Lane determination device, lane determination direction, and lane determination computer program

Abstract

To provide a lane determination device capable of determining the lane in which other vehicles travel there around even when lane markings are difficult to detect from images generated by an imaging unit mounted on a vehicle.SOLUTION: In the lane determination device, a processor includes: a detection unit 31 that detects the other vehicle area where other vehicles are running around a vehicle and are represented from images representing the surroundings of the vehicle generated by an imaging unit mounted on the vehicle; and a determination unit 32 that is configured so as to, if the other vehicle area touches either the left or right edge of the image and, if the position of the bottom edge of the other vehicle area is included in the specified range in the vertical direction of the image, determine the other vehicle is traveling in the lane adjacent to the lane the vehicle is traveling.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a lane determination device that determines the lane in which other vehicles around a vehicle are traveling, a lane determination direction, and a lane determination computer program. [Background technology]

[0002] In order to control the automatic driving of a vehicle or to assist the driver of the vehicle, it is desirable to be able to accurately detect the positional relationship between the vehicle and other vehicles around it. Therefore, a technology for detecting the lane in which a preceding vehicle is traveling has been proposed (see Patent Document 1).

[0003] The vehicle obstacle detection device disclosed in Patent Document 1 detects a preceding vehicle from two images generated by a stereo camera, detects a white line from one of the two images, and determines the driving lane of the preceding vehicle based on the positional relationship between the detection area of ​​the preceding vehicle and the white line. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 11-153406 Summary of the Invention [Problem to be solved by the invention]

[0005] In the above technology, the lane in which the preceding vehicle is traveling is determined based on its position relative to white lines on the road. However, depending on the road surface conditions or the conditions around the vehicle, it may be difficult to detect lane markings from images generated by an on-board camera. For example, lane markings may be blurred or difficult to see in an image due to a wet road surface, or may be obscured by an object other than the target vehicle, making it difficult to detect the lane markings. Therefore, it is preferable to be able to determine the lane in which other vehicles around the vehicle are traveling even when lane markings cannot be detected from an image.

[0006] Therefore, an object of the present invention is to provide a lane determination device that can determine the lane in which other vehicles around the vehicle are traveling, even when it is difficult to detect lane markings from an image generated by an imaging unit installed in the vehicle. [Means for solving the problem]

[0007] According to one embodiment, there is provided a lane determination device that includes a detection unit that detects an other vehicle area showing another vehicle traveling around the vehicle from an image showing the surroundings of the vehicle generated by an imaging unit mounted on the vehicle, and a determination unit that determines that the other vehicle is traveling in a lane adjacent to the lane in which the vehicle is traveling if the other vehicle area is in contact with either the left or right edge of the image and the position of the bottom edge of the other vehicle area is within a predetermined range in the vertical direction of the image.

[0008] In this lane determining device, the predetermined range is preferably a range in the vertical direction in which adjacent lanes are displayed on the image in a direction corresponding to the horizontal angle of view of the imaging unit.

[0009] Furthermore, it is preferable that the determination unit widens the predetermined range as the width of the lane on the road on which the vehicle is traveling increases.

[0010] According to another embodiment, there is provided a lane determination method including: detecting an other vehicle area representing another vehicle traveling around the vehicle from an image representing the surroundings of the vehicle generated by an imaging unit mounted on the vehicle; and determining that the other vehicle is traveling in a lane adjacent to the lane in which the vehicle is traveling if the other vehicle area abuts on either the left or right edge of the image and the position of the bottom edge of the other vehicle area is within a predetermined range in the up-down direction of the image.

