Intersecting road detection device, intersecting road detection method, and program

Abstract

To appropriately detect an intersecting road that intersects a road on which a host vehicle is traveling.SOLUTION: An intersecting road detection device 15 includes: an acquisition section 3B that acquires information indicating road pixels corresponding to roads and wall pixels corresponding to walls included in a host vehicle front image; a first identification section 3C that identifies wall bottom portion pixels which are portions adjacent to pixels corresponding to host vehicle traveling road included in the road pixels among the wall pixels; a second identification section 3D that identifies wall high portion pixels which are portions higher than height of the host vehicle traveling road by a predetermined value or more among the wall pixels; a third identification section 3E that identifies wall high edge portion pixels which are portions adjacent to pixels other than the wall pixels among the wall high portion pixels; and a determination section 3F that determines that an intersecting road which is a road intersecting the host vehicle traveling road exists in a position of the pixels other than the wall pixels, when the pixels other than the wall pixels adjacent to the wall high edge portion pixels are the road pixels.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an intersection road detection device, an intersection road detection method, and a program.

Background Art

[0002] Patent Document 1 describes that it is determined whether a lateral road (including a lateral road extending in the left - right direction with respect to the vehicle and an oblique direction) is shown in a photographed image.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, in the technique described in Patent Document 1, the measurement result of an autofocus device is used to determine whether a lateral road is shown in a photographed image. Therefore, in the technique described in Patent Document 1, when information indicating the measurement result of the autofocus device is not included in the data of the photographed image, the lateral road included in the photographed image cannot be detected. During the running of the host vehicle, in order to respond to the sudden appearance of bicycles, pedestrians, etc. near intersections, or to reduce the collision between the host vehicle and surrounding vehicles traveling on an intersecting road that is the road intersecting with the road on which the host vehicle is running at an intersection, it is necessary to detect the intersecting road (intersection). When GPS (Global Positioning System) and map information are used for detecting the intersecting road (intersection), the cost may increase, or there is a risk that the position of the intersecting road (intersection) may be erroneously detected due to GPS displacement. When the intersecting road (intersection) is detected using the lane lines, etc. of the road on which the host vehicle is running, which are included in the image obtained by photographing the front of the host vehicle, there is a risk that the intersecting road (intersection) may not be appropriately detected when there are no clear lane lines on the road on which the host vehicle is running. Since the intersecting road is a place where something may suddenly appear on the road on which the host vehicle is running, it is necessary to detect it appropriately.

[0005] In view of the above points, an object of the present disclosure is to provide an intersecting road detection device, an intersecting road detection method, and a program that can appropriately detect an intersecting road that intersects with the road on which the host vehicle is running.

Means for Solving the Problem

[0006] (1) One aspect of the present disclosure is to obtain information indicating road pixels, which are pixels corresponding to a road included in an image generated from an image captured in front of a host vehicle, and wall pixels, which are pixels corresponding to a wall included in the image, and based on the road pixels and the wall pixels indicated by the information acquired by the acquisition unit, among the wall pixels, a wall bottom pixel that is a portion adjacent to a pixel corresponding to a road on which the host vehicle is traveling, which is the road on which the host vehicle is traveling, is specified by a first specifying unit, and based on the road pixels and the wall pixels indicated by the information acquired by the acquisition unit, among the wall pixels, a wall high pixel that is a portion higher than a predetermined value from the height of the road on which the host vehicle is traveling is specified by a second specifying unit, and based on the road pixels and the wall pixels indicated by the information acquired by the acquisition unit, a wall high edge pixel that is a portion adjacent to a pixel other than the wall pixel among the wall high pixels is specified by a third specifying unit, and when a pixel other than the wall pixel adjacent to the wall high edge pixel is the road pixel, a determination unit determines that there is an intersecting road, which is a road intersecting the road on which the host vehicle is traveling, at the position of the pixel other than the wall pixel. The intersection road detection device includes the above components.

[0007] (2) In the intersection road detection device of (1), when the pixel other than the wall pixel adjacent to the wall high edge pixel is not the road pixel, the determination unit may determine that there is no intersecting road at the position of the pixel other than the wall pixel.

