bs before the first oncoming vehicle, it is determined that the first oncoming vehicle has stopped in the blind spot area Bs (S313 in FIG. 5). As a result, when multiple oncoming vehicles C2 pass through the blind spot area Bs, if a second oncoming vehicle traveling behind the first oncoming vehicle exits the blind spot area Bs before the first oncoming vehicle, it is determined that the first oncoming vehicle has stopped in the blind spot area Bs. Therefore, the first oncoming vehicle can be excluded from the multiple oncoming vehicles C2 that have entered the blind spot area Bs (i.e., the oncoming vehicles C2 to be monitored).

[0045] (7) Furthermore, based on the images acquired from the imaging unit 22, the number of oncoming vehicles C2 continuously entering the blind spot area Bs is detected. If there are multiple oncoming vehicles C2 detected (S304 "No" in FIG. 5) and the length of the line of oncoming vehicles C2 is shorter than the length of the blind spot area Bs (S303 "No" in FIG. 5), and it is determined that only the leading oncoming vehicle C2 (the oncoming vehicle in front) of the multiple oncoming vehicles C2 has exited the blind spot area Bs during the time period Te since the leading oncoming vehicle C2 entered the blind spot area Bs exceeds the threshold time Tth (S315 "Yes" in FIG. 5) (S314 in FIG. 5), it is determined that the oncoming vehicle C2 (the oncoming vehicle in the rear) traveling behind the oncoming vehicle in front has stopped in the blind spot area Bs (S316 in FIG. 5). As a result, when multiple oncoming vehicles C2 pass through the blind spot area Bs, if it is determined that only the oncoming vehicles in front have exited the blind spot area Bs before the elapsed time Te since the first oncoming vehicle C2 entered the blind spot area Bs exceeds the threshold time Tth, it is determined that the oncoming vehicle behind has stopped in the blind spot area Bs. Therefore, based on the determination result that the oncoming vehicle behind has stopped in the blind spot area Bs, it can be determined that there are no oncoming vehicles C2 traveling in the blind spot area Bs.

[0046] (8) Furthermore, if, based on the images acquired from the imaging unit 22, the length of the procession of oncoming vehicles C2 continuously entering the blind spot area Bs is equal to or greater than the length of the blind spot area Bs ("Yes" in S303 of FIG. 5), it is determined whether another oncoming vehicle C2 (a second oncoming vehicle) traveling behind one of the oncoming vehicles C2 (a first oncoming vehicle) in the procession at the time of entering the blind spot area Bs has exited the blind spot area Bs before the first oncoming vehicle (S318 of FIG. 5). If it is determined that the second oncoming vehicle has exited the blind spot area Bs before the first oncoming vehicle, it is determined that the first oncoming vehicle has stopped in the blind spot area Bs (S319 of FIG. 5). As a result, when multiple oncoming vehicles C2 pass through the blind spot area Bs, if the second oncoming vehicle traveling behind the first oncoming vehicle has exited the blind spot area Bs before the first oncoming vehicle, it is determined that the first oncoming vehicle has stopped in the blind spot area Bs. Therefore, the first oncoming vehicle can be excluded from the multiple oncoming vehicles C2 that have entered the blind spot area Bs (that is, the oncoming vehicles C2 to be monitored).

[0047] (9) Furthermore, based on the images acquired from the imaging unit 22, if the length of the procession of oncoming vehicles C2 continuously entering the blind spot area Bs is equal to or greater than the length of the blind spot area Bs (S303 "Yes" in Figure 5), and if it is determined that only the leading oncoming vehicle C2 (the oncoming vehicle in front) among the oncoming vehicles C2 in the procession has exited the blind spot area Bs during the time period Te since the leading oncoming vehicle C2 entered the blind spot area Bs exceeds the threshold time Tth (S321 "Yes" in Figure 5) (S320 in Figure 5), it is determined that the oncoming vehicle C2 (the oncoming vehicle in the rear) traveling behind the oncoming vehicle in front has stopped in the blind spot area Bs (S322 in Figure 5). As a result, when multiple oncoming vehicles C2 pass through the blind spot area Bs, if it is determined that only the oncoming vehicles in front have exited the blind spot area Bs before the elapsed time Te since the first oncoming vehicle C2 entered the blind spot area Bs exceeds the threshold time Tth, it is determined that the oncoming vehicle behind has stopped in the blind spot area Bs. Therefore, based on the determination result that the oncoming vehicle behind has stopped in the blind spot area Bs, it can be determined that there are no oncoming vehicles C2 traveling in the blind spot area Bs.