[0011] According to yet another embodiment, there is provided a lane determination computer program, the lane determination computer program including instructions for causing a processor mounted on the vehicle to execute the following: detect an other vehicle area representing another vehicle traveling around the vehicle from an image representing the surroundings of the vehicle generated by an imaging unit mounted on the vehicle, and determine that the other vehicle is traveling in a lane adjacent to the lane in which the vehicle is traveling if the other vehicle area abuts on either the left or right edge of the image and the position of the bottom edge of the other vehicle area is within a predetermined range in the up-down direction of the image. [Effects of the Invention]

[0012] The lane determination device according to the present disclosure has the advantage of being able to determine the lane in which other vehicles around the vehicle are traveling, even when it is difficult to detect lane markings from an image generated by an imaging unit mounted on the vehicle. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a schematic configuration diagram of a vehicle control system in which a lane determination device is implemented. [Figure 2] 1 is a hardware configuration diagram of an electronic control device that is an embodiment of a lane determination device. [Figure 3] FIG. 2 is a functional block diagram of a processor of an electronic control unit related to vehicle control processing including lane determination processing. [Figure 4] 1 is a diagram showing an example of the relationship between the field of view of an in-vehicle camera, the position of another vehicle, and the area of ​​the other vehicle on the image. FIG. [Figure 5]10 is an operational flowchart of a vehicle control process including a lane determination process. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, a lane determination device, a lane determination method, and a lane determination computer program executed by the lane determination device will be described with reference to the drawings. The lane determination device detects an area representing another vehicle traveling around the vehicle from an image representing the vehicle's surroundings generated by an imaging unit mounted on the vehicle. The lane determination device then determines that the other vehicle is traveling in a lane adjacent to the host vehicle's lane if the area representing the other vehicle is adjacent to either the left or right edge of the image and the position of the bottom edge of the other vehicle area is within a predetermined range in the vertical direction of the image. Hereinafter, the area representing the other vehicle on the image may be referred to as the other vehicle area. Furthermore, the lane adjacent to the host vehicle's lane may be simply referred to as the adjacent lane. Furthermore, the vehicle in which the lane determination device is implemented may be referred to as the host vehicle.

[0015] An example in which the lane determination device is applied to a vehicle control system will be described below. In this example, the lane determination device performs lane determination processing on an image acquired by a camera mounted on the host vehicle to detect other vehicles traveling around the host vehicle and determine whether the other vehicles are traveling in an adjacent lane. The determination result is then used for driving control of the host vehicle.

[0016] FIG. 1 is a schematic configuration diagram of a vehicle control system in which a lane determination device is implemented. FIG. 2 is a hardware configuration diagram of an electronic control unit, which is an example of a lane determination device. In this embodiment, the vehicle control system 1 is mounted on a vehicle 10 (i.e., the vehicle itself) and controls the vehicle 10. The vehicle control system 1 includes a camera 2 for capturing images of the surroundings of the vehicle 10 and an electronic control unit (ECU) 3, which is an example of a lane determination device. The camera 2 and the ECU 3 are communicably connected via an in-vehicle network conforming to a standard such as a controller area network. The vehicle control system 1 may further include a storage device (not shown) that stores high-precision maps representing information used for autonomous driving control, such as lane widths, speed limits, and the positions and types of road markings and road signs, such as lane markings, for each section of the road. The vehicle control system 1 may also include a ranging sensor (not shown) such as a LiDAR or radar. The vehicle control system 1 may also include a receiver (not shown) such as a GPS receiver for determining the vehicle's own position in accordance with a satellite positioning system. Furthermore, the vehicle control system 1 may also include a navigation device (not shown) for searching for a planned travel route for the vehicle 10.

[0017] Camera 2 is an example of an imaging unit, and includes a two-dimensional detector configured with an array of photoelectric conversion elements, such as a CCD or C-MOS, that are sensitive to visible light, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. Camera 2 is mounted, for example, inside the passenger compartment of vehicle 10 so as to face forward of vehicle 10. Camera 2 photographs the area ahead of vehicle 10 at predetermined photographing intervals (for example, 1 / 30 to 1 / 10 seconds) and generates an image of the area ahead. The image obtained by camera 2 may be a color image or a grayscale image.

[0018] Every time the camera 2 generates an image, it outputs the generated image and the time of photographing (that is, the time of generation of the image) to the ECU 3 via the in-vehicle network.

[0019] The ECU 3 controls the vehicle 10. In this embodiment, the ECU 3 determines whether another vehicle detected from a time-series series of images acquired by the camera 2 is traveling in an adjacent lane, and controls the vehicle 10 to automatically drive the vehicle 10 based on the determination result. To this end, the ECU 3 has a communication interface 21, a memory 22, and a processor 23.