[0008] (3) One aspect of the present disclosure is that an intersection road detection device acquires information indicating road pixels, which are pixels corresponding to the road included in the image, and wall pixels, which are pixels corresponding to the wall included in the image, generated from an image obtained by photographing the front of the host vehicle. The intersection road detection device, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step, performs a first specifying step of specifying wall bottom pixels, which are portions of the wall pixels adjacent to pixels corresponding to the road on which the host vehicle is traveling, which is the road included in the road pixels. The intersection road detection device, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step, performs a second specifying step of specifying wall high pixels, which are portions of the wall pixels that are higher than a predetermined value from the height of the road on which the host vehicle is traveling. The intersection road detection device, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step, performs a third specifying step of specifying wall high edge pixels, which are portions of the wall high pixels adjacent to pixels other than the wall pixels. The intersection road detection device includes a determination step of determining that there is an intersection road, which is a road intersecting the road on which the host vehicle is traveling, at the position of the pixel other than the wall pixel adjacent to the wall high edge pixel when the pixel other than the wall pixel adjacent to the wall high edge pixel is the road pixel. This is an intersection road detection method.

[0009] (4) One aspect of the present disclosure is to cause a processor to perform an acquisition step of acquiring information indicating road pixels, which are pixels corresponding to a road included in the image and generated from an image obtained by photographing the front of the host vehicle, and wall pixels, which are pixels corresponding to a wall included in the image; a first specifying step of specifying, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step, wall bottom pixels, which are portions of the wall pixels adjacent to pixels corresponding to the road on which the host vehicle is traveling, which is the road included in the road pixels; a second specifying step of specifying, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step, wall high pixels, which are portions of the wall pixels that are higher than a predetermined value from the height of the road on which the host vehicle is traveling; a third specifying step of specifying, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step, wall high edge pixels, which are portions of the wall high pixels adjacent to pixels other than the wall pixels; and a determination step of determining that there is an intersecting road, which is a road intersecting the road on which the host vehicle is traveling, at the position of the pixel other than the wall pixel when the pixel other than the wall pixel adjacent to the wall high edge pixel is a road pixel.

Advantages of the Invention

[0010] According to the present disclosure, an intersecting road intersecting the road on which the host vehicle is traveling can be appropriately detected.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the intersection road detection device, intersection road detection method, and program of the present disclosure will be described with reference to the drawings.

[0013] <First Embodiment> FIG. 1 is a diagram showing an example of the host vehicle 1 to which the intersection road detection device 15 according to the first embodiment is applied. In the example shown in FIG. 1, the host vehicle 1 includes a camera 11, an HMI (Human Machine Interface) 12, a vehicle state sensor 13, a surrounding situation sensor 14, an intersection road detection device 15, a vehicle control device 16, a steering actuator 16A, a braking actuator 16B, and a driving actuator 16C. The camera 11 captures an image of the front of the host vehicle 1 and transmits data of the host vehicle front image to the intersection road detection device 15 and the vehicle control device 16. The HMI 12 has functions such as receiving various operations of the driver of the host vehicle 1, and transmits a signal indicating the operation of the driver of the host vehicle 1 to the vehicle control device 16. The vehicle state sensor 13 detects the state of the host vehicle 1 and transmits the detection result to the vehicle control device 16. The vehicle state sensor 13 includes, for example, a vehicle speed sensor and the like. The surrounding situation sensor 14 detects, for example, obstacles, surrounding vehicles, pedestrians, etc. existing around the host vehicle 1, and transmits the detection result to the vehicle control device 16. The surrounding situation sensor 14 includes, for example, a camera that captures images of the side, rear, etc. of the host vehicle 1, LiDAR (Light Detection And Ranging), radar, sonar, etc. The intersection road detection device 15 detects a road (intersection road RD3 (see FIG. 3)) that intersects the road on which the host vehicle 1 is traveling (host vehicle traveling roads RD1, RD2 (see FIGS. 2 and 3)), and transmits the detection result to the vehicle control device 16. The vehicle control device 16 is configured by a driving support ECU (Electronic Control Unit). The vehicle control device 16 controls the steering actuator 16A, the braking actuator 16B, and the driving actuator 16C based on information (data, signals) transmitted from, for example, the camera 11, the HMI 12, the vehicle state sensor 13, the surrounding situation sensor 14, and the intersection road detection device 15.

