Object recognition device, object recognition method and storage medium

Abstract

The present invention provides an object recognition device, an object recognition method, and a storage medium that can obtain information related to an object with high importance among objects located around a vehicle without omission in a short time. The object recognition device of the embodiment comprises: a setting unit that sets a high-resolution area to be processed at a higher resolution than other areas in a first image obtained by photographing the surroundings of a vehicle based on the surrounding information of the vehicle; and a recognition unit that recognizes an object located around the vehicle by processing an image corresponding to the set high-resolution area at a high resolution.

Description

Technical Field

[0001] The invention relates to an object recognition device, an object recognition method and a storage medium. Background Art

[0002] Conventionally, there is known a technology for controlling a vehicle by acquiring information on a road or the like based on an image captured by an onboard camera (for example, refer to Japanese Patent Application Publication No. 2012-252501 and Japanese Patent No. 6412934). Summary of the invention

[0003] Problems to be solved by the invention

[0004] In the past, in order to obtain accurate information about roads, etc., it was necessary to capture images at high resolution and perform image processing. However, since it takes time to process high-resolution images, it may affect subsequent vehicle control, etc. On the other hand, if the range of high-resolution images is excessively limited in order to shorten the processing time, it is possible that important information that is originally necessary will be lost.

[0005] The present invention has been completed in consideration of such a situation, and one of its purposes is to provide an object recognition device, an object recognition method, and a storage medium that can obtain information related to highly important objects among objects located around a vehicle without omission in a short time.

[0006] Solutions to Solve Problems

[0007] The object recognition device, object recognition method, and storage medium of the present invention adopt the following structure.

[0008] (1) An object recognition device according to one embodiment of the present invention comprises: a setting unit which sets a high-resolution area setting unit for processing a first image obtained by photographing the periphery of a vehicle at a higher resolution than other areas in the first image based on the periphery information of the vehicle; and a recognition unit which recognizes an object located in the periphery of the vehicle by processing an image corresponding to the set high-resolution area at a high resolution.

[0009] According to a second aspect, in the object recognition device according to the first aspect, the recognition unit recognizes the object by processing the image of the high-resolution region in the first image at a high resolution.

[0010] The scheme (3) is based on the object recognition device of the above-mentioned scheme (1), and the recognition unit recognizes the object by processing a second image with high resolution, and the second image is an image obtained by photographing the area around the vehicle corresponding to the high-resolution area with high resolution.

[0011] According to a fourth aspect of the present invention, based on the object recognition device of any one of the above-mentioned aspects (1) to (3), the setting unit sets a region including another vehicle in the first image as the high-resolution region, and the recognition unit recognizes the other vehicle.

[0012] According to a fifth aspect, in the object recognition device according to the fourth aspect, the setting unit determines an area including the other vehicle by performing image analysis on the first image, and sets the determined area as the high-resolution area.

[0013] According to scheme (6), based on the object recognition device of scheme (4) or (5) above, the recognition unit recognizes the action state of the other vehicle based on the image of the lighting part of the other vehicle contained in the image corresponding to the high-resolution area.

[0014] According to the scheme (7), based on the object recognition device of any one of the schemes (4) to (6) above, when the first image contains a first other vehicle traveling in a lane in the same direction as the vehicle, the setting unit sets an area at least including the rear portion of the first other vehicle as the high-resolution area; and when the first image contains a second other vehicle traveling in a lane opposite to the lane in which the vehicle is traveling, the setting unit sets an area at least including the front portion of the second other vehicle as the high-resolution area.

[0015] According to scheme (8), based on the object recognition device of any one of schemes (1) to (7) above, the setting unit sets a region including a traffic structure in the first image as the high-resolution region, and the recognition unit recognizes the traffic structure.

[0016] According to the embodiment (9), based on the object recognition device according to the embodiment (8), the setting unit determines an area including the traffic structure by performing image analysis on the first image, and sets the determined area as the high-resolution area.

[0017] According to scheme (10), based on the object recognition device of scheme (8) or (9) above, the setting unit uses pre-stored map information containing road information to determine the area containing the traffic structure, and sets the determined area as the high-resolution area.

[0018] (11) Another embodiment of the object recognition method of the present invention enables a computer mounted on a vehicle to perform the following processing: for a first image obtained by photographing the periphery of the vehicle, based on the periphery information of the vehicle, setting a high-resolution area to be processed at a higher resolution than other areas in the first image; and identifying objects located in the periphery of the vehicle by processing the image corresponding to the set high-resolution area at the high resolution.

[0019] (12) A storage medium of another embodiment of the present invention stores a program, which enables a computer installed in a vehicle to perform the following processing: for a first image obtained by photographing the periphery of the vehicle, setting a high-resolution area to be processed at a higher resolution than other areas in the first image based on the periphery information of the vehicle; and identifying objects located in the periphery of the vehicle by processing the image corresponding to the set high-resolution area at the high resolution.

[0020] Effects of the Invention

[0021] According to the above schemes (1) to (12), by setting the high-resolution area based on the surrounding information of the vehicle, the area of ​​the high-resolution image acquisition target can be changed, and the high-resolution image acquisition area can be limited to a necessary range and acquired. As a result, information related to important objects among the objects located in the surrounding area of ​​the vehicle can be acquired in a short time without omission.

[0022] According to the above aspects (4) to (7), it is possible to obtain information on other highly important vehicles located around the vehicle without omission in a short time.

[0023] According to the above aspects (8) to (10), it is possible to obtain information on important traffic structures located around the vehicle without omission in a short time. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a configuration diagram of a vehicle system using the object recognition device according to the embodiment.

[0025] Figure 2 It is a functional configuration diagram of the first control unit and the second control unit in the embodiment.

[0026] Figure 3 This is a flowchart showing an example of object recognition processing performed by the recognition unit of the automatic driving control device according to the embodiment.

[0027] Figure 4A This is a diagram for explaining an example of a case where a high-resolution area is set based on the presence of another vehicle according to the embodiment.

[0028] Figure 4B This is a diagram for explaining an example of a case where a high-resolution area is set based on the presence of another vehicle according to the embodiment.

[0029] Figure 4C This is a diagram for explaining an example of a case where a high-resolution area is set based on the presence of another vehicle according to the embodiment.

[0030] Figure 4D This is a diagram for explaining an example of a case where a high-resolution area is set based on the presence of another vehicle according to the embodiment.

[0031] Figure 5A This is a diagram for explaining an example of setting a high-resolution area based on the presence of a traffic structure according to an embodiment.

[0032] Figure 5B This is a diagram for explaining an example of setting a high-resolution area based on the presence of a traffic structure according to an embodiment.