[0020] The communication interface 21 is an example of a communication unit, and has an interface circuit for connecting the ECU 3 to an in-vehicle network. That is, the communication interface 21 is connected to the camera 2 via the in-vehicle network. Every time the communication interface 21 receives an image from the camera 2, it passes the received image to the processor 23.

[0021] The memory 22 is an example of a storage unit and includes, for example, a volatile semiconductor memory and a nonvolatile semiconductor memory. The memory 22 stores various data used in the lane determination process executed by the processor 23 of the ECU 3. The memory 22 stores, as such data, parameters representing information about the camera 2, such as the focal length, shooting direction, and installation height of the camera 2, as well as various parameters for identifying a classifier used to detect other vehicles. The memory 22 also stores various information used in the lane determination of other vehicles. Such information includes a predetermined range in the vertical direction of the image that is compared with the position of the bottom edge of the other vehicle area. The memory 22 also stores, for a certain period of time, various data obtained or generated during the lane determination process, such as a series of images acquired during a recent predetermined period and the other vehicle area in each of the series of images. The memory 22 may also store information used for driving control of the vehicle 10, such as a high-precision map.

[0022] The processor 23 is an example of a control unit and includes one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may further include other arithmetic circuits such as a logic operation unit, a numerical operation unit, or a graphics processing unit. The processor 23 executes vehicle control processing, including lane determination processing, on received images at predetermined intervals while the vehicle 10 is traveling.

[0023] 3 is a functional block diagram of the processor 23 of the ECU 3, which is related to vehicle control processing including lane determination processing. The processor 23 includes a detection unit 31, a determination unit 32, and a vehicle control unit 33. Each of these units included in the processor 23 is a functional module implemented by, for example, a computer program running on the processor 23. Alternatively, each of these units included in the processor 23 may be a dedicated arithmetic circuit provided in the processor 23. Of these units included in the processor 23, the detection unit 31 and the determination unit 32 execute the lane determination processing. Note that if multiple cameras are provided on the vehicle 10, the processor 23 may execute the lane determination processing for each camera based on images acquired by that camera.

[0024] The detection unit 31 inputs the latest image it has received into the classifier at predetermined intervals, thereby detecting an other vehicle area in which another vehicle is depicted in the image.

[0025] The detection unit 31 may use, as such a classifier, a deep neural network (DNN) having a convolutional neural network (CNN)-type architecture, such as a Single Shot MultiBox Detector (SSD) or Faster R-CNN. Alternatively, the detection unit 31 may use, as such a classifier, a DNN having a self-attention network (SAN)-type architecture, such as a Vision Transformer. Alternatively, the detection unit 31 may use, as such a classifier, a classifier based on another machine learning method, such as an AdaBoost classifier. Such a classifier is trained in advance to detect other vehicles from images according to a predetermined learning method, such as backpropagation, using a large number of training images depicting vehicles.

[0026] The classifier may be trained in advance to further detect objects that affect the traveling of the vehicle 10, such as road markings such as lane markings or stop lines, road signs, and pedestrians. In this case, the detection unit 31 can input an image to the classifier to detect not only other vehicle areas but also object areas in which these objects are represented from the image.

[0027] The detection unit 31 notifies the determination unit 32 and the vehicle control unit 33 of information indicating the position and range of each detected other vehicle area on the image, and stores the information in the memory 22. Furthermore, if an object area showing a road marking or the like is detected, the detection unit 31 notifies the vehicle control unit 33 of information indicating the position and range of each detected object area on the image and the type of object shown in the object area.

[0028] The determination unit 32 determines whether each detected other vehicle area is adjacent to either the left or right edge of the image. If the lower end of the other vehicle area is within a predetermined range in the vertical direction of the image, the determination unit 32 determines that the other vehicle represented in the other vehicle area is traveling in an adjacent lane. If the lower end of the other vehicle area is above the upper limit of the predetermined range, the determination unit 32 determines that the other vehicle represented in the other vehicle area is traveling in a lane farther from the own lane than the adjacent lane. Conversely, if the lower end of the other vehicle area is below the lower limit of the predetermined range, the determination unit 32 does not determine the lane in which the other vehicle represented in the other vehicle area is traveling at that time. Alternatively, the determination unit 32 may determine the lane in which the other vehicle represented in the other vehicle area is traveling using another method. The predetermined range is a range in the vertical direction in which the adjacent lanes are displayed on the image in the direction corresponding to the horizontal angle of view of the camera 2.