[0014] The intersection road detection device 15 is configured by a microcomputer including a communication interface (I / F) 151, a memory 152, and a processor 153. The communication interface 151 has an interface circuit for connecting the intersection road detection device 15 to the camera 11 and the vehicle control device 16. The memory 152 stores programs and various data used in the processes executed by the processor 153. The processor 153 has functions as an image processing device 3A, an acquisition unit 3B, a first specifying unit 3C, a second specifying unit 3D, a third specifying unit 3E, and a determination unit 3F. The image processing device 3A acquires data of the host vehicle front image transmitted from the camera 11. Further, the image processing device 3A executes an image segmentation (identification of a subject included in the image) process such as semantic segmentation on the host vehicle front image.

[0015] FIGS. 2 and 3 are diagrams showing an example of the processing result of the image segmentation executed by the image processing device 3A. Specifically, FIG. 2 shows a first example of the processing result of the image segmentation executed by the image processing device 3A, and FIG. 3 shows a second example of the processing result of the image segmentation executed by the image processing device 3A. In the example shown in FIG. 2, in the processing result of image segmentation executed by the image processing device 3A on the front image of the host vehicle captured by the camera 11, road pixels RP corresponding to the road (host vehicle traveling road RD1) on which the host vehicle 1 is traveling, and wall pixels WP corresponding to walls WL1 and WL2 provided adjacent to the host vehicle traveling road RD1 are included. The wall pixels WP corresponding to the wall WL1 include a wall bottom pixel WP1 that is a portion adjacent to the road pixels RP corresponding to the host vehicle traveling road RD1, and a wall upper pixel WP2 that is a portion higher than a predetermined value (for example, several tens of centimeters, etc.) than the height of the host vehicle traveling road RD1. The wall upper pixel WP2 includes a wall upper edge pixel WP2A that is a portion adjacent to a pixel other than the wall pixel WP (for example, a pixel corresponding to the portion surrounded by the circle CL in FIG. 2), and a wall upper non-edge pixel WP2B that is a portion not adjacent to a pixel other than the wall pixel WP. In the example shown in FIG. 3, in the processing result of image segmentation executed by the image processing device 3A on the front image of the host vehicle captured by the camera 11, road pixels RP corresponding to the road (host vehicle traveling road RD2) on which the host vehicle 1 is traveling and the road (intersecting road RD3) intersecting the host vehicle traveling road RD2, and wall pixels WP corresponding to walls WL3 and WL4 provided adjacent to the host vehicle traveling road RD2 are included. The wall pixels WP corresponding to the wall WL3 include the wall bottom pixel WP1, the wall upper edge pixel WP2A of the wall upper pixel WP2, and the wall upper non-edge pixel WP2B.

[0016] In the example shown in FIG. 1, the acquisition unit 3B acquires information indicating road pixels RP, wall pixels WP, etc. from the processing result of image segmentation executed by the image processing device 3A. That is, the acquisition unit 3B acquires information indicating pixels (road pixels RP) corresponding to the roads RD1, RD2, and RD3 included in the front image of the host vehicle, pixels (wall pixels WP) corresponding to the walls WL1, WL2, WL3, and WL4 included in the front image of the host vehicle, etc., which are generated from the image (front image of the host vehicle) obtained by photographing the front of the host vehicle 1. Specifically, in the example shown in FIG. 2, the acquisition unit 3B acquires information indicating road pixels RP corresponding to the road RD1 during the travel of the host vehicle, wall pixels WP corresponding to the walls WL1 and WL2, and the like. In the example shown in FIG. 3, the acquisition unit 3B acquires information indicating road pixels RP corresponding to the road RD2 and the intersecting road RD3 during the travel of the host vehicle, wall pixels WP corresponding to the walls WL1 and WL2, and the like.

[0017] In the example shown in FIG. 1, the first specifying unit 3C specifies, based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B, the wall bottom pixels WP1 that are adjacent to the pixels corresponding to the roads RD1 and RD2 during the travel of the host vehicle included in the road pixels RP among the wall pixels WP. Specifically, in the example shown in FIG. 2, the first specifying unit 3C specifies, based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B, the wall bottom pixels WP1 that are adjacent to the pixels corresponding to the road RD1 during the travel of the host vehicle included in the road pixels RP among the wall pixels WP. In the example shown in FIG. 3, the first specifying unit 3C specifies, based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B, the wall bottom pixels WP1 that are adjacent to the pixels corresponding to the road RD2 during the travel of the host vehicle included in the road pixels RP among the wall pixels WP.

