Object detection device, object detection method, object detection program, and recording medium

Abstract

To provide technology enabling even more effective target detection.SOLUTION: An object detection device (6) is configured to detect an object (B) based on a captured image (Pg) of a path ahead of an own vehicle (V). The object detection device includes a gradient information acquisition unit (602), a detection area setting unit (604), and a detection unit (605). The gradient information acquisition unit acquires gradient information on a road (Rd) ahead of the own vehicle. The detection area setting unit sets a target detection area (Br) within the captured image based on the gradient information acquired by the gradient information acquisition unit. The detection unit detects targets within the target detection area set by the detection area setting unit.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to a target detection device, a target detection method, a target detection program, and a computer-readable, non-transient, physical recording medium on which such a target detection program is recorded, which detect targets based on captured images of a location ahead of a vehicle. [Background technology]

[0002] Conventionally, technologies have been proposed for recognizing traffic lights and other signals from captured images captured by an imaging device such as an in-vehicle camera. For example, a device described in Patent Document 1 includes a scaled image generation unit, a region extraction unit, a region division unit, a region identification unit, and a lighting color determination unit. The scaled image generation unit generates multiple enlarged and reduced images, each with different scaling ratios, from the captured image input from the camera and outputs them to the region extraction unit. The region extraction unit uses traffic light dictionary information to extract a traffic light region containing a traffic light from the scaled image input from the scaled image generation unit and outputs image information within the extracted traffic light region to the region division unit. The size of the traffic light in the captured image varies depending on the distance from the vehicle. Therefore, the region extraction unit can extract the traffic light region by searching the multiple scaled images input from the scaled image generation unit with different scaling ratios. The region division unit divides the traffic light region into multiple light source regions containing the traffic light sources. The region identification unit identifies the light source region containing the lit light source as the lit region based on the brightness difference between the multiple light source regions. The lighting color determining unit determines the lighting color of the traffic light based on the color of the lighting area. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-130163 Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology described in Patent Document 1, traffic lights are recognized by enlarging and reducing the captured image to various sizes. However, due to processing time constraints, it may not be possible to enlarge and reduce the image to various sizes. On the other hand, due to processing time constraints, it may be necessary to reduce the image. When reducing the captured image in this way, the resolution of traffic lights located far away decreases, and it may not be possible to extract the traffic light area as intended. The present disclosure has been made in consideration of the circumstances exemplified above. In other words, the present disclosure provides, for example, a technology that enables even better target detection. [Means for solving the problem]

[0005] In one aspect of the present disclosure, a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V) includes: a gradient information acquisition unit (602) that acquires gradient information on a road (Rd) ahead of the host vehicle; a detection area setting unit (604) that sets a target detection area (Br) within the captured image based on the gradient information acquired by the gradient information acquisition unit; a detection unit (605) that detects the target within the target detection area set by the detection area setting unit; It is equipped with: In another aspect of the present disclosure, a target detection method executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V) includes: acquire gradient information of a road (Rd) ahead of the host vehicle; Based on the acquired gradient information, a target detection region (Br) is set within the captured image; The target is detected within the set target detection area. In yet another aspect of the present disclosure, a target detection program executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V) includes, as processing executed by the target detection device, A process of acquiring gradient information on a road (Rd) ahead of the host vehicle; A process of setting a target detection region (Br) within the captured image based on the acquired gradient information; a process of detecting the target within the set target detection area; Includes: In yet another aspect of the present disclosure, a computer-readable non-transient physical recording medium having recorded thereon a target detection program executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a vehicle (V) includes, as a process included in the target detection program, A process of acquiring gradient information on a road (Rd) ahead of the host vehicle; A process of setting a target detection region (Br) within the captured image based on the acquired gradient information; a process of detecting the target within the set target detection area; Includes:

[0006] In addition, in each section of the application documents, each element may be assigned a reference symbol in parentheses. However, such reference symbols merely indicate an example of the correspondence between the element and the specific means described in the embodiments below. Therefore, the present disclosure is not limited in any way by the above-mentioned reference symbols. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a schematic diagram showing a vehicle to which the present disclosure is applied while traveling; [Figure 2] 2 is a schematic diagram showing an example of a captured image acquired using the camera shown in FIG. 1. FIG. [Figure 3] 2 is a block diagram showing a schematic device configuration of the in-vehicle system shown in FIG. 1. FIG. [Figure 4] FIG. 4 is a block diagram showing a schematic functional configuration realized in the target detection device shown in FIG. 3. [Figure 5] 5 is a flowchart showing an outline of an example of the operation of the target detection device shown in FIGS. 3 and 4. [Figure 6]FIG. 5 is a diagram showing an outline of an example of the operation of the target detection device shown in FIGS. 3 and 4. [Figure 7] FIG. 5 is a diagram showing an outline of an example of the operation of the target detection device shown in FIGS. 3 and 4. DETAILED DESCRIPTION OF THE INVENTION

[0008] (Embodiment: Configuration) Hereinafter, exemplary embodiments and specific examples of the present disclosure will be described with reference to the accompanying drawings as appropriate. First, referring to Fig. 1, an in-vehicle system 1 is configured to be mounted on a vehicle V and to perform various operations in the vehicle V. Hereinafter, the vehicle V equipped with the in-vehicle system 1 will be referred to as the "host vehicle."

[0009] (In-vehicle system configuration) The in-vehicle system 1 is equipped with a camera 2 that captures images of the surroundings of the vehicle, and is configured to perform image recognition based on images captured by this camera 2 to perform operations such as presenting information to occupants and controlling driving in the vehicle. "Information presentation" includes display and audio output. "Driving control" includes the execution of longitudinal vehicle motion control subtasks and / or lateral vehicle motion control subtasks. The longitudinal vehicle motion control subtasks are starting, accelerating / decelerating, and stopping. The lateral vehicle motion control subtask is steering. Typically, the in-vehicle system 1 has a configuration as, for example, a so-called driving automation system, i.e., an automated driving system and / or a driving assistance system.

[0010] The camera 2 is equipped with an image sensor such as a CCD or CMOS, and is mounted at a predetermined position on the vehicle to capture images of the surroundings of the vehicle. CCD stands for Charge Coupled Device. CMOS stands for Complementary Metal Oxide Semiconductor. In this embodiment, the vehicle is equipped with at least a front camera as the camera 2. FIG. 2 shows an example of an image Pg of the area ahead of the vehicle captured by the front camera as the camera 2. The front camera is installed so as to capture an image of a road Rd ahead of the vehicle and targets B on or around the road Rd. Targets B include not only three-dimensional objects but also planar road markings Rp. Three-dimensional objects include road signs, traffic signals TS, and the like, in addition to objects that may be obstacles to travel, such as pedestrians and other vehicles. The road markings Rp include road dividing lines Ln.

[0011] Referring to FIG. 3, the in-vehicle system 1 includes, in addition to a camera 2, an in-vehicle sensor 3, a navigation device 4, a communication device 5, a target detection device 6, an HMI device 7, and a vehicle control device 8. HMI stands for Human Machine Interface. The camera 2, the in-vehicle sensor 3, the navigation device 4, and the communication device 5 are connected to the target detection device 6 via an in-vehicle network so as to be able to exchange information or signals. The HMI device 7 and the vehicle control device 8 are also connected to the target detection device 6 via the in-vehicle network so as to be able to exchange information or signals. The in-vehicle network is configured to comply with a predetermined communication standard such as CAN (international registered trademark: International Registration Number 1048262A). CAN (international registered trademark) is an abbreviation for Controller Area Network. Note that the in-vehicle network may have, in addition to a main network conforming to CAN (international registered trademark), another main network or sub-network conforming to LIN, FlexRay, or the like. LIN stands for Local Interconnect Network.

[0012] The on-board sensors 3 are configured to detect various quantities related to the driving state of the host vehicle. The "driving state" includes the driving operation state, driving behavior state, and driving environment state of the host vehicle. The "driving operation state" refers to the state related to the driving operation input of the host vehicle by the driver of the host vehicle or the vehicle control device 8 described later, and includes, for example, the steering amount, throttle opening, brake operation amount, shift range, etc. In other words, the on-board sensors 3 include an accelerator pedal sensor, a brake pedal sensor, a shift position sensor, a steering angle sensor, etc. The "driving behavior state" refers to the state related to the motion, i.e., physical behavior, of the host vehicle, and includes, for example, vehicle speed, acceleration, yaw rate, etc. In other words, the on-board sensors 3 include a vehicle speed sensor, a yaw rate sensor, an acceleration sensor, etc. The "driving environment state" refers to the environment around the host vehicle, and includes, for example, the illuminance, weather, outside temperature, road surface condition, the presence of objects such as pedestrians and other vehicles, etc. That is, the on-board sensors 3 include an illuminance sensor, a raindrop sensor, an outside air temperature sensor, a radar sensor, a laser radar sensor, a sonar sensor, etc. Among the on-board sensors 3, a sensor related to the presence state of an object is called an ADAS sensor. ADAS stands for Advanced Driver-Assistance Systems. The ADAS sensor may include a camera 2.