[0033] Figure 5C This is a diagram for explaining an example of setting a high-resolution area based on the presence of a traffic structure according to an embodiment.

[0034] Fig. 6A This is a diagram for explaining an example of setting a high-resolution area based on the curvature of a road according to an embodiment.

[0035] Figure 6B This is a diagram for explaining an example of setting a high-resolution area based on the curvature of a road according to an embodiment.

[0036] Figure 6C This is a diagram for explaining an example of setting a high-resolution area based on the curvature of a road according to an embodiment.

[0037] Fig. 7A This is a diagram for explaining an example of setting a high-resolution area based on the vehicle speed according to the embodiment.

[0038] Figure 7B This is a diagram for explaining an example of setting a high-resolution area based on the vehicle speed according to the embodiment.

[0039] Figure 7C This is a diagram for explaining an example of setting a high-resolution area based on the vehicle speed according to the embodiment. DETAILED DESCRIPTION

[0040] Hereinafter, embodiments of an object recognition device, an object recognition method, and a storage medium according to the present invention will be described with reference to the accompanying drawings.

[0041] [Overall structure]

[0042] Figure 11 is a structural diagram of a vehicle system using an object recognition device according to an embodiment. The vehicle equipped with the vehicle system 1 is, for example, a two-wheeled, three-wheeled, or four-wheeled vehicle, and its driving source is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination thereof. The electric motor operates using the power generated by a generator connected to the internal combustion engine or the power discharged by a secondary battery or a fuel cell.

[0043] The vehicle system 1 includes, for example, a camera 10, a radar device 12, a LIDAR (Light Detection and Ranging) 14, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, a vehicle sensor 40, a navigation device 50, an MPU (Map Positioning Unit) 60, a driving operating unit 70, an automatic driving control device 100, a driving force output device 200, a braking device 210, and a steering device 220. These devices and equipment are interconnected through multi-channel communication lines such as CAN (Controller Area Network) communication lines, serial communication lines, wireless communication networks, etc. It should be noted that Figure 1 The structure shown is just an example, and part of the structure may be omitted or another structure may be further added.

[0044] The camera 10 is, for example, a digital camera that utilizes a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 10 is installed at any part of a vehicle (hereinafter referred to as the vehicle M) equipped with the vehicle system 1. When shooting the front, the camera 10 is installed at the top of the front windshield, the back of the rearview mirror in the vehicle, etc. When shooting the rear, the camera 10 is installed at the top of the rear windshield, the rear door, etc. When shooting the side, the camera 10 is installed at the rearview mirror on the door, etc. The camera 10, for example, repeatedly and periodically shoots the surroundings of the vehicle M. The camera 10 may also be a stereo camera.

[0045] The radar device 12 radiates radio waves such as millimeter waves to the periphery of the vehicle M, and detects radio waves (reflected waves) reflected from an object to detect at least the position (distance and direction) of the object. The radar device 12 is installed at any part of the vehicle M. The radar device 12 can also detect the position and speed of the object by FM-CW (Frequency Modulated Continuous Wave) method.

[0046] The LIDAR 14 irradiates light (or electromagnetic waves of a wavelength close to that of light) to the periphery of the vehicle M and measures scattered light. The LIDAR 14 detects the distance to the object based on the time from light emission to light reception. The irradiated light is, for example, a pulsed laser. The LIDAR 14 is installed at any part of the vehicle M.

[0047] The object recognition device 16 performs sensor fusion processing on the detection results detected by part or all of the camera 10, the radar device 12, and the LIDAR 14 to recognize the position, type, speed, etc. of the object. The object recognition device 16 outputs the recognition result to the automatic driving control device 100. The object recognition device 16 can output the detection results of the camera 10, the radar device 12, and the LIDAR 14 directly to the automatic driving control device 100. The object recognition device 16 can also be omitted from the vehicle system 1.

[0048] The communication device 20 communicates with other vehicles around the host vehicle M using, for example, a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), or the like, or communicates with various server devices via a wireless base station.

[0049] The HMI 30 presents various information to the occupants of the vehicle M, and receives input operations from the occupants. The HMI 30 includes various display devices, speakers, buzzers, touch panels, switches, keys, and the like.

[0050] The vehicle sensor 40 includes a vehicle speed sensor that detects the speed of the host vehicle M, an acceleration sensor that detects acceleration, an azimuth sensor that detects the orientation of the host vehicle M, and the like.

[0051] The navigation device 50 includes, for example, a GNSS (Global Navigation Satellite System) receiver 51, a navigation HMI 52, and a route determination unit 53. The navigation device 50 stores first map information 54 in a storage device such as a HDD (Hard Disk Drive) or a flash memory.

[0052] The GNSS receiver 51 determines the position of the vehicle M based on the signal received from the GNSS satellite (radio waves arriving from artificial satellites). The position of the vehicle M can also be determined or supplemented by an INS (Inertial Navigation System) using the output of the vehicle sensor 40. The navigation HMI 52 includes a display device, a speaker, a touch panel, buttons, etc. The navigation HMI 52 can also be partially or completely shared with the aforementioned HMI 30. The path determination unit 53, for example, refers to the first map information 54 to determine the path (hereinafter referred to as the path on the map) from the position of the vehicle M determined by the GNSS receiver 51 (or an arbitrary position input) to the destination input by the occupant using the navigation HMI 52.

[0053] The first map information 54 is, for example, information that expresses the shape of a road by representing the lines of the road and the nodes connected by the lines. The first map information 54 may also include the curvature of the road, POI (Point Of Interest) information, etc. The path on the map is output to the MPU 60. The navigation device 50 may also provide path guidance using the navigation HMI 52 based on the path on the map. The navigation device 50 may also be implemented by the function of a terminal device such as a smartphone or a tablet terminal held by the passenger. The navigation device 50 may also send the current position and destination to the navigation server via the communication device 20, and obtain a path equivalent to the path on the map from the navigation server.

[0054] The MPU 60 includes, for example, a recommended lane determination unit 61, and stores the second map information 62 in a storage device such as a HDD or a flash memory. The recommended lane determination unit 61 is implemented by a hardware processor (computer) such as a CPU (Central Processing Unit) executing a program (software). In addition, the recommended lane determination unit 61 can be implemented by hardware (including a circuit unit; circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), and a GPU (Graphics Processing Unit), or can be implemented by the collaboration of software and hardware. The program can be pre-stored in a storage device (a storage device having a non-temporary storage medium) of the MPU 60, or can be stored in a removable storage medium such as a DVD or a CD-ROM, and installed in the storage device of the MPU 60 by assembling the storage medium (non-temporary storage medium) in a drive device.