[0018] In the example shown in FIG. 1, the second specifying unit 3D specifies, based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B, the wall high pixels WP2 that are portions of the wall pixels WP that are higher than a predetermined value above the heights of the roads RD1 and RD2 during the travel of the host vehicle. Specifically, in the example shown in FIG. 2, the second specifying unit 3D specifies, based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B, the wall high pixels WP2 that are portions of the wall pixels WP that are higher than a predetermined value above the height of the road RD1 during the travel of the host vehicle. In the example shown in FIG. 3, the second specifying unit 3D specifies, based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B, the wall high pixels WP2 that are portions of the wall pixels WP that are higher than a predetermined value above the height of the road RD2 during the travel of the host vehicle.

[0019] In the example shown in FIG. 1, the third specifying unit 3E specifies a wall height edge pixel WP2A, which is a part of the wall height pixels WP2 that is adjacent to pixels other than the wall pixels WP, based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B. Specifically, in the example shown in FIG. 2, the third specifying unit 3E specifies a wall height edge pixel WP2A, which is a part of the wall height pixels WP2 that is adjacent to pixels other than the wall pixels WP (for example, pixels corresponding to the portion surrounded by the circle CL in FIG. 2, etc.), based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B. In the example shown in FIG. 2, for example, pixels corresponding to a fence, pixels corresponding to border plantings, pixels corresponding to guardrails, pixels corresponding to fields, pixels corresponding to a river, etc. correspond to "pixels other than the wall pixels WP". In the example shown in FIG. 3, the third specifying unit 3E specifies a wall height edge pixel WP2A, which is a part of the wall height pixels WP2 that is adjacent to pixels other than the wall pixels WP (for example, pixels corresponding to the portion surrounded by the circle CL in FIG. 3, etc.), based on the road pixels RP and the wall pixels WP indicated by the information acquired by the acquisition unit 3B. In the example shown in FIG. 3, for example, the road pixels RP corresponding to the intersecting road RD3 correspond to "pixels other than the wall pixels WP".

[0020] In the example shown in FIG. 1, the determination unit 3F determines whether a pixel other than the wall pixel adjacent to the wall height edge pixel WP2A is a road pixel RP. When a pixel other than the wall pixel adjacent to the wall height edge pixel WP2A is a road pixel RP, the determination unit 3F determines that there is an intersecting road RD3, which is a road intersecting the road RD2 on which the host vehicle is traveling, at the position of the pixel other than the wall pixel adjacent to the wall height edge pixel WP2A. On the other hand, when a pixel other than the wall pixel adjacent to the wall height edge pixel WP2A is not a road pixel RP, the determination unit 3F determines that there is no intersecting road (a road intersecting the road RD1 on which the host vehicle is traveling) at the position of the pixel other than the wall pixel adjacent to the wall height edge pixel WP2A. Specifically, in the example shown in FIG. 2, since pixels other than the mural pixels adjacent to the wall high-edge pixel WP2A (for example, pixels corresponding to the portion surrounded by the circle CL in FIG. 2) are not road pixels RP, the determination unit 3F determines that there is no intersecting road (a road intersecting the road RD1 on which the host vehicle is traveling) at the position of the pixels other than the mural pixels adjacent to the wall high-edge pixel WP2A. In the example shown in FIG. 3, since pixels other than the mural pixels adjacent to the wall high-edge pixel WP2A (for example, pixels corresponding to the portion surrounded by the circle CL in FIG. 3) are road pixels RP, the determination unit 3F determines that there is an intersecting road RD3 at the position of the pixels other than the mural pixels adjacent to the wall high-edge pixel WP2A.

[0021] In the example shown in FIG. 1, when the determination unit 3F determines that there is an intersecting road RD3 at the position of the pixels other than the mural pixels adjacent to the wall high-edge pixel WP2A, the vehicle control device 16 (the driving support ECU) causes the HMI 12 to output, for example, a warning indicating that the intersecting road RD3 exists at the position of the pixels other than the mural pixels adjacent to the wall high-edge pixel WP2A (that is, in front of the traveling direction of the host vehicle 1) by display, voice, or the like based on the detection result of the intersecting road detection device 15 (the determination result of the determination unit 3F). In other examples, when the determination unit 3F determines that there is an intersecting road RD3 at the position of the pixels other than the mural pixels adjacent to the wall high-edge pixel WP2A, the vehicle control device 16 (the driving support ECU) may execute braking support and / or steering support to avoid a collision between the host vehicle 1 and another vehicle, a pedestrian, etc. that jumps out from the intersecting road RD3 onto the road RD2 on which the host vehicle is traveling.