[0013] The navigation device 4 is configured to be able to output information relating to the current position of the vehicle and the driving route. The navigation device 4 also has a map information database 41. The map information database 41 has so-called HD map information. HD stands for High Definition. HD map information is high-precision three-dimensional road map information, and is information including road shapes such as curvature, gradient, width, and number of lanes. In other words, the navigation device 4 is configured to be able to output the planned driving route and attribute information of the road on which the vehicle is currently traveling, as well as the current position and map information of the vehicle, to the target detection device 6, the HMI device 7, and the vehicle control device 8. The attribute information of the road includes the speed limit, width, curve curvature, gradient, etc.

[0014] The communication device 5 is an in-vehicle communication module also referred to as DCM, and is configured to be able to communicate information with an external server Z via base stations around the vehicle using wireless communication compliant with communication standards such as LTE or 5G. DCM is an abbreviation for Data Communication Module. LTE is an abbreviation for Long Term Evolution. 5G is an abbreviation for 5th Generation. The communication device 5 is configured to be able to acquire various information such as road traffic information such as congestion information and the latest map information from the external server Z and output it to the target detection device 6, the HMI device 7, and the vehicle control device 8.

[0015] The target detection device 6 is configured to detect a target B ahead of the host vehicle based on a captured image Pg of the destination of the host vehicle. That is, the target detection device 6 is configured to detect a target B around the host vehicle based on information and signals acquired from the camera 2, the on-board sensor 3, etc. Furthermore, based on the detection result of the target B, the target detection device 6 generates and outputs signals required for information presentation in the HMI device 7 and driving control in the vehicle control device 8. That is, the target detection device 6 has a configuration as an electronic circuit unit called an image processing ECU, a target recognition ECU, or a target detection ECU. ECU is an abbreviation for Electronic Control Unit.

[0016] In this embodiment, the target detection device 6 is configured as an on-board microcomputer including at least a processor 61 and a memory 62. The processor 61 includes at least one arithmetic unit configured as a CPU or MPU and its peripheral circuits (e.g., a timer circuit, etc.). The memory 62 includes at least a RAM and a ROM or a nonvolatile rewritable memory among various non-transient physical storage media such as a ROM, a RAM, and a nonvolatile rewritable memory. The nonvolatile rewritable memory is a storage device that is rewritable when powered on but retains information in an unrewritable manner when powered off, such as a flash memory. The information processing device 9 is configured so that the processor 61 reads and executes a computer program from the memory 62 to realize a predetermined function for recognizing targets around the vehicle. The memory 62 stores the computer program as well as various data required to execute the program, such as initial values, maps, and look-up tables.

[0017] 4 shows an example of a functional configuration realized on the target detection device 6 as an on-board microcomputer by the processor 61 executing a computer program. That is, the target detection device 6 has, as such a functional configuration, an image acquisition unit 601, a gradient information acquisition unit 602, a lane marking information acquisition unit 603, a detection area setting unit 604, and a detection unit 605. Each of these functional configurations will be described below. In the following description, unless otherwise noted, in this embodiment, the camera 2 refers to the front camera. However, it goes without saying that the present disclosure is not limited to such an embodiment.

[0018] The image acquisition unit 601 is configured to acquire image data captured by the camera 2. That is, in this embodiment, the image acquisition unit 601 receives image data corresponding to the captured image Pg acquired using the camera 2 from the camera 2 and stores a certain amount of the image data in chronological order.