[0048] (10) Furthermore, based on images of multiple time ranges acquired by the imaging unit 22, the passing time To, which is the time required for a vehicle to pass through the non-image capture area A3, is measured, and the measured multiple passing times To are statistically processed to set the threshold time Tth. This allows the threshold time Tth to be set reflecting the time actually required to pass through the non-image capture area A3 (blind spot area Bs), and the behavior of the oncoming vehicle C2 that has entered the blind spot area Bs to be more appropriately determined. (11) Furthermore, in measuring the passing time To, the same vehicle is identified from each of the images of the two imaging areas A1 and A2 that sandwich the non-image area A3, and the time from when the identified vehicle disappears from one image (the image of imaging area A1) to when it appears in the other image (the image of imaging area A2) is measured. This makes it possible to measure the passing time To of the non-image area A3 for each oncoming vehicle C2, for example, even when multiple vehicles pass through the non-image area A3, and to more appropriately set the threshold time Tth. (12) In addition, in measuring the passing time To, a vehicle that passes through the non-image capture area A3 without stopping is identified, and the time required for the identified vehicle to pass through the non-image capture area A3 is measured. As a result, for example, by measuring the time when the vehicle enters the non-image capture area A3 and the time when it exits the non-image capture area A3, the passing time To required to pass through the non-image capture area A3 can be more appropriately calculated.

[0049] (13) In addition, the measured passing time To is accumulated for each environmental condition, including the time of day and weather. This allows the threshold time Tth to be set for each of various environmental conditions, reflecting the environmental conditions, and allows for more appropriate judgment of the behavior of the oncoming vehicle C2 that has entered the blind spot Bs. (14) In addition, the accumulated passing times To are statistically processed for each environmental condition to calculate the average passing time Tave, and the calculated average passing time Tave is set as the threshold time Tth for each environmental condition. This allows for more appropriate determination of the behavior of the oncoming vehicle C2 in the blind spot Bs.

[0050] (Variation) (1) Between the processing of S202 and the processing of S203, the vehicle behavior determination unit 52 may determine whether the blind spot area Bs satisfies specific road conditions based on road map data stored in the high-precision map DB 35, and may allow a determination as to whether the oncoming vehicle C2 has stopped in the blind spot area Bs only if it determines that the specific road conditions are met (S501 in FIG. 9). This may avoid the execution of the blind spot area determination process and the execution of unnecessary determinations. In S501 in FIG. 9, it is determined whether the blind spot area Bs satisfies the specific road conditions, and if it is determined that it is met (S501 "Yes"), the process proceeds to S205 via S203 and S204, and the blind spot area determination process is executed. On the other hand, if it is determined that it is not met (S501 "No"), the process proceeds to S206, and the execution of the blind spot area determination process is avoided. FIG. 9 is a flowchart showing the operation of the vehicle behavior determination unit 52 and the like.

[0051] (2) An example of the road condition in S501 of FIG. 9 is that there is no road branch within the blind spot Bs. In this case, the vehicle behavior determination unit 52 determines whether there is a road branch within the blind spot Bs based on road map data (S501 of FIG. 9). Only when it determines that there is no road branch, does it permit the determination of whether the oncoming vehicle C2 has stopped within the blind spot Bs (S205 of FIG. 9). Here, for example, if the blind spot Bs into which the oncoming vehicle C2 has entered is a blind spot Bs with a road branch, the oncoming vehicle C2 may proceed onto the road after the branch within the blind spot Bs, and the elapsed time Te since the oncoming vehicle C2 entered the blind spot Bs may exceed the threshold time Tth. Furthermore, if the elapsed time Te exceeds the threshold time Tth, it may be erroneously determined that the oncoming vehicle C2 has stopped within the blind spot Bs. In contrast, in this embodiment, only when there is no road branch within the blind spot Bs, is the determination of whether the oncoming vehicle C2 has stopped within the blind spot Bs performed. That is, if there is a road fork in the blind spot area Bs, the system does not determine whether the oncoming vehicle C2 has stopped in the blind spot area Bs, which prevents the oncoming vehicle C2 from erroneously determining that it has stopped in the blind spot area Bs when it proceeds onto the road after the fork.