[0022] FIG. 4 is a flowchart for explaining an example of the processing executed by the processor 153 of the intersecting road detection device 15 according to the first embodiment. In the example shown in FIG. 4, in step S10, the acquisition unit 3B acquires information indicating the road pixels RP and the mural pixels WP. In step S11, the first specifying unit 3C specifies a wall bottom pixel WP1, which is a portion of the wall pixel WP adjacent to pixels corresponding to the roads RD1 and RD2 on which the host vehicle is traveling and included in the road pixel RP, based on the road pixel RP and the wall pixel WP indicated by the information acquired in step S10. In step S12, the second specifying unit 3D specifies a wall high pixel WP2, which is a portion of the wall pixel WP that is higher than a predetermined value from the heights of the roads RD1 and RD2 on which the host vehicle is traveling, based on the road pixel RP and the wall pixel WP indicated by the information acquired in step S10. In step S13, the third specifying unit 3E specifies a wall high edge pixel WP2A, which is a portion of the wall high pixel WP2 specified in step S12 and adjacent to pixels other than the wall pixel WP, based on the road pixel RP and the wall pixel WP indicated by the information acquired in step S10.

[0023] In step S14, the determination unit 3F determines whether a pixel other than the wall pixel adjacent to the wall high edge pixel WP2A specified in step S12 is a road pixel RP. If YES, the process proceeds to step S15; if NO, the process proceeds to step S16. In step S15, the determination unit 3F determines that there is an intersecting road RD3, which is a road intersecting the road RD2 on which the host vehicle is traveling, at the position of the pixel other than the wall pixel adjacent to the wall high edge pixel WP2A specified in step S12. In step S16, the determination unit 3F determines that there is no intersecting road (a road intersecting the road RD1 on which the host vehicle is traveling) at the position of the pixel other than the wall pixel adjacent to the wall high edge pixel WP2A specified in step S12.

[0024] In the intersection road detection device 15 according to the first embodiment, in a scene where a part of the intersection road RD3 intersecting the road RD2 during the travel of the host vehicle is hidden by the wall WL3, for the front image of the host vehicle captured by the camera 11, in the processing result of image segmentation (for example, the processing result of image segmentation shown in FIG. 3), usually, the wall high-edge pixel WP2A that should not be adjacent to the road pixel RP is adjacent to the road pixel RP corresponding to the intersection road RD3 in the processing result of image segmentation when the processing result of image segmentation includes the road pixel RP corresponding to the intersection road RD3. This situation is utilized. Furthermore, in the intersection road detection device 15 according to the first embodiment, as described above, when pixels other than the wall pixels adjacent to the wall high-edge pixel WP2A are road pixels RP, it is determined that there is an intersection road RD3 intersecting the road RD2 during the travel of the host vehicle at the position of the pixels other than the wall pixels adjacent to the wall high-edge pixel WP2A. In the intersection road detection device 15 according to the first embodiment, in order to detect road pixels RP, wall pixels WP, etc. included in the front image of the host vehicle (that is, in order to detect the attributes of the pixels), for example, the "label per pixel" calculated (output) in the processing of semantic segmentation (processing in the image processing device 3A) that assigns attributes to each of a plurality of pixels included in the image is utilized.

[0025] <Second Embodiment> The host vehicle 1 to which the intersection road detection device 15 according to the second embodiment is applied is configured in the same manner as the host vehicle 1 to which the intersection road detection device 15 according to the first embodiment described above is applied, except for the points described later.

[0026] FIG. 5 is a diagram showing an example of the host vehicle 1 to which the intersection road detection device 15 according to the second embodiment is applied. As described above, in an example of the host vehicle 1 (the example shown in FIG. 1) to which the intersection road detection device 15 according to the first embodiment is applied, the processor 153 of the intersection road detection device 15 has a function as the image processing device 3A. On the other hand, in the example shown in FIG. 5, the processor 153 of the intersection road detection device 15 does not have the function as the image processing device 3A, and an image processing device 17 having the same function as the image processing device 3A is provided outside the intersection road detection device 15. That is, in the example shown in FIG. 5, the host vehicle 1 includes the image processing device 17 separately from the intersection road detection device 15.