[0019] The gradient information acquisition unit 602 acquires gradient information for the destination road Rd. "Gradient information" refers to information about the road surface gradient on the destination road Rd within a predetermined distance range ahead of the current location of the host vehicle. The gradient information may be information corresponding to the road surface gradient itself, or information indicating the relationship between the distance from the current location of the host vehicle and the altitude or elevation difference. The gradient information can be acquired, for example, based on map information or information about the planned route of the host vehicle. Alternatively, the gradient information can be acquired by estimating the gradient of the destination road Rd through machine learning based on a captured image Pg including the destination road Rd. The gradient information can be obtained using either or both of information acquired based on map information or information about the planned route of the host vehicle and the machine learning results (i.e., fusion results).

[0020] The lane marking information acquisition unit 603 acquires recognition information of the road marking lines Ln on the destination road Rd through image recognition. Specifically, in this embodiment, the lane marking information acquisition unit 603 generates recognition information of the road marking lines Ln through image recognition based on the captured image Pg. Because technology for recognizing road marking lines Ln was already well known at the time of filing this application, further detailed description will be omitted in this specification.

[0021] The detection area setting unit 604 is configured to set a target detection area Br within the captured image Pg, as shown in Fig. 2. In this embodiment, the target detection area Br is an area that is the target of image recognition of a target B (e.g., a traffic signal TS, a road sign, etc.) that exists locally and is different from the road dividing lines Ln that extend along the extension direction of the road Rd ahead. The target detection area Br may also be referred to as ROI. ROI is an abbreviation for Region of Interest.

[0022] In this embodiment, the detection area setting unit 604 sets a target detection area Br based on gradient information acquired by the gradient information acquisition unit 602 and recognition information of the road lane markings Ln acquired by the lane marking information acquisition unit 603. Specifically, the detection area setting unit 604 sets the height, i.e., the vertical position, of the target detection area Br in the captured image Pg based on the gradient information, and sets the horizontal position of the target detection area Br in the captured image Pg based on the recognition information of the road lane markings Ln. The detection unit 605 detects targets B, such as traffic signals TS and road signs, within the target detection area Br set by the detection area setting unit 604.

[0023] The HMI device 7 includes a display device, an audio output device, and the like for presenting various types of information and warnings to the occupants of the vehicle. The display device may include a meter, a meter display, a center information display, a head-up display, an electronic mirror, and the like. The vehicle control device 8 is configured as a so-called driving ECU, which is an on-board computer that controls the driving force generation mechanism, driving force transmission mechanism, braking mechanism, steering mechanism, and the like of the vehicle. That is, the vehicle control device 8 is configured to execute longitudinal and / or lateral motion control of the vehicle. More specifically, the vehicle control device 8 is configured to be able to execute at least a part of the motion control of the vehicle, such as starting, acceleration / deceleration, braking, stopping, steering, and the like.

[0024] (Example of operation) An outline of the target detection operation by the target detection device 6 according to this embodiment will be described below. In the flowchart shown in FIG. 5, "S" is an abbreviation for "step." The target detection device 6 according to this embodiment, the target detection method and target detection program executed thereby, and a computer-readable, non-transient, tangible recording medium on which such program is recorded may be collectively referred to as "this embodiment." Such a recording medium may be realized, for example, by a ROM, a non-volatile rewritable memory, a magnetic disk, an optical disk, or the like. Specifically, such a recording medium may be realized in any format, for example, by an external server Z, a portable terminal device, an optical disk such as a CD-ROM, a memory card detachable from a computer device such as a terminal device, or the like.

[0025] When a predetermined target detection condition is met, the processor 61 provided in the target detection device 6 reads out the target detection routine shown in Fig. 5 from the memory 62 and repeatedly executes the routine at predetermined time intervals (e.g., 10 msec intervals) while the target detection condition is met. The target detection condition includes, for example, that the ignition switch is turned on, that the shift position is other than "P", etc. When the processor 61 starts the target detection routine shown in Fig. 5, it executes the processes of steps 101 to 105 in order.

[0026] In step 101, the processor 61 acquires a captured image Pg. The processing content of step 101 corresponds to the function of the image acquisition unit 601. In step 102, the processor 61 acquires gradient information on the destination road Rd. The processing content of step 102 corresponds to the function of the gradient information acquisition unit 602. In step 103, the processor 61 acquires recognition information of the road dividing line Ln on the destination road Rd. The processing content of step 103 corresponds to the function of the dividing line information acquisition unit 603.