[0055] The recommended lane determination unit 61 divides the path on the map provided by the navigation device 50 into a plurality of blocks (for example, every 100 [m] in the vehicle's traveling direction), and determines a recommended lane for each block with reference to the second map information 62. The recommended lane determination unit 61 determines the lane number from the left to travel on. When there is a branch point in the path on the map, the recommended lane determination unit 61 determines the recommended lane so that the host vehicle M can travel on a reasonable path for traveling to the branch destination.

[0056] The second map information 62 is map information with higher accuracy than the first map information 54. The second map information 62 includes, for example, information on the center of a lane (road centerline, centerline) or information on a lane boundary (road dividing line, dividing line). In addition, the second map information 62 may include road information (road signs, road structures such as traffic lights), traffic restriction information, address information (address, zip code), facility information, telephone number information, etc. The second map information 62 may be updated at any time by communicating with other devices through the communication device 20.

[0057] The driving operating parts 70 include, for example, an accelerator pedal, a brake pedal, a shift lever and other operating parts in addition to the steering wheel 72. A sensor for detecting the amount of operation or the presence or absence of operation is installed on the driving operating parts 70. The detection result of the sensor is output to the automatic driving control device 100, or to a part or all of the driving drive force output device 200, the braking device 210 and the steering device 220. The steering wheel 72 does not necessarily have to be annular, and can also be in the form of a special-shaped steering wheel, an operating lever, a button, etc. A steering grip sensor 74 is installed on the steering wheel 72. The steering grip sensor 74 is implemented by an electrostatic capacitance sensor or the like, and outputs a signal to the automatic driving control device 100 that can detect whether the driver is holding the steering wheel 72 (that is, it is in contact with it in a state where force can be applied).

[0058] The automatic driving control device 100, for example, includes a first control unit 120 and a second control unit 160. The first control unit 120 and the second control unit 160 are respectively implemented by, for example, a hardware processor (computer) such as a CPU executing a program (software). In addition, some or all of these components may also be implemented by hardware (including a circuit unit: circuitry) such as an LSI, an ASIC, an FPGA, a GPU, or the like, or may be implemented by the coordination of software and hardware. The program may be pre-stored in a storage device (a storage device having a non-temporary storage medium) such as an HDD or a flash memory of the automatic driving control device 100, or may be stored in a removable storage medium such as a DVD or a CD-ROM, and may be installed in the HDD or the flash memory of the automatic driving control device 100 by assembling the storage medium (non-temporary storage medium) to the drive device.

[0059] Figure 2 1 is a functional configuration diagram of the first control unit 120 and the second control unit 160. The first control unit 120 includes, for example, a recognition unit 130 and an action plan generation unit 140. The automatic driving control device 100, the first control unit 120, or the recognition unit 130 is an example of an "object recognition device."

[0060] The first control unit 120 implements functions based on AI (Artificial Intelligence) and functions based on a pre-given model in parallel. For example, the function of "identifying intersections" can be implemented by "parallel execution of intersection identification based on deep learning and the like and identification based on pre-given conditions (the presence of signals and road signs that can be pattern matched), and scoring both for comprehensive evaluation." In this way, the reliability of autonomous driving is ensured.

[0061] The recognition unit 130 recognizes the position, velocity, acceleration and other states of objects in the vicinity of the vehicle M based on at least a portion of the information input from the camera 10, the radar device 12, and the LIDAR 14. The position of the object target is identified, for example, as a position on an absolute coordinate with a representative point (center of gravity, drive shaft center, etc.) of the vehicle M as the origin, and is used in control. The position of the object can be represented by a representative point such as the center of gravity or a corner of the object, or by an area. The "state" of the object can also include the acceleration, jerk or "action state" of the object (for example, whether a lane change is being made or is about to be made).

[0062] In addition, the recognition unit 130, for example, recognizes the lane in which the host vehicle M is traveling (driving lane). For example, the recognition unit 130 recognizes the driving lane by comparing the pattern of road dividing lines (e.g., the arrangement of solid lines and dotted lines) obtained from the second map information 62 with the pattern of road dividing lines around the host vehicle M recognized based on the image captured by the camera 10. It should be noted that, not limited to road dividing lines, the recognition unit 130 can also recognize the driving lane by recognizing road dividing lines, driving road boundaries (road boundaries) including shoulders, curbs, central median strips, guardrails, etc. In this recognition, the position of the host vehicle M obtained from the navigation device 50 and the processing results processed by the INS can also be added. In addition, the recognition unit 130 recognizes temporary stop lines, obstacles, red lights, toll booths, and other road phenomena.

[0063] When recognizing the driving lane, the recognition unit 130 recognizes the position and posture of the host vehicle M relative to the driving lane. For example, the recognition unit 130 may recognize the deviation of the reference point of the host vehicle M from the center of the lane and the angle formed by the traveling direction of the host vehicle M with respect to the line connecting the centers of the lanes as the relative position and posture of the host vehicle M with respect to the driving lane. Alternatively, the recognition unit 130 may recognize the position of the reference point of the host vehicle M with respect to any side end (road dividing line or road boundary) of the driving lane as the relative position of the host vehicle M with respect to the driving lane.

[0064] The recognition unit 130 includes, for example, an acquisition unit 131, a high-resolution region setting unit 132, an imaging instruction unit 133, and an object recognition unit 134. The acquisition unit 131 acquires information input from the camera 10, the radar device 12, and the LIDAR 14. The high-resolution region setting unit 132 is an example of a "setting unit." The object recognition unit 134 is an example of a "recognition unit."

[0065] The high-resolution region setting unit 132 sets a high-resolution region to be processed at a higher resolution than other regions in the surrounding image obtained by photographing the surrounding of the host vehicle M by the camera 10. For example, the high-resolution region setting unit 132 sets a high-resolution region required for obtaining a high-resolution image (hereinafter referred to as a "high-resolution image") for the low-resolution surrounding image (hereinafter referred to as a "low-resolution image") photographed by the camera 10. First, the high-resolution region setting unit 132 obtains the surrounding information of the host vehicle M while traveling based on the low-resolution image photographed by the camera 10. The surrounding information indicates the general situation of the surroundings such as the type of objects located around the host vehicle M and the approximate position of the objects. The high-resolution region setting unit 132 obtains the surrounding information of the host vehicle M while traveling by performing image analysis such as pattern matching on the low-resolution image. It should be noted that the high-resolution region setting unit 132 may also obtain the surrounding information of the host vehicle M while traveling based on the information input from the radar device 12 or the LIDAR 14. Furthermore, the high-resolution area setting unit 132 may acquire the surrounding information of the host vehicle M based on the second map information 62 stored in the storage device of the MPU 60 .