[0029] There is a one-to-one correspondence between each pixel on the image and the orientation as seen from the camera 2 that generates the image. Therefore, as long as the other vehicle area is adjacent to either the left or right edge of the image, the horizontal orientation of the other vehicle as seen from the camera 2 is approximately constant, at an orientation corresponding to the horizontal angle of view of the camera 2. As described above, the installation height and shooting direction of the camera 2 are pre-stored in the memory 22 and are known. Furthermore, it is estimated that the bottom edge of the other vehicle area represents the position where the other vehicle is in contact with the road surface. Therefore, the determination unit 32 can estimate the distance from the camera 2 to the other vehicle based on the position of the bottom edge of the other vehicle area on the image. In other words, the closer the position of the bottom edge of the other vehicle area is to the bottom edge of the image, the closer the other vehicle is to the vehicle 10. Furthermore, the vehicle 10 usually travels along the center line of its own lane, and it is assumed that the distance from the vehicle 10 to adjacent lanes does not change significantly. Therefore, the determination unit 32 can determine whether or not another vehicle is traveling in an adjacent lane based on whether or not the position of the bottom edge of the other vehicle area when the other vehicle area is in contact with either the left or right edge of the image is included in a specified range.

[0030] FIG. 4 is a diagram showing an example of the relationship between the field of view of an on-board camera, the position of another vehicle, and the other vehicle area on an image. FIG. 4 illustrates a case in which another vehicle 410 is traveling in an adjacent lane 402 to the left of the own lane 401 in which the vehicle 10 is traveling, and a case in which the other vehicle 410 is traveling in an adjacent lane 403 to the left of the adjacent lane 402. Furthermore, FIG. 4 illustrates that the other vehicle 410 is traveling at a position along the left edge 411 of the field of view of the camera 2 mounted on the vehicle 10. Therefore, when the other vehicle 410 is traveling in the adjacent lane 402, the other vehicle area 421 on the image 420 generated by the camera 2 is adjacent to the left edge of the image 420. Similarly, when the other vehicle 410 is traveling in the lane 403, the other vehicle area 431 on the image 430 generated by the camera 2 is also adjacent to the left edge of the image 430. 4, the direction of the other vehicle 410 as seen from the vehicle 10 is constant regardless of the lane in which the other vehicle 410 is traveling. Therefore, when the other vehicle 410 is traveling in the adjacent lane 402, the distance d1 from the vehicle 10 to the other vehicle 410 is shorter than the distance d2 from the vehicle 10 to the other vehicle 410 when the other vehicle 410 is traveling in the lane 403. Therefore, the position of the bottom edge of the other vehicle area 421 on the image 420 is lower than the position of the bottom edge of the other vehicle area 431 on the image 430. In this way, the distance between the vehicle 10 and the other vehicle 410 changes depending on the lane in which the other vehicle 410 is traveling, and therefore the position of the bottom edge of the other vehicle area on the image changes. Therefore, the determination unit 32 can determine whether the other vehicle 410 is traveling in the adjacent lane 402 based on whether the position of the lower end of the other vehicle area is included in a predetermined range 440 in the vertical direction in which the adjacent lane is represented on the image in the orientation corresponding to the horizontal angle of view of the camera 2.