[0027] In step 104, the processor 61 sets a target detection region Br within the captured image Pg based on the gradient information acquired in step 102 and the recognition information acquired in step 103. The processing content of step 104 corresponds to the function of the detection region setting unit 604. In step 105, the processor 61 detects a target B, such as a traffic signal TS or a road sign, within the target detection region Br. The processing content of step 105 corresponds to the function of the detection unit 605.

[0028] 6 and 7 show examples of setting a target detection region Br on a slope. In the captured image Pg in the upper part of each figure, the recognition information of the road dividing line Ln is shown by a thin solid line, and the road surface detection position is indicated by a circle plot. The lower part of each figure shows a plot of the height distribution of the road surface detection position in the traveling direction. For the upslope shown in FIG. 6, the pre-correction detection region Brr, which is an ROI set without considering the road surface slope, is positioned too low to detect traffic signals TS and the like. In contrast, according to this embodiment, the target detection region Br can be set by moving the ROI upward from the position of the pre-correction detection region Brr based on the slope information shown in the lower part of each figure. On the other hand, for the downslope shown in FIG. 7, the pre-correction detection region Brr is positioned too high to detect traffic signals TS and the like. In contrast, according to this embodiment, the target detection region Br can be set by moving the ROI downward from the position of the pre-correction detection region Brr based on the slope information shown in the lower part of each figure.

[0029] (effect) As described above in detail, in this embodiment, the target detection region Br, which is the ROI, is set in an appropriate position in the captured image Pg for detecting a traffic signal TS, etc., in accordance with the road shape of the road Rd ahead of the host vehicle. This effectively reduces the processing time and processing load, and enables the traffic signal TS, etc., which is the target B to be detected, to be effectively detected.

[0030] (Variation) The present disclosure is not limited to the above-described embodiments and specific examples. Therefore, the above-described embodiments and the like can be modified as appropriate. Representative modifications will be described below. In the following description of the modifications, differences from the above-described embodiments and the like will be mainly described. Furthermore, the same reference numerals are used for parts that are identical or equivalent to each other in the above-described embodiments and the following modifications. Therefore, in the following description of the modifications, the explanations in the above-described embodiments and the like can be used as appropriate for components that have the same reference numerals as the above-described embodiments and the like, unless there is a technical contradiction or special additional explanation.

[0031] The present disclosure is not limited to the specific applications and device configurations shown in the above embodiments. For example, the host vehicle may be a so-called automobile or a motorcycle. There are no particular limitations on the type of automobile or motorcycle.

[0032] All or part of the target object detection device 6 may be configured to include a digital circuit, such as an ASIC or FPGA, configured to be able to realize the above-mentioned functions or operations. ASIC stands for Application Specific Integrated Circuit. FPGA stands for Field Programmable Gate Array. In other words, in the target object detection device 6, an on-board microcomputer portion and a digital circuit portion may coexist.

[0033] A computer program according to the present disclosure that enables the execution of various operations, procedures, or processes described in the above embodiments can be downloaded or upgraded via V2X communication using the communication device 5. V2X stands for Vehicle to X. Alternatively, such a computer program can be downloaded or upgraded via a terminal device installed in a vehicle manufacturing plant, a repair shop, a dealer, or the like. Such a computer program may be stored on a memory card, an optical disk, a magnetic disk, or the like.

[0034] In this way, each of the above functional configurations and processes may be realized by a special-purpose computer provided by configuring a processor 61 and memory 62 programmed to execute one or more functions embodied in a computer program. Alternatively, each of the above functional configurations and processes may be realized by a special-purpose computer provided by configuring a processor 61 with one or more dedicated hardware logic circuits. Alternatively, each of the above functional configurations and processes may be realized by one or more special-purpose computers configured by combining one or more processors 61 programmed to execute one or more functions and one or more memories 62 with one or more other processors 61 configured with one or more hardware logic circuits. Furthermore, a computer program may be stored in a computer-readable, non-transitory storage medium as instructions to be executed by a computer. In other words, each of the above functional configurations and processes may be expressed as a computer program including procedures for implementing the same, or as a non-transitory storage medium storing the computer program.