[0066] Next, the high-resolution region setting unit 132 sets a high-resolution region for the low-resolution image based on the acquired surrounding information. For example, the high-resolution region setting unit 132 sets the region containing other vehicles in the low-resolution image as the high-resolution region. The high-resolution region setting unit 132 determines the region containing other vehicles by performing image analysis on the low-resolution image, and sets the determined region as the high-resolution region. Alternatively, the high-resolution region setting unit 132 sets the region containing traffic structures in the low-resolution image as the high-resolution region. The high-resolution region setting unit 132 determines the region containing traffic structures by performing image analysis on the low-resolution image, and sets the determined region as the high-resolution region. Road structures include, for example, road signs, traffic signals, curbs, central medians, guardrails, fences, walls, intersections, and the like. In addition, road structures may also include, for example, road dividing lines, pedestrian crossings, bicycle crossings, temporary stop lines, and other road surface markings drawn or attached to the road surface. It should be noted that the high-resolution region setting unit 132 may set the high-resolution region based on the state of the road on which the host vehicle M is traveling (road curvature, etc.) or the traveling state of the host vehicle M, such as the speed of the host vehicle M.

[0067] Alternatively, the high-resolution region setting unit 132 sets a high-resolution region for the surrounding image captured by the camera 10 (e.g., the surrounding image captured at a high resolution) based on the acquired surrounding information. For example, the high-resolution region setting unit 132 sets the region containing other vehicles in the surrounding image as the high-resolution region. The high-resolution region setting unit 132 determines the region containing other vehicles by performing image analysis on the surrounding image at a low resolution, and sets the determined region as the high-resolution region. Alternatively, the high-resolution region setting unit 132 sets the region containing a traffic structure in the surrounding image as the high-resolution region. The high-resolution region setting unit 132 determines the region containing a traffic structure by performing image analysis on the surrounding image, and sets the determined region as the high-resolution region.

[0068] That is, the high-resolution region setting unit 132 sets a high-resolution region to be processed at a higher resolution than other regions in the surrounding image (first image) obtained by capturing the surroundings of the host vehicle M based on the surrounding information of the host vehicle M.

[0069] The imaging instruction unit 133 sends an imaging instruction to the camera 10 to capture a high-resolution image of the high-resolution area set by the high-resolution area setting unit 132. The camera 10 that receives the imaging instruction captures the area around the host vehicle M corresponding to the high-resolution area at a high resolution, and sends the captured high-resolution image to the automatic driving control device 100. Thus, the acquisition unit 131 acquires the high-resolution image of the set high-resolution area.

[0070] The object recognition unit 134 processes the image corresponding to the high-resolution area set by the high-resolution area setting unit 132 at a high resolution to recognize detailed information of an object located in the vicinity of the host vehicle M. For example, the object recognition unit 134 recognizes the state of a lighting part (turn indicator, brake light, etc.) of another vehicle, the content or state of a road structure, etc., included in the high-resolution image, and recognizes the detailed information of the object.

[0071] That is, the object recognition unit 134 recognizes the object by processing the image of the high-resolution area in the surrounding image (first image) at high resolution. In addition, the object recognition unit 134 recognizes the object by processing the high-resolution image (second image) at high resolution, which is an image obtained by photographing the area around the vehicle corresponding to the high-resolution area at high resolution.

[0072] The action plan generation unit 140 generates a target trajectory for the vehicle M to automatically (independent of the driver's operation) travel in the future in a manner that allows the vehicle M to travel on the recommended lane determined by the recommended lane determination unit 61 in principle and to cope with the surrounding conditions of the vehicle M. The target trajectory includes, for example, a speed element. For example, the target trajectory is represented by a trajectory in which the locations (track points) that the vehicle M should arrive at are arranged in sequence. The track point is the location that the vehicle M should arrive at at every specified driving distance (for example, a few [m]) along the way. Different from this, the target speed and target acceleration at every specified sampling time (for example, a few tenths [sec]) are generated as part of the target trajectory. In addition, the track point can also be the position that the vehicle M should arrive at at every specified sampling time at the sampling time. In this case, the information on the target speed and target acceleration is represented by the interval between the track points.

[0073] The action plan generation unit 140 may set an event for autonomous driving when generating a target trajectory. The events for autonomous driving include a constant speed driving event, a low speed following driving event, a lane change event, a branching event, a merging event, a takeover event, etc. The action plan generation unit 140 generates a target trajectory corresponding to the activated event.

[0074] The second control unit 160 controls the travel driving force output device 200 , the braking device 210 , and the steering device 220 so that the host vehicle M passes through the target track generated by the action plan generation unit 140 at a predetermined timing.

[0075] The second control unit 160 includes, for example, an acquisition unit 162, a speed control unit 164, and a steering control unit 166. The acquisition unit 162 acquires information of the target track (track point) generated by the action plan generation unit 140, and stores the information in a memory (not shown). The speed control unit 164 controls the travel drive force output device 200 or the braking device 210 based on the speed element attached to the target track stored in the memory. The steering control unit 166 controls the steering device 220 according to the curvature of the target track stored in the memory. The processing of the speed control unit 164 and the steering control unit 166 is implemented, for example, by a combination of feedforward control and feedback control. As an example, the steering control unit 166 performs a combination of feedforward control corresponding to the curvature of the road ahead of the vehicle M and feedback control based on the deviation from the target track.

[0076] The driving force output device 200 outputs the driving force (torque) for driving the vehicle to the driving wheels. The driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, and a transmission, and an ECU (Electronic Control Unit) that controls them. The ECU controls the above structure according to information input from the second control unit 160 or information input from the driving operation member 70.

[0077] The brake device 210 includes, for example, a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the hydraulic cylinder, and a brake ECU. The brake ECU controls the electric motor according to information input from the second control unit 160 or information input from the driving operating member 70, so that a brake torque corresponding to the braking operation is output to each wheel. The brake device 210 may include a mechanism that transmits the hydraulic pressure generated by the operation of the brake pedal included in the driving operating member 70 to the hydraulic cylinder via the master hydraulic cylinder as a backup. It should be noted that the brake device 210 is not limited to the structure described above, and may also be an electronically controlled hydraulic brake device that controls the actuator according to information input from the second control unit 160 to transmit the hydraulic pressure of the master hydraulic cylinder to the hydraulic cylinder.

[0078] The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor, for example, applies force to a rack-and-pinion mechanism to change the direction of the steering wheel. The steering ECU drives the electric motor according to information input from the second control unit 160 or information input from the driving operating member 70 to change the direction of the steering wheel.