[0052] (3) Furthermore, an example of the road condition in S501 of FIG. 9 is that there is no boarding or alighting area within the blind spot Bs. In this case, the vehicle behavior determination unit 52 determines, based on road map data, whether there is a boarding or alighting area within the blind spot Bs for a transportation vehicle transporting passengers (S501 of FIG. 9). Only when it is determined that there is no boarding or alighting area within the blind spot Bs, does it permit the determination of whether the oncoming vehicle C2 has stopped within the blind spot Bs (S205 of FIG. 9). Here, for example, if the blind spot Bs into which the oncoming vehicle C2 has entered is the blind spot Bs where a boarding or alighting area for a transportation vehicle is located, there is a possibility that the transportation vehicle (oncoming vehicle C2) will temporarily stop within the blind spot Bs, and the elapsed time Te since the oncoming vehicle C2 entered the blind spot Bs may exceed the threshold time Tth. Furthermore, if the threshold time Tth is exceeded, there is a possibility that the oncoming vehicle C2 will be erroneously determined to have stopped within the blind spot Bs. In contrast, in this embodiment, a determination is made as to whether the oncoming vehicle C2 has stopped in the blind spot Bs only when there is no transportation vehicle boarding or alighting location within the blind spot Bs. In other words, if there is a transportation vehicle boarding or alighting location within the blind spot Bs, a determination as to whether the oncoming vehicle C2 has stopped in the blind spot Bs is not made. This makes it possible to prevent an erroneous determination that the oncoming vehicle C2 has stopped in the blind spot Bs when the transportation vehicle (oncoming vehicle C2) has temporarily stopped at a boarding or alighting location.

[0053] (4) Furthermore, an example of the road condition in S501 of Fig. 9 is that there is no place in the blind spot area Bs where the oncoming vehicle C2 can overtake. In this case, the vehicle behavior determination unit 52 determines, based on road map data, whether there is a place in the blind spot area Bs where the oncoming vehicle C2 can overtake (S501 of Fig. 9), and allows the determination of whether the oncoming vehicle C2 has stopped in the blind spot area Bs only when it determines that there is no place where the oncoming vehicle C2 can overtake (S205 of Fig. 9). For example, if the oncoming lane has two or more lanes, it determines that there is a place where the oncoming vehicle C2 can overtake, and if the oncoming lane is one lane, it determines that there is no place where the oncoming vehicle C2 can overtake. For example, if the blind spot Bs into which the oncoming vehicle C2 has entered is a blind spot Bs that has a location where the oncoming vehicle C2 can overtake, the rear oncoming vehicle C2 (second oncoming vehicle) among the multiple oncoming vehicles C2 may overtake the leading oncoming vehicle C2 (first oncoming vehicle), causing the order of the oncoming vehicles C2 to change between when they enter the blind spot Bs and when they exit the blind spot Bs. Furthermore, if the order of the oncoming vehicles C2 changes, it may be erroneously determined that the first oncoming vehicle has stopped in the blind spot Bs. In contrast, in this embodiment, a determination is made as to whether the oncoming vehicle C2 has stopped in the blind spot Bs only when there is no location within the blind spot Bs where the oncoming vehicle C2 can overtake. In other words, if there is a location within the blind spot Bs where the oncoming vehicle C2 can overtake, the determination as to whether the oncoming vehicle C2 has stopped in the blind spot Bs is not made. Therefore, it is possible to prevent the occurrence of an erroneous determination that the oncoming vehicle C2 has stopped in the blind spot area Bs due to a change in the order of the oncoming vehicle C2. [Explanation of symbols]