[0031] Note that, if the other vehicle area does not border either the left or right edge of the image, the determination unit 32 may determine the lane in which the other vehicle depicted in the other vehicle area is traveling using another method. For example, if lane markings are detected from the image, the determination unit 32 may determine the lane in which the other vehicle depicted in the other vehicle area is traveling based on the positional relationship between the other vehicle area and the lane markings. Furthermore, as described above, the position of the bottom edge of the other vehicle area on the image is estimated to represent the position where the other vehicle depicted in the other vehicle area borders the road surface. Therefore, the determination unit 32 estimates the distance from the vehicle 10 to the other vehicle based on parameters such as the position of the bottom edge of the other vehicle area on the image and the shooting direction of the camera 2. Furthermore, the determination unit 32 estimates the lateral distance between the vehicle 10 and the other vehicle in a direction perpendicular to the extension direction of the own lane based on the estimated value of the distance from the vehicle 10 to the other vehicle, the orientation from the camera 2 corresponding to the center position of the other vehicle area on the image, and the traveling direction of the vehicle 10. The determination unit 32 may then determine the lane in which the other vehicle is traveling based on the lateral distance in lane width units obtained by dividing the estimated lateral distance by the width of the lane at the current position of the vehicle 10. That is, if the lateral distance in lane width units is less than 1, the determination unit 32 determines that the other vehicle is traveling in the same lane, and if the lateral distance in lane width units is between 1 and 2, the determination unit 32 determines that the other vehicle is traveling in an adjacent lane. Furthermore, if the lateral distance in lane width units is greater than 2, the determination unit 32 can determine that the other vehicle is traveling in a lane that is farther away from the same lane than the adjacent lane. Note that the determination unit 32 may determine the position indicated by the latest positioning information received by the ECU 3 from a GPS receiver (not shown) as the current position of the vehicle 10. The determination unit 32 may also refer to a high-precision map to identify the width of the lane at the current position of the vehicle 10.

[0032] The determination unit 32 notifies the vehicle control unit 33 of the determination result of the lane in which the other vehicle shown in each other vehicle area is traveling, for each other vehicle area.

[0033] The vehicle control unit 33 performs automatic driving control of the vehicle 10 using the determination result of the lane in which each of the other vehicles traveling around the vehicle 10 is traveling.

[0034] For example, if there is another vehicle traveling ahead of vehicle 10 in the own lane, vehicle control unit 33 controls the speed of vehicle 10 so that the distance between vehicle 10 and the other vehicle is maintained at or above a predetermined distance. As described for determination unit 32, vehicle control unit 33 may estimate the distance between vehicle 10 and the other vehicle based on the position of the bottom edge of the other vehicle area in which the other vehicle traveling in the own lane is displayed. Alternatively, if vehicle 10 is equipped with a distance measurement sensor (not shown), vehicle control unit 33 may use the distance measured by the distance measurement sensor in a direction corresponding to the center of the other vehicle area in which the other vehicle traveling in the own lane is displayed as the distance between vehicle 10 and the other vehicle.

[0035] The vehicle control unit 33 may also identify a destination lane leading to the destination indicated in the planned driving route received by the ECU 3 from a navigation device (not shown). If the destination lane is an adjacent lane to the vehicle's own lane, the vehicle control unit 33 causes the vehicle 10 to change lanes to the adjacent lane. At this time, if the determination unit 32 determines that another vehicle is traveling in the adjacent lane to which the vehicle 10 is to change lanes, the vehicle control unit 33 sets a planned driving trajectory for the vehicle 10 so that the distance between the other vehicle and the vehicle 10 is maintained at a predetermined distance or greater. The vehicle control unit 33 then controls each unit of the vehicle 10 so that the vehicle 10 travels along the planned driving trajectory. The vehicle control unit 33 may identify the vehicle's own lane in which the vehicle 10 is traveling based on the high-precision map and the image generated by the camera 2. For example, the vehicle control unit 33 projects features such as road markings detected from the image by the detection unit 31 onto the high-precision map while assuming the position and traveling direction of the vehicle 10, thereby determining the degree of match between the detected features and the corresponding features depicted on the high-precision map. The vehicle control unit 33 repeats the above process while varying the assumed position and traveling direction of the vehicle 10 in various ways, thereby identifying the position and traveling direction of the vehicle 10 that maximizes the degree of match. The vehicle control unit 33 then estimates the assumed position and traveling direction of the vehicle 10 that maximizes the degree of match as the actual position and traveling direction of the vehicle 10. Furthermore, the vehicle control unit 33 refers to the high-precision map and identifies the lane that includes the estimated position of the vehicle 10 as the vehicle's own lane.