[0079] The object recognition process will be described below using a flowchart. Figure 3 1 is a flowchart showing an example of object recognition processing performed by the recognition unit 130 of the automatic driving control device 100 according to the embodiment. In the following description, a case where the host vehicle M is performing automatic driving under the control of automatic driving by the automatic driving control device 100 is described as an example. Figure 3 The object recognition process of the flowchart shown is repeatedly executed while the host vehicle M is performing automatic driving.

[0080] (1) Setting of high-resolution area based on the presence of other vehicles

[0081] First, the process of setting the high-resolution area based on the presence of another vehicle will be described. Figures 4A to 4D This is a diagram for explaining an example of a case where a high-resolution area is set based on the presence of another vehicle according to the embodiment.

[0082] First, the acquisition unit 131 acquires the surrounding image captured by the camera 10 (step S101). Figure 4A The surrounding image LR1 is obtained by capturing the space in the traveling direction of the host vehicle M as shown. It should be noted that the acquisition unit 131 may acquire information input from the radar device 12 or the LIDAR 14 in addition to the information input from the camera 10 .

[0083] Next, the high-resolution region setting unit 132 processes the acquired surrounding image LR1 at a low resolution to obtain surrounding information of the traveling vehicle M (step S103). The high-resolution region setting unit 132 obtains surrounding information of the traveling vehicle M by, for example, performing image analysis such as pattern matching on the surrounding image LR1. It should be noted that the high-resolution region setting unit 132 may also obtain surrounding information of the traveling vehicle M based on information input from the radar device 12 or the LIDAR 14. For example, after obtaining Figure 4A In the case of the surrounding image LR1 shown in FIG. 1 , the high-resolution region setting unit 132 obtains general information about other vehicles, such as the presence or absence of other vehicles in the space in the traveling direction of the host vehicle M, the positions of other vehicles, and the distances to other vehicles. Figure 4A In the example shown, the high-resolution region setting unit 132 recognizes two other vehicles V1 and V3 traveling in the same lane as the host vehicle M and another vehicle V2 traveling in the oncoming lane in the space in the travel direction of the host vehicle M.

[0084] Next, the high-resolution region setting unit 132 sets a high-resolution region for the surrounding image LR1 based on the acquired surrounding information (step S105). Figure 4BIn the example shown, the high-resolution region setting unit 132 identifies two other vehicles V1 and V2 within a predetermined distance around the host vehicle M, and sets a region including each of these other vehicles V1 and V2 as a high-resolution region. For example, the high-resolution region setting unit 132 sets two regions, a region R1-1 including at least the rear of the other vehicle V1 and a region R1-2 including at least the front of the other vehicle V2, as high-resolution regions. Figure 4B In the example shown, the other vehicle V3 is spaced apart from the host vehicle M and is not within the predetermined distance. In this case, the high-resolution region setting unit 132 excludes the other vehicle V3 from the target of setting the high-resolution region.

[0085] That is, the high-resolution region setting unit 132 sets the region including other vehicles in the surrounding image LR1 (first image) as the high-resolution region. In addition, the high-resolution region setting unit 132 determines the region including other vehicles by performing image analysis on the surrounding image LR1, and sets the determined region as the high-resolution region.

[0086] In addition, the high-resolution area setting unit 132 can also pre-identify other vehicles traveling on the side or rear of the vehicle M based on the information input from the camera 10, the radar device 12, and the LIDAR 14, and when the other vehicle overtakes the vehicle M and appears in front of the vehicle M, the area including the other vehicle is set as the high-resolution area.

[0087] Next, the imaging instruction unit 133 sends an imaging instruction to the camera 10 to capture a high-resolution image of the set high-resolution area (step S107). The camera 10 that receives the imaging instruction captures the area around the host vehicle M corresponding to the high-resolution area at a high resolution, and transmits the captured high-resolution image to the automatic driving control device 100. Thus, the acquisition unit 131 acquires the high-resolution image of the set high-resolution area (step S109). Figure 4C This means that by shooting with high resolution Figure 4B The high-resolution image HR1 - 1 is obtained by viewing the area corresponding to the high-resolution area R1 - 1 shown. Figure 4D This means that by shooting with high resolution Figure 4B The high-resolution image HR1 - 2 is obtained by focusing on the area corresponding to the high-resolution area R1 - 2 shown.

[0088] It should be noted that, in the case where the acquisition unit 131 acquires both the low-resolution image and the high-resolution image of the surrounding information of the host vehicle M in the above-mentioned step S101, the acquisition process of the high-resolution image in the above-mentioned steps S107 and S109 can be omitted. In addition, in the case where the surrounding image used for acquiring the surrounding information of the host vehicle M is a high-resolution image, the acquisition process of the high-resolution image in the above-mentioned steps S107 and S109 can be omitted.

[0089] Next, the object recognition unit 134 processes the acquired high-resolution image or a partial image of a high-resolution area set in the surrounding image at a high resolution to recognize detailed information of an object located around the vehicle M (step S111). For example, the object recognition unit 134 uses Figure 4C The object recognition unit 134 can recognize the state of the lighting parts (turn indicator, brake light, etc.) of the other vehicle V1 and the operation state of the other vehicle V1. Figure 4D The high-resolution image HR1-2 shown in the figure recognizes the state of the lighting parts (turn indicator, brake light, etc.) of the other vehicle V2, thereby recognizing the action state of the other vehicle V2. Afterwards, the action plan generation unit 140 generates a target track using the acquired surrounding image and high-resolution image, as well as the recognition result of the object recognition unit 134, and the second control unit 160 controls the driving force output device 200, the brake device 210, and the steering device 220 so that the host vehicle M passes through the generated target track at a predetermined time. Based on the above, the processing of this flowchart ends.

[0090] That is, the high-resolution region setting unit 132 recognizes the motion state of the other vehicle based on the image of the lighted portion of the other vehicle included in the image corresponding to the high-resolution region. When the first image includes a first other vehicle traveling in a lane in the same direction as the host vehicle M, the high-resolution region setting unit 132 sets a region including at least the rear portion of the first other vehicle as the high-resolution region. When the first image includes a second other vehicle traveling in a lane opposite to the lane in which the host vehicle is traveling, the high-resolution region setting unit 132 sets a region including at least the front portion of the second other vehicle as the high-resolution region.

[0091] (2) Setting of high-resolution areas based on the presence of road structures

[0092] Next, the process of setting the high-resolution area based on the presence of the road structure will be described. Figures 5A to 5C This is a diagram for explaining an example of setting a high-resolution area based on the presence of a traffic structure according to an embodiment.