[0035] The present disclosure is not limited to the specific functions and operational aspects described in the above embodiment. For example, HD map information, from which gradient information is acquired, may be sequentially received from an external server Z. Furthermore, the gradient information may also take into account the pitching attitude of the vehicle. For example, the vertical position of the target detection area Br, which was set based on map information or the like, may be corrected based on the pitching attitude detected by the on-board sensor 3. The explanation using FIGS. 6 and 7 is merely an example for providing a simple understanding of the effects of the present disclosure. Therefore, the present disclosure is not limited to the aspect of setting the target detection area Br by moving the position of the pre-correction detection area Brr, which is an ROI set without considering the road surface slope. In other words, generating or setting the pre-correction detection area Brr is not an essential element of the present disclosure.

[0036] It goes without saying that the elements constituting the above-described embodiments are not necessarily essential unless expressly stated as essential or clearly considered essential in principle. Furthermore, when numerical values ​​such as the number, value, amount, and range of components are mentioned, the present disclosure is not limited to those specific numbers unless expressly stated as essential or clearly limited to a specific number in principle. Similarly, when the shape, direction, positional relationship, etc. of components are mentioned, the present disclosure is not limited to those shapes, directions, positional relationships, etc. unless expressly stated as essential or clearly limited to a specific shape, direction, positional relationship, etc. in principle.

[0037] Similar expressions such as "acquire," "calculate," "estimate," "detect," and "sensing" may be substituted for each other as appropriate within the scope of technical inconsistency. Furthermore, "exceeding the threshold" and "above the threshold" may be substituted for each other as appropriate within the scope of technical inconsistency. The same applies to "below the threshold" and "below the threshold."

[0038] The variations are not limited to the above examples. For example, all or part of one of the variations may be combined with all or part of another, provided that no technical contradiction exists. Furthermore, all or part of the above specific example and all or part of the variations may be combined with each other, provided that no technical contradiction exists.

[0039] (Disclosure perspective) As is clear from the above description of the embodiments and modifications, this specification discloses at least the following matters.

[0040] [Perspective A] Using a camera (2) mounted on the vehicle (V), a captured image (Pg) of the area ahead of the vehicle is acquired; acquire gradient information of a road (Rd) ahead of the host vehicle; Based on the acquired gradient information, a target detection region (Br) is set within the captured image; Detecting a target (B) ahead of the host vehicle within the set target detection area. Target detection method.

[0041] [Perspective B1] A target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V), a gradient information acquisition unit (602) that acquires gradient information on a road (Rd) ahead of the host vehicle; a detection area setting unit (604) that sets a target detection area (Br) within the captured image based on the gradient information acquired by the gradient information acquisition unit; a detection unit (605) that detects the target within the target detection area set by the detection area setting unit; A target detection device comprising: [Perspective B2] the detection area setting unit sets a vertical position of the target detection area in the captured image based on the gradient information acquired by the gradient information acquisition unit. A target detection device according to aspect B1. [Perspective B3] the gradient information acquisition unit acquires the gradient information by estimating a gradient of the destination road through machine learning based on the captured image including the destination road. A target detection device according to aspect B1 or B2. [Perspective B4] the gradient information acquisition unit acquires the gradient information based on map information or planned driving route information of the host vehicle. The target detection device according to any one of the aspects B1 to B3. [Perspective B5] the detection area setting unit sets the target detection area based on recognition information of a road division line (Ln) on the destination road obtained by image recognition and the gradient information acquired by the gradient information acquisition unit. A target detection device according to any one of the aspects B1 to B4.

[0042] [Perspective C1] A target detection method executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V), acquire gradient information of a road (Rd) ahead of the host vehicle; Based on the acquired gradient information, a target detection region (Br) is set within the captured image; Detecting the target within the set target detection area. Target detection method. [Perspective C2] setting a vertical position of the target detection area in the captured image based on the acquired gradient information; The target detection method according to aspect C1. [Perspective C3] acquiring the gradient information by estimating the gradient of the destination road by machine learning based on the captured image including the destination road; A target detection method according to aspect C1 or C2. [Perspective C4] The gradient information is acquired based on map information or planned travel route information of the host vehicle. A target detection method according to any one of the aspects C1 to C3. [Perspective C5] setting the target detection area based on recognition information of a road division line (Ln) on the road ahead obtained by image recognition and the acquired gradient information; A target detection method according to any one of the aspects C1 to C4.