[0027] In the example shown in FIG. 5, the camera 11 transmits the data of the host vehicle front image to the vehicle control device 16 and the image processing device 17. The image processing device 17 acquires the data of the host vehicle front image transmitted from the camera 11. Further, the image processing device 17 executes an image segmentation (identification of the subject included in the image), such as semantic segmentation, on the host vehicle front image. The acquisition unit 3B acquires information indicating the road pixel RP, the wall pixel WP, etc. from the processing result of the image segmentation executed by the image processing device 17.

[0028] <Third Embodiment> The host vehicle 1 to which the intersection road detection device 15 of the third embodiment is applied is configured in the same manner as the host vehicle 1 to which the intersection road detection device 15 of the first embodiment described above is applied, except for the points described later.

[0029] As described above, in an example of the host vehicle 1 to which the intersection road detection device 15 of the first embodiment is applied (the example shown in FIG. 1), the vehicle control device 16 is configured by the driving support ECU. On the other hand, in an example of the host vehicle 1 to which the intersection road detection device 15 of the third embodiment is applied, the vehicle control device 16 is configured by the automatic driving ECU.

[0030] In an example of the host vehicle 1 to which the intersection road detection device 15 of the first embodiment is applied as described above (the example shown in FIG. 1), when the determination unit 3F determines that an intersection road RD3 exists at a position of a pixel other than the wall pixels adjacent to the wall high-edge pixel WP2A, the vehicle control device 16 (driving support ECU) outputs, based on the detection result of the intersection road detection device 15 (the determination result of the determination unit 3F), an alarm indicating that the intersection road RD3 exists at a position of a pixel other than the wall pixels adjacent to the wall high-edge pixel WP2A (that is, in front of the traveling direction of the host vehicle 1) to the HMI 12, for example, by display, voice, or the like. On the other hand, in an example of the host vehicle 1 to which the intersection road detection device 15 of the third embodiment is applied, when the determination unit 3F determines that an intersection road RD3 exists at a position of a pixel other than the wall pixels adjacent to the wall high-edge pixel WP2A, the vehicle control device 16 (automatic driving ECU) generates a traveling plan for the host vehicle 1 to avoid a collision between the host vehicle 1 and other vehicles, pedestrians, etc. that jump out from the intersection road RD3 onto the host vehicle traveling road RD2, and controls the steering actuator 16A, the braking actuator 16B, and the driving actuator 16C based on the traveling plan.

[0031] <Fourth Embodiment> The host vehicle 1 to which the intersection road detection device 15 of the fourth embodiment is applied is configured in the same manner as the host vehicle 1 to which the intersection road detection device 15 of the second embodiment described above is applied, except for the points described later.

[0032] In an example of the host vehicle 1 to which the intersection road detection device 15 of the second embodiment is applied as described above (the example shown in FIG. 5), the vehicle control device 16 is configured by a driving support ECU. On the other hand, in an example of the host vehicle 1 to which the intersection road detection device 15 of the fourth embodiment is applied, the vehicle control device 16 is constituted by an automatic driving ECU. In an example of the host vehicle 1 to which the intersection road detection device 15 of the fourth embodiment is applied, similar to the example of the host vehicle 1 to which the intersection road detection device 15 of the third embodiment described above is applied, when the determination unit 3F determines that an intersection road RD3 exists at the position of a pixel other than the mural painting pixel adjacent to the wall high edge pixel WP2A, the vehicle control device 16 (automatic driving ECU) generates a travel plan for the host vehicle 1 to avoid a collision between the host vehicle 1 and another vehicle, a pedestrian, etc. that jumps out from the intersection road RD3 to the host vehicle traveling road RD2, and based on the travel plan, controls the steering actuator 16A, the braking actuator 16B, and the driving actuator 16C.

[0033] As described above, the embodiments of the intersection road detection device, the intersection road detection method, and the program of the present disclosure have been described with reference to the drawings. However, the intersection road detection device, the intersection road detection method, and the program of the present disclosure are not limited to the above-described embodiments, and appropriate changes can be made without departing from the spirit of the present disclosure. The configurations of the respective examples of the above-described embodiments may be appropriately combined. In each example of the above-described embodiments, the processing performed in the intersection road detection device 15 has been described as software processing performed by executing a program. However, the processing performed in the intersection road detection device 15 may be processing performed by hardware. Alternatively, the processing performed in the intersection road detection device 15 may be processing that combines both software and hardware. Further, a program stored in the memory 152 of the intersection road detection device 15 (a program that realizes the functions of the processor 153 of the intersection road detection device 15) may be recorded on a computer-readable storage medium such as a semiconductor memory, a magnetic recording medium, an optical recording medium, etc., and provided, distributed, etc.