[0093] First, the acquisition unit 131 acquires the surrounding image captured by the camera 10 (step S101). Figure 5A The surrounding image LR2 of the space in the traveling direction of the host vehicle M is shown. It should be noted that the acquisition unit 131 may acquire information input from the radar device 12 or the LIDAR 14 in addition to the information input from the camera 10 .

[0094] Next, the high-resolution region setting unit 132 processes the acquired surrounding image LR2 at a low resolution to obtain surrounding information of the traveling vehicle M (step S103). The high-resolution region setting unit 132 obtains surrounding information of the traveling vehicle M by, for example, performing image analysis such as pattern matching on the surrounding image LR2. It should be noted that the high-resolution region setting unit 132 may also obtain surrounding information of the traveling vehicle M based on information input from the radar device 12 or the LIDAR 14. For example, after obtaining Figure 5A In the case of the surrounding image LR2 shown in FIG. 1 , the high-resolution region setting unit 132 obtains general information related to the road structure, such as the presence or absence of a road structure in the space in the traveling direction of the host vehicle M, the position of the road structure, and the distance of the road structure. Figure 5A In the illustrated example, the high-resolution region setting unit 132 recognizes the traffic signal T1 located in the space in the traveling direction of the host vehicle M.

[0095] Alternatively, the high-resolution area setting unit 132 may obtain the surrounding information of the host vehicle M based on the second map information 62 stored in the storage device of the MPU 60. For example, the high-resolution area setting unit 132 recognizes general information related to the road structure, such as the presence or absence of a road structure in the space in the traveling direction of the host vehicle M, the position of the road structure, and the distance to the road structure, based on the second map information 62.

[0096] Next, the high-resolution region setting unit 132 sets a high-resolution region for the surrounding image LR2 based on the acquired surrounding information (step S105). Figure 5A and 5B In the illustrated example, the high-resolution region setting unit 132 recognizes a road structure (traffic signal T1 ) within a predetermined distance around the host vehicle M, and sets a region including the traffic signal T1 as the high-resolution region R2 .

[0097] It should be noted that, in the above-mentioned step S103, when the high-resolution region setting unit 132 is acquiring the surrounding information of the host vehicle M based on the second map information 62, the high-resolution region setting unit 132 determines the position of the road structure in the surrounding image LR2 by comparing and establishing a correspondence between the pattern of the road dividing lines and the position of the road structure obtained from the second map information 62 and the pattern of the road dividing lines around the host vehicle M recognized from the image captured by the camera 10. Furthermore, the high-resolution region setting unit 132 sets a high-resolution region that at least includes the determined road structure for the surrounding image LR2.

[0098] That is, the high-resolution region setting unit 132 sets the region including the traffic structure in the surrounding image LR2 (first image) as the high-resolution region. In addition, the high-resolution region setting unit 132 determines the region including the traffic structure by performing image analysis on the first image, and sets the determined region as the high-resolution region. In addition, the high-resolution region setting unit 132 determines the region including the traffic structure using the pre-stored second map information (map information) including road information, and sets the determined region as the high-resolution region.

[0099] Next, the imaging instruction unit 133 sends an imaging instruction to the camera 10 to capture a high-resolution image of the set high-resolution area (step S107). The camera 10 that receives the imaging instruction captures the area around the host vehicle M corresponding to the high-resolution area at a high resolution, and transmits the captured high-resolution image to the automatic driving control device 100. Thus, the acquisition unit 131 acquires the high-resolution image of the set high-resolution area (step S109). Figure 5C is achieved by capturing images with high resolution Figure 5B A high-resolution image HR2 is obtained by focusing on the area corresponding to the high-resolution area R2 shown.

[0100] It should be noted that, when the acquisition unit 131 acquires both the low-resolution image and the high-resolution image of the surrounding information of the host vehicle M in the above-mentioned step S101, the acquisition process of the high-resolution image in the above-mentioned steps S107 and S109 may be omitted. In addition, when the surrounding image used for acquiring the surrounding information of the host vehicle M is a high-resolution image, the acquisition process of the high-resolution image in the above-mentioned steps S107 and S109 may be omitted.

[0101] Next, the object recognition unit 134 processes the acquired high-resolution image or a partial image of a high-resolution area set in the surrounding image at a high resolution, thereby recognizing detailed information of an object located around the vehicle M (step S111). For example, the object recognition unit 134 uses Figure 5C The high-resolution image HR2 shown in the figure is used to identify the operating state of the traffic signal T1 (the difference between red, green, and yellow lights). Afterwards, the action plan generation unit 140 generates a target track using the acquired surrounding image and high-resolution image and the recognition result obtained by the object recognition unit 134, and the second control unit 160 controls the driving force output device 200, the braking device 210, and the steering device 220 so that the vehicle M passes through the generated target track at a predetermined time. Based on the above, the processing of this flowchart ends.

[0102] (3) Setting of high-resolution areas based on road curvature

[0103] Next, the process of setting the high-resolution area based on the road curvature will be described. Figures 6A to 6C A diagram for explaining an example of setting a high-resolution area based on the curvature of a road according to an embodiment.

[0104] First, the acquisition unit 131 acquires the surrounding information captured by the camera 10 (step S101 ). It should be noted that the acquisition unit 131 may acquire information input from the radar device 12 or the LIDAR 14 in addition to the information input from the camera 10 .

[0105] Next, the high-resolution area setting unit 132 processes the acquired surrounding image at a low resolution to obtain the surrounding information of the traveling vehicle M (step S103). The high-resolution area setting unit 132 obtains the surrounding information of the traveling vehicle M by, for example, performing image analysis such as pattern matching on the surrounding image. It should be noted that the high-resolution area setting unit 132 can also obtain the surrounding information of the traveling vehicle M based on the information input from the radar device 12 and the LIDAR 14. For example, the high-resolution area setting unit 132 identifies the state of the road on which the vehicle M is traveling (the curvature of the road, the curvature radius of the road, etc.). It should be noted that the high-resolution area setting unit 132 can also obtain the surrounding information of the traveling vehicle M based on the second map information 62 stored in the storage device of the MPU 60.

[0106] Next, the high-resolution region setting unit 132 sets a high-resolution region for the surrounding image based on the acquired surrounding information (step S105). It should be noted that in the above-mentioned step S103, when the high-resolution region setting unit 132 is identifying the surrounding conditions of the host vehicle M based on the second map information 62, the high-resolution region setting unit 132 compares the pattern of the road dividing lines obtained from the second map information 62 with the pattern of the road dividing lines around the host vehicle M identified from the image captured by the camera 10 and establishes a corresponding relationship, thereby determining the position of the road in the surrounding image. In addition, the high-resolution region setting unit 132 sets a high-resolution region for the surrounding image according to the curvature of the road.