[0054] 1...vehicle control system, 10...server device, 11...communication unit, 12...vehicle information DB, 13...image processing unit, 14...infrastructure DB, 15...high-precision map DB, 16...information processing device, 16a...processor, 16b...storage device, 20...infrastructure device, 201...rear side imaging unit, 202...front side imaging unit, 21...communication unit, 22...imaging unit, 221...rear side imaging unit, 222...front side imaging unit, 30...in-vehicle device, 31...communication unit, 32...object detection unit, 33...vehicle information detection unit, 34...self-position detection unit, 35...high-precision map DB, 36...actuator, 36a...processor, 36b...storage device, 37...vehicle control unit, 41...driving control unit, 42...stopping determination unit, 51...blind spot area identification unit, 52...vehicle behavior determination unit

Claims

1. Detecting objects around the vehicle using an object detection unit mounted on the vehicle; controlling the running of the vehicle based on the detection result of the surrounding object; acquiring images of a plurality of areas of the road from a plurality of imaging units arranged on the road side; Identifying blind spots on the lane in which the vehicle is traveling and on the opposite lane, which are areas in which the object detection unit cannot detect an object and which cannot be imaged by the image capture unit; Based on the acquired image, it is determined whether there is a target object on the oncoming lane that is moving in the opposite direction to the traveling direction of the vehicle and entering the blind spot area; When it is determined that the target object is present, the time that has elapsed since the target object entered the blind spot area is compared with a predetermined threshold time to determine the behavior of the target object, and the traveling of the vehicle is controlled based on the determination result of the behavior of the target object. Vehicle control method.

2. In identifying the blind spot area, a non-image area that overlaps with an area where another vehicle parked on the road is present on the lane in which the vehicle is traveling is identified as the blind spot area, out of a plurality of non-image areas that cannot be imaged by the imaging unit. The vehicle control method according to claim 1 .

3. the target object is an oncoming vehicle traveling in the oncoming lane, By comparing the elapsed time with the threshold time, it is determined whether the oncoming vehicle has stopped in the blind spot area as a determination of the behavior of the target object. The vehicle control method according to claim 2 .

4. Based on the image, the number of oncoming vehicles continuously entering the blind spot area is detected, and if the number of detected oncoming vehicles is one and the oncoming vehicle has not left the blind spot area, it is determined whether the elapsed time since the oncoming vehicle entered the blind spot area exceeds the threshold time, and if it is determined that the threshold time has been exceeded, it is determined that the oncoming vehicle has stopped in the blind spot area. The vehicle control method according to claim 3.

5. Based on the image, the number of oncoming vehicles continuously entering the blind spot area is detected, and if there are multiple oncoming vehicles detected, the length of the line of oncoming vehicles is shorter than the length of the blind spot area, and none of the multiple oncoming vehicles has left the blind spot area, it is determined whether the elapsed time since the leading oncoming vehicle entered the blind spot area has exceeded the threshold time, and if it is determined that the threshold time has been exceeded, it is determined that all of the multiple oncoming vehicles have stopped in the blind spot area. The vehicle control method according to claim 3.

6. Based on the image, the number of oncoming vehicles continuously entering the blind spot area is detected, and if there are multiple oncoming vehicles detected and the length of the line of vehicles formed by the oncoming vehicles is shorter than the length of the blind spot area, it is determined whether a second oncoming vehicle, which is one of the multiple oncoming vehicles and is traveling behind a first oncoming vehicle when the oncoming vehicles entered the blind spot area, has exited the blind spot area before the first oncoming vehicle, and if it is determined that the second oncoming vehicle has exited the blind spot area before the first oncoming vehicle, it is determined that the first oncoming vehicle has stopped in the blind spot area. The vehicle control method according to claim 3.