[0036] Alternatively, if the determination unit 32 determines that another vehicle is traveling in an adjacent lane to which the vehicle is about to change lanes, the vehicle control unit 33 may predict whether the other vehicle will change lanes into the vehicle's own lane. In this case, the vehicle control unit 33 tracks the other vehicle traveling in the adjacent lane by applying a predetermined tracking method, such as the KLT algorithm, to a time-series series of images captured by the camera 2 over a recent predetermined period. That is, the vehicle control unit 33 associates other vehicle areas depicting the same other vehicle in each of the series of images. The vehicle control unit 33 then identifies the turn signal status of the other vehicle by inputting the other vehicle areas depicting the same other vehicle in each of the series of images in chronological order into a classifier that has been trained in advance to identify the turn signal status. The vehicle control unit 33 then predicts that the other vehicle will change lanes into the vehicle's own lane if the turn signal status of the other vehicle is flashing on the side of the vehicle's own lane. The vehicle control unit 33 can use, for example, a recurrent neural network as such a classifier. When the vehicle control unit 33 predicts that another vehicle traveling in an adjacent lane will change lanes into the vehicle's own lane, it controls each part of the vehicle 10 so that the distance between the vehicle 10 and the other vehicle is maintained at or above a predetermined distance.

[0037] Furthermore, when an obstacle such as a pedestrian is detected from the image, the vehicle control unit 33 controls each part of the vehicle 10 so that the vehicle 10 does not collide with the obstacle.

[0038] 5 is an operational flowchart of a vehicle control process including a lane determination process. The processor 23 may execute the vehicle control process in accordance with the following operational flowchart at predetermined intervals. In the operational flowchart below, the processes of steps S101 to S105 correspond to the lane determination process according to this embodiment.

[0039] The detection unit 31 of the processor 23 detects one or more other vehicle areas from the latest image generated by the camera 2 (step S101). The determination unit 32 of the processor 23 selects, from each other vehicle area, an other vehicle area that is adjacent to either the left or right edge of the image (step S102). Then, for the selected other vehicle area, the determination unit 32 determines whether the position of the bottom edge of the other vehicle area on the image is included in a predetermined range in the vertical direction of the image (step S103). If the position of the bottom edge is included in the predetermined range (step S103—Yes), the determination unit 32 determines that the other vehicle represented in the other vehicle area is traveling in an adjacent lane (step S104). On the other hand, if the position of the bottom edge is outside the predetermined range (step S103—No), the determination unit 32 determines that the other vehicle represented in the other vehicle area is traveling in a lane other than the adjacent lane (step S105). If a plurality of other vehicle areas are selected, the determination unit 32 may execute the processes of steps S103 to S105 for each of the selected other vehicle areas.

[0040] Furthermore, for other vehicles displayed in the other vehicle area that have not been selected, the determination unit 32 determines the lane in which the other vehicles are traveling using another method (step S106).

[0041] After steps S104 to S106, the vehicle control unit 33 of the processor 23 performs automatic driving control of the vehicle 10 using the determination results of the lanes in which each of the other vehicles traveling around the vehicle 10 is traveling (step S107). Then, the processor 23 ends the vehicle control process.

[0042] As described above, this lane determination device detects other vehicle areas from an image showing the surroundings of a vehicle. If the other vehicle area is adjacent to either the left or right edge of the image and the position of the bottom edge of the other vehicle area is within a predetermined range in the vertical direction of the image, this lane determination device determines that the other vehicle is traveling in a lane adjacent to the lane in which the vehicle is traveling. In this way, this lane determination device can determine whether the other vehicle is traveling in an adjacent lane without detecting lane markings. Therefore, this lane determination device can determine the lane in which the other vehicle around the vehicle is traveling, even if it is difficult to detect lane markings from an image generated by an imaging unit installed in the vehicle.

[0043] According to a modified example, the camera 2 may be mounted so as to face rearward from the vehicle 10. In this case, the lane determination device can also determine whether another vehicle is traveling in an adjacent lane based on the image generated by the camera 2, as in the above embodiment.