[0107] In obtaining Fig. 6A In the case of the surrounding image LR3 as shown in FIG. 1 , the high-resolution region setting unit 132 recognizes that the road on which the host vehicle M is traveling is a straight road. In this case, the high-resolution region setting unit 132 sets a high-resolution region R3 of a predetermined size including an area in front of the host vehicle M in the traveling direction in the surrounding image LR3.

[0108] On the other hand, having achieved Figure 6B In the case of the surrounding image LR4 as shown in FIG. 1 , the high-resolution region setting unit 132 recognizes that the road on which the host vehicle M is traveling is a road that curves to the left (with a small curvature). In this case, the high-resolution region setting unit 132 sets a high-resolution region R4 including an area of ​​a predetermined size that deviates from the front direction of the traveling direction of the host vehicle M by a distance D (D1) to the left in the surrounding image LR4. The distance D is set according to the curvature of the road. The distance D is set to increase as the curvature of the road increases. In this way, by setting the high-resolution region according to the curvature of the road, the acquisition target area of ​​the high-resolution image can be made variable, and high-precision information can be acquired while being limited to a necessary range.

[0109] On the other hand, having achieved Figure 6C In the case of the surrounding image LR5 as shown in FIG. 1 , the high-resolution region setting unit 132 recognizes that the road on which the host vehicle M is traveling is curved to the left (with a large curvature). In this case, the high-resolution region setting unit 132 sets a high-resolution region R5 including an area of ​​a predetermined size that is offset to the left from the front of the host vehicle M in the traveling direction by a distance D (D2) in the surrounding image LR5. Figure 6B Compared to the roads shown, Figure 6C The curvature of the road shown is large. Figure 6C In the case shown, the distance D2 is set to be Figure 6B In the case shown the distance D1 has a large value.

[0110] Next, the imaging instruction unit 133 sends an imaging instruction to the camera 10 to capture a high-resolution image of the set high-resolution area (step S107). The camera 10 that receives the imaging instruction captures the area around the host vehicle M corresponding to the high-resolution area at a high resolution, and transmits the captured high-resolution image to the automatic driving control device 100. Thus, the acquisition unit 131 acquires the high-resolution image of the set high-resolution area (step S109).

[0111] It should be noted that, when the acquisition unit 131 acquires both the low-resolution image and the high-resolution image of the surrounding information of the host vehicle M in the above-mentioned step S101, the acquisition process of the high-resolution image in the above-mentioned steps S107 and S109 may be omitted. In addition, when the surrounding image used for acquiring the surrounding information of the host vehicle M is a high-resolution image, the acquisition process of the high-resolution image in the above-mentioned steps S107 and S109 may be omitted.

[0112] Next, the object recognition unit 134 processes the acquired high-resolution image or the partial image of the high-resolution area set in the surrounding image with high resolution, thereby recognizing detailed information of the object located around the host vehicle M (step S111). Thereafter, the action plan generation unit 140 generates a target track using the acquired surrounding image and high-resolution image and the recognition result recognized by the object recognition unit 134, and the second control unit 160 controls the travel driving force output device 200, the braking device 210, and the steering device 220 so that the host vehicle M passes through the generated target track at a predetermined time. Based on the above, the processing of this flowchart ends.

[0113] (4) Setting of high-resolution area based on vehicle speed

[0114] Next, the process of setting the high-resolution area based on the vehicle speed will be described. Figures 7A to 7C A diagram for explaining an example of setting a high-resolution area based on the vehicle speed according to the embodiment.

[0115] First, the acquisition unit 131 acquires a surrounding image captured by the camera 10 (step S101 ). It should be noted that the acquisition unit 131 may acquire information input from the radar device 12 or the LIDAR 14 in addition to the information input from the camera 10 .

[0116] Next, the high-resolution region setting unit 132 processes the acquired surrounding image at a low resolution to obtain the surrounding information of the traveling vehicle M (step S103). The high-resolution region setting unit 132 obtains the surrounding information of the traveling vehicle M by, for example, performing image analysis such as pattern matching on the surrounding image. It should be noted that the high-resolution region setting unit 132 may also obtain the surrounding information of the traveling vehicle M based on the information input from the radar device 12 or the LIDAR 14. It should be noted that the processing of step S103 may also be omitted.

[0117] Next, the high-resolution region setting unit 132 sets a high-resolution region for the acquired surrounding image based on the vehicle speed of the host vehicle M detected by the vehicle speed sensor of the vehicle sensor 40 (step S105 ).

[0118] Next, the imaging instruction unit 133 sends an imaging instruction to the camera 10 to capture a high-resolution image of the set high-resolution area (step S107). The camera 10 that receives the imaging instruction captures the area around the host vehicle M corresponding to the high-resolution area at a high resolution, and transmits the captured high-resolution image to the automatic driving control device 100. Thus, the acquisition unit 131 acquires the high-resolution image of the set high-resolution area (step S109).

[0119] It should be noted that, when the acquisition unit 131 acquires both the low-resolution image and the high-resolution image of the surrounding information of the host vehicle M in the above-mentioned step S101, the acquisition process of the high-resolution image in the above-mentioned steps S107 and S109 may be omitted. In addition, when the surrounding image used for acquiring the surrounding information of the host vehicle M is a high-resolution image, the acquisition process of the high-resolution image in the above-mentioned steps S107 and S109 may be omitted.

[0120] Fig. 7A The peripheral image LR6 captured when the host vehicle M is stopped (vehicle speed is zero) is shown. In this case, the high-resolution region setting unit 132 sets a high-resolution region R6 that includes the entire region of the peripheral image LR6. The camera 10 captures the region around the host vehicle M corresponding to the high-resolution region R6 at a high resolution, thereby obtaining a high-resolution image HR6.

[0121] Figure 7BThe peripheral image LR7 captured when the vehicle M is traveling (vehicle speed is slow) is shown. In this case, the high-resolution region setting unit 132 sets a high-resolution region R7 including the area in front of the vehicle M in the traveling direction in the peripheral image LR7. The position and size of the high-resolution region R7 are set according to the vehicle speed. As the vehicle speed increases, the high-resolution region R7 is set to be farther away from the vehicle and smaller in size. The camera 10 captures the area around the vehicle M corresponding to the high-resolution image HR7 at a high resolution to obtain the high-resolution image HR7.