[0043] [Perspective D1] A target detection program executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V), The process performed by the device is A process of acquiring gradient information on a road (Rd) ahead of the host vehicle; A process of setting a target detection region (Br) within the captured image based on the acquired gradient information; a process of detecting the target within the set target detection area; A target detection program including: [Perspective D2] the process of setting the target detection area includes a process of setting a vertical position of the target detection area in the captured image based on the acquired gradient information. A target detection program according to aspect D1. [Perspective D3] the process of acquiring the gradient information includes a process of acquiring the gradient information by estimating the gradient of the destination road by machine learning based on the captured image including the destination road. A target detection program according to aspect D1 or D2. [Perspective D4] The process of acquiring the gradient information includes a process of acquiring the gradient information based on map information or planned driving route information of the host vehicle. A target detection program according to any one of aspects D1 to D3. [Perspective D5] the process of setting the target detection area includes a process of setting the target detection area based on recognition information of a road division line (Ln) on the destination road obtained by image recognition and the acquired gradient information. A target detection program according to any one of aspects D1 to D4.

[0044] [Perspective E1] A computer-readable non-transient tangible recording medium storing a target detection program executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a vehicle (V), The processing included in the target detection program is A process of acquiring gradient information of a road (Rd) ahead of the host vehicle; A process of setting a target detection region (Br) within the captured image based on the acquired gradient information; a process of detecting the target within the set target detection area; A recording medium including: [Perspective E2] the process of setting the target detection area includes a process of setting a vertical position of the target detection area in the captured image based on the acquired gradient information. A recording medium according to aspect E1. [Perspective E3] the process of acquiring the gradient information includes a process of acquiring the gradient information by estimating the gradient of the destination road by machine learning based on the captured image including the destination road. A recording medium according to aspect E1 or E2. [Perspective E4] The process of acquiring the gradient information includes a process of acquiring the gradient information based on map information or planned driving route information of the host vehicle. A recording medium according to any one of aspects E1 to E3. [Perspective E5] the process of setting the target detection area includes a process of setting the target detection area based on recognition information of a road division line (Ln) on the destination road obtained by image recognition and the acquired gradient information. A recording medium according to any one of aspects E1 to E4. [Explanation of symbols]

[0045] 6 Target detection device 602 Gradient information acquisition unit 604 Detection area setting unit 605 Detector B Target Br Target detection area Ln Road boundary line Pg Captured image Rd Destination road V Vehicle

Claims

1. A target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V), a gradient information acquisition unit (602) that acquires gradient information on a road (Rd) ahead of the host vehicle; a detection area setting unit (604) that sets a target detection area (Br) within the captured image based on the gradient information acquired by the gradient information acquisition unit; a detection unit (605) that detects the target within the target detection area set by the detection area setting unit; A target detection device comprising:

2. the detection area setting unit sets a vertical position of the target detection area in the captured image based on the gradient information acquired by the gradient information acquisition unit. The target detection device according to claim 1 .

3. the gradient information acquisition unit acquires the gradient information by estimating a gradient of the destination road through machine learning based on the captured image including the destination road. The target detection device according to claim 2 .

4. the gradient information acquisition unit acquires the gradient information based on map information or planned driving route information of the host vehicle. The target detection device according to claim 2 .

5. the detection area setting unit sets the target detection area based on recognition information of a road division line (Ln) on the destination road obtained by image recognition and the gradient information acquired by the gradient information acquisition unit. The target detection device according to any one of claims 1 to 4.

6. A target detection method executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V), comprising: acquire gradient information of a road (Rd) ahead of the host vehicle; setting a target detection region (Br) within the captured image based on the acquired gradient information; Detecting the target within the set target detection area. Target detection method.

7. A target detection program executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a host vehicle (V), The process executed by the target detection device is A process of acquiring gradient information of a road (Rd) ahead of the host vehicle; a process of setting a target detection region (Br) within the captured image based on the acquired gradient information; a process of detecting the target within the set target detection area; A target detection program including:

8. A computer-readable non-transient tangible recording medium storing a target detection program executed by a target detection device (6) that detects a target (B) based on a captured image (Pg) of a destination of a vehicle (V), The processing included in the target detection program is A process of acquiring gradient information of a road (Rd) ahead of the host vehicle; a process of setting a target detection region (Br) within the captured image based on the acquired gradient information; a process of detecting the target within the set target detection area; A recording medium including:

Images