[0044] The predetermined range in the vertical direction of the image may also be adjusted according to the width of the lane on the road on which the vehicle 10 is currently traveling. In this case, as described above, the determination unit 32 identifies the width of the lane by referring to the current position of the vehicle 10, which is represented by the latest positioning information generated by the GPS receiver, and the high-precision map. The determination unit 32 then increases the predetermined width as the identified lane width increases. Furthermore, since it is estimated that the distance from the vehicle 10 to an adjacent lane increases as the identified lane width increases, the determination unit 32 may increase the lower limit of the predetermined width as the identified lane width increases. By adjusting the predetermined range according to the lane width in this way, the determination unit 32 can more accurately determine whether another vehicle is traveling in the adjacent lane.

[0045] A computer program that realizes the functions of each part of the processor 23 of the lane determination device according to the above embodiment or modified example may be provided in a form recorded on a computer-readable portable recording medium such as a semiconductor memory, a magnetic recording medium, or an optical recording medium.

[0046] As described above, those skilled in the art can make various modifications to the embodiments within the scope of the present invention. [Explanation of symbols]

[0047] 1. Vehicle control system 2 Cameras 3 Electronic control unit (lane determination device) 21 Communication Interface 22 Memory 23 processors 31 Detection unit 32 Judgment section 33 Vehicle control unit

Claims

1. a detection unit that is mounted on a vehicle and detects an other vehicle area showing other vehicles traveling around the vehicle from an image showing an area in front of the vehicle or an area behind the vehicle, the image being generated by a camera attached to face the front or rear of the vehicle; if the other vehicle area is in contact with either the left or right edge of the image and the position of the bottom edge of the other vehicle area is included in a range in the up-down direction in which an adjacent lane to the own vehicle lane in which the vehicle is traveling is represented on the image in an orientation corresponding to the horizontal angle of view of the camera, it is determined that the other vehicle is traveling in the adjacent lane; a determination unit that determines that the other vehicle is traveling in a lane farther from the own vehicle lane than the adjacent lane when the other vehicle area is in contact with either the left or right end of the image and the position of the lower end of the other vehicle area is above the upper limit of the range; and A lane determination device having the following.

2. The vehicle further includes a memory unit that stores map information representing the width of lanes in each section of a road, 2. The lane determination device according to claim 1, wherein the determination unit identifies a lane width in a section of a road on which the vehicle is traveling by referring to the map information and the position of the vehicle measured by a positioning device mounted on the vehicle, and the wider the identified lane width, the wider the range is set.

3. Detecting an other vehicle area showing other vehicles traveling around the vehicle from an image showing an area in front of the vehicle or an area behind the vehicle, the image being generated by a camera mounted on the vehicle and facing forward or backward of the vehicle; if the other vehicle area is in contact with either the left or right edge of the image, and the position of the bottom edge of the other vehicle area is included in a range in the up-down direction in which an adjacent lane to the lane in which the vehicle is traveling is represented on the image in an orientation corresponding to the horizontal angle of view of the camera, it is determined that the other vehicle is traveling in a lane adjacent to the lane in which the vehicle is traveling; If the other vehicle area is in contact with either the left or right edge of the image and the position of the lower edge of the other vehicle area is above the upper limit of the range, it is determined that the other vehicle is traveling in a lane farther from the own vehicle lane than the adjacent lane. A lane determination method including:

4. Detecting an other vehicle area showing other vehicles traveling around the vehicle from an image showing an area in front of the vehicle or an area behind the vehicle, the image being generated by a camera mounted on the vehicle and facing forward or backward of the vehicle; if the other vehicle area is in contact with either the left or right edge of the image, and the position of the bottom edge of the other vehicle area is included in a range in the up-down direction in which an adjacent lane to the lane in which the vehicle is traveling is represented on the image in an orientation corresponding to the horizontal angle of view of the camera, it is determined that the other vehicle is traveling in a lane adjacent to the lane in which the vehicle is traveling; If the other vehicle area is in contact with either the left or right edge of the image and the position of the lower edge of the other vehicle area is above the upper limit of the range, it is determined that the other vehicle is traveling in a lane farther from the own vehicle lane than the adjacent lane. A computer program for lane determination that causes a processor mounted on the vehicle to execute the above.

Images