Description of Reference Numerals

[0034] 1…Self-vehicle, 11…Camera, 12…HMI, 13…Vehicle state sensor, 14…Surrounding situation sensor, 15…Intersection road detection device, 151…Communication interface, 152…Memory, 153…Processor, 3A…Image processing device, 3B…Acquisition unit, 3C…First specifying unit, 3D…Second specifying unit, 3E…Third specifying unit, 3F…Determination unit, 16…Vehicle control device, 16A…Steering actuator, 16B…Brake actuator, 16C…Drive actuator, 17…Image processing device

Claims

1. An acquisition unit that acquires information indicating road pixels, which are pixels corresponding to a road included in the image and generated from an image captured in front of the host vehicle, and wall pixels, which are pixels corresponding to a wall included in the image; A first specifying unit that specifies, based on the road pixels and the wall pixels indicated by the information acquired by the acquisition unit, wall bottom pixels that are portions of the wall pixels adjacent to pixels corresponding to the road on which the host vehicle is traveling, which is the road included in the road pixels; A second specifying unit that specifies, based on the road pixels and the wall pixels indicated by the information acquired by the acquisition unit, wall high pixels that are portions of the wall pixels higher than a predetermined value from the height of the road on which the host vehicle is traveling; A third specifying unit that specifies, based on the road pixels and the wall pixels indicated by the information acquired by the acquisition unit, wall high edge pixels that are portions of the wall high pixels adjacent to pixels other than the wall pixels; An intersection road detection device comprising: a determination unit that determines that an intersection road, which is a road intersecting the road on which the host vehicle is traveling, exists at the position of a pixel other than the wall pixel when the pixel other than the wall pixel adjacent to the wall high edge pixel is the road pixel.

2. The intersection road detection device according to claim 1, wherein the determination unit determines that the intersection road does not exist at the position of the pixel other than the wall pixel when the pixel other than the wall pixel adjacent to the wall high edge pixel is not the road pixel.

3. An acquisition step in which an intersection road detection device acquires information indicating road pixels, which are pixels corresponding to a road included in the image and generated from an image captured in front of the host vehicle, and wall pixels, which are pixels corresponding to a wall included in the image; A first specifying step in which the intersection road detection device specifies, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step, wall bottom pixels that are portions of the wall pixels adjacent to pixels corresponding to the road on which the host vehicle is traveling, which is the road included in the road pixels; A second specifying step in which the intersection road detection device specifies, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step, wall high pixels that are portions of the wall pixels higher than a predetermined value from the height of the road on which the host vehicle is traveling; A third specifying step of specifying, by the intersection road detection device, wall height edge pixels that are portions of the wall height pixels other than the wall pixels and adjacent to pixels other than the wall pixels, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step; A determination step of determining that an intersection road, which is a road intersecting the road on which the host vehicle is traveling, exists at the position of the pixel other than the wall pixel when the pixel other than the wall pixel adjacent to the wall height edge pixel is the road pixel. An intersection road detection method comprising: **Claim 4** In a processor, An acquisition step of acquiring information indicating a road pixel, which is a pixel corresponding to a road included in the image and generated from an image obtained by photographing the front of the host vehicle, and a wall pixel, which is a pixel corresponding to a wall included in the image; A first specifying step of specifying, by the intersection road detection device, wall bottom pixels that are portions of the wall pixels adjacent to pixels corresponding to the road on which the host vehicle is traveling and included in the road pixels, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step; A second specifying step of specifying, by the intersection road detection device, wall height pixels that are portions of the wall pixels higher than a predetermined value from the height of the road on which the host vehicle is traveling, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step; A third specifying step of specifying, by the intersection road detection device, wall height edge pixels that are portions of the wall height pixels other than the wall pixels and adjacent to pixels other than the wall pixels, based on the road pixels and the wall pixels indicated by the information acquired in the acquisition step; A program for causing the processor to execute a determination step of determining that an intersection road, which is a road intersecting the road on which the host vehicle is traveling, exists at the position of the pixel other than the wall pixel when the pixel other than the wall pixel adjacent to the wall height edge pixel is the road pixel.

Images