7. Based on the image, the number of oncoming vehicles continuously entering the blind spot area is detected, and if there are multiple oncoming vehicles detected and the length of the line of oncoming vehicles is shorter than the length of the blind spot area, if it is determined that only the front oncoming vehicle, which is the front oncoming vehicle among the multiple oncoming vehicles, has exited the blind spot area before the elapsed time since the front oncoming vehicle entered the blind spot area exceeds the threshold time, it is determined that the rear oncoming vehicle, which is the oncoming vehicle traveling behind the front oncoming vehicle, has stopped in the blind spot area. The vehicle control method according to claim 3.

8. If the length of a line of oncoming vehicles continuously entering the blind spot area is equal to or longer than the length of the blind spot area, based on the image, it is determined whether a second oncoming vehicle, which is one of the oncoming vehicles in the line of vehicles traveling behind a first oncoming vehicle that is one of the oncoming vehicles in the line of vehicles at the time of entering the blind spot area, has exited the blind spot area before the first oncoming vehicle, and if it is determined that the second oncoming vehicle has exited the blind spot area before the first oncoming vehicle, it is determined that the first oncoming vehicle has stopped in the blind spot area. The vehicle control method according to claim 3.

9. When the length of a line of oncoming vehicles continuously entering the blind spot area is equal to or longer than the length of the blind spot area based on the image, if it is determined that only the front oncoming vehicle, which is the front oncoming vehicle among the oncoming vehicles in the line of vehicles, has exited the blind spot area during the time that has elapsed since the front oncoming vehicle entered the blind spot area until the threshold time has elapsed, it is determined that the rear oncoming vehicle, which is the oncoming vehicle traveling behind the front oncoming vehicle, has stopped in the blind spot area. The vehicle control method according to claim 3.

10. It is determined whether a part of the procession of vehicles is captured in each of the images of the two imaging regions sandwiching the non-imaging region, and if it is determined that a part of the procession of vehicles is captured in each of the images, it is determined that the length of the procession of vehicles is equal to or longer than the length of the blind spot region.

10. A vehicle control method according to claim 8 or 9.

11. Based on the images of a plurality of time ranges, a plurality of passing times, which are the times required for a vehicle to pass through the non-image capture area, are measured, and statistical processing is performed on the measured passing times to set the threshold time. The vehicle control method according to claim 3.

12. Based on road map data, it is determined whether the blind spot area satisfies specific road conditions, and only when it is determined that the specific road conditions are satisfied, it is permitted to determine whether the oncoming vehicle has stopped in the blind spot area. The vehicle control method according to claim 3.

13. It is determined whether there is a road branch in the blind spot area based on the road map data, and only when it is determined that there is no road branch, it is permitted to determine whether the oncoming vehicle has stopped in the blind spot area. The vehicle control method according to claim 12.

14. Based on the road map data, it is determined whether there is a boarding / alighting place for a transportation vehicle transporting people within the blind spot area, and only when it is determined that there is no boarding / alighting place, it is permitted to determine whether the oncoming vehicle has stopped in the blind spot area. The vehicle control method according to claim 12.

15. Based on the road map data, it is determined whether there is a place in the blind spot area where overtaking is possible, and only when it is determined that there is no place in the blind spot area where overtaking is possible, it is permitted to determine whether the oncoming vehicle has stopped in the blind spot area. The vehicle control method according to claim 12.

16. an object detection unit mounted on a vehicle and configured to detect objects around the vehicle; a driving control unit that controls driving of the vehicle based on the detection result of the surrounding object; an image acquisition unit that acquires images of multiple areas of the road from multiple imaging units arranged on the road side; a blind spot area specifying unit that specifies a blind spot area on a lane in which the vehicle is traveling and an oncoming lane, the blind spot area being an area in which the object detection unit cannot detect an object and an image cannot be captured by the image capturing unit; a vehicle behavior determination unit that determines, based on the image, whether or not there is a target object on the oncoming lane that is moving in a direction opposite to the traveling direction of the vehicle and entering the blind spot area, and, if it is determined that there is a target object, determines the behavior of the target object by comparing the elapsed time since the target object entered the blind spot area with a predetermined threshold time; When the determination result of the behavior of the target object is obtained, the traveling control unit controls the traveling of the vehicle based on the determination result of the behavior of the target object. Vehicle control system.

Images