[0122] Figure 7C The peripheral image LR8 captured when the vehicle M is traveling (at a high speed) is shown. In this case, the high-resolution region setting unit 132 sets a high-resolution region R8 including the area ahead of the vehicle M in the traveling direction in the peripheral image LR8. The size of the high-resolution region R8 is set according to the vehicle speed. Figure 7B The example speed shown is compared to Figure 7C The example shown is at a high speed. Therefore, Figure 7C The position and size of the high-resolution area R8 in the illustrated case are set to Figure 7B The area around the vehicle M corresponding to the high-resolution area R8 is photographed with high resolution by the camera 10, and a high-resolution image HR8 is obtained. In this way, by setting the high-resolution area according to the vehicle speed, the area to be acquired for the high-resolution image can be changed, and high-precision information can be acquired in a limited necessary range.

[0123] Next, the object recognition unit 134 processes the acquired high-resolution image or the partial image of the high-resolution area set in the surrounding image with high resolution, thereby recognizing detailed information of the object located around the host vehicle M (step S111). Thereafter, the action plan generation unit 140 generates a target track using the acquired surrounding image and high-resolution image and the recognition result recognized by the object recognition unit 134, and the second control unit 160 controls the travel driving force output device 200, the braking device 210, and the steering device 220 so that the host vehicle M passes through the generated target track at a predetermined time. Based on the above, the processing of this flowchart ends.

[0124] According to the embodiment described above, the high-resolution region setting unit 132 (setting unit) sets a high-resolution region to be processed at a higher resolution than other regions in the surrounding image based on the surrounding information of the vehicle for the surrounding image (first image) obtained by photographing the surrounding of the host vehicle M (vehicle); and the object recognition unit 134 (recognition unit) processes the image corresponding to the set high-resolution region at a high resolution to recognize the objects located in the surrounding of the vehicle, thereby enabling information related to the objects with high importance among the objects located in the surrounding of the vehicle to be acquired in a short time without omission. In this way, by setting the high-resolution region based on the surrounding information of the vehicle, the region to be acquired for the high-resolution image can be made variable, and the region to be acquired for the high-resolution image can be limited to a necessary range and acquired.

[0125] The above-described embodiment can be expressed as follows.

[0126] The object recognition device is configured to include:

[0127] a storage device storing a program; and

[0128] Hardware processor,

[0129] The hardware processor executes the program to perform the following processing:

[0130] For a first image obtained by photographing the periphery of a vehicle, a high-resolution area is set based on the periphery information of the vehicle to be processed at a higher resolution than other areas in the first image; and

[0131] By processing the image corresponding to the set high-resolution area at a high resolution, an object located around the vehicle is recognized.

[0132] Although specific embodiments of the present invention have been described above using the embodiments, the present invention is not limited to such embodiments at all, and various modifications and substitutions can be made without departing from the gist of the present invention.

Claims

1. An object recognition device, wherein: The object recognition device comprises: a setting unit for setting, for a first image obtained by photographing the periphery of a vehicle, a high-resolution area to be processed at a higher resolution than other areas in the first image based on the periphery information of the vehicle; as well as a recognition unit that recognizes an object located around the vehicle by processing an image corresponding to the set high-resolution area at a high resolution, When a curved road is recognized in the first image captured along the traveling direction of the vehicle, the setting unit sets, as the high-resolution area, an area of ​​a predetermined size that deviates in the left-right direction from the traveling direction of the vehicle by a distance corresponding to the curvature of the curved road, The recognition unit recognizes the object by processing a second image with high resolution, the second image being an image obtained by capturing a region around the vehicle corresponding to the high resolution region set by the setting unit with high resolution.

2. The object recognition device according to claim 1, wherein: The recognition section recognizes the object by processing the image of the high-resolution area in the first image at a high resolution.

3. The object recognition device according to claim 1 or 2, wherein: The setting unit sets a region in the first image including other vehicles as the high-resolution region, The recognition unit recognizes the other vehicle.

4. The object recognition device according to claim 3, wherein: The setting unit determines a region including the other vehicle by performing image analysis on the first image, and sets the determined region as the high-resolution region.

5. The object recognition device according to claim 3, wherein: The recognition unit recognizes the operation state of the other vehicle based on the image of the lighting portion of the other vehicle included in the image corresponding to the high-resolution area.

6. The object recognition device according to claim 3, wherein: The setting unit sets a region including at least a rear portion of the first other vehicle as the high-resolution region when the first image includes a first other vehicle traveling in a lane in the same direction as the vehicle. When the first image includes a second other vehicle traveling in an oncoming lane of the lane in which the vehicle is traveling, a region including at least a front portion of the second other vehicle is set as the high-resolution region.

7. The object recognition device according to claim 1 or 2, wherein: The setting unit sets a region including a traffic structure in the first image as the high-resolution region, The recognition unit recognizes the traffic structure.

8. The object recognition device according to claim 7, wherein: The setting unit determines a region including the traffic structure by performing image analysis on the first image, and sets the determined region as the high-resolution region.

9. The object recognition device according to claim 7, wherein: The setting unit determines an area including the traffic structure using pre-stored map information including road information, and sets the determined area as the high-resolution area.

10. A method for object recognition, wherein: The object recognition method enables a computer mounted on a vehicle to perform the following processing: For a first image obtained by photographing the periphery of a vehicle, a high-resolution area is set to be processed at a higher resolution than other areas in the first image based on the periphery information of the vehicle; as well as By processing the image corresponding to the set high-resolution area at a high resolution, an object located around the vehicle is recognized, When a curved road is recognized in the first image captured along the traveling direction of the vehicle, an area of ​​a predetermined size deviated in the left-right direction from the traveling direction of the vehicle by a distance corresponding to the curvature of the curved road is set as the high-resolution area, The object is recognized by processing a second image at a high resolution, the second image being an image obtained by photographing an area around the vehicle corresponding to the set high resolution area at a high resolution.

11. A storage medium, wherein: The storage medium stores a program that causes a computer mounted on a vehicle to execute the following processing: For a first image obtained by photographing the periphery of a vehicle, a high-resolution area is set to be processed at a higher resolution than other areas in the first image based on the periphery information of the vehicle; as well as By processing the image corresponding to the set high-resolution area at a high resolution, an object located around the vehicle is recognized, When a curved road is recognized in the first image captured along the traveling direction of the vehicle, an area of ​​a predetermined size deviated in the left-right direction from the traveling direction of the vehicle by a distance corresponding to the curvature of the curved road is set as the high-resolution area, The object is recognized by processing a second image at a high resolution, the second image being an image obtained by photographing an area around the vehicle corresponding to the set high resolution area at a high resolution.

Images