Object identification device and object identification program

Abstract

The present invention provides an object identification device and an object identification program that can reduce operational delays. [Solution] The object identification device 500 includes a fusion unit 504 that generates a fusion target based on first target information, which is detection information of an object in a first range, and second target information, which is detection information of an object in a second range; a ghost determination unit 505 that determines whether the fusion target corresponds to a real object or is a ghost; a transition determination unit 506 that determines whether the fusion target is in a transition state, having been detected in a non-overlapping range of the first and second ranges and then detected in an overlapping range; and a ghost relaxation unit 508 that relaxes the conditions for determining that a fusion target corresponds to a real object, compared to the case where it is determined not to be in a transition state, for a fusion target determined to be in a transition state.

Description

[[Technical Field]]

[0001] The present disclosure relates to an object identification device and an object identification program. [[Background Art]]

[0002] In the vehicle control device described in Patent Document 1, a radar sensor using millimeter waves or the like detects an object as a radar target, an image sensor detects the object as an image target, and the radar target and the image target are fused to generate a fusion target. When a state where the object is detected as a fusion target transitions to a state where the object is detected only as a radar target, vehicle control for the object is not performed unless the object is within a predetermined short distance. [[Prior Art Literature]] [[Patent Documents]]

[0003] [[Patent Document 1]] Japanese Patent No. 6539228 [[Summary of the Invention]] [[Problem to be Solved by the Invention]]

[0004] When a state where an object is detected only as a radar target outside the angle of view of the image sensor transitions to a state where the object is detected as a fusion target, there is a risk that operation delay of vehicle control may occur due to the time required to accumulate the reliability of the fusion target. However, Patent Document 1 does not describe the behavior when the state transitions as described above.

[0005] In view of the above points, an object of the present disclosure is to provide an object identification device and an object identification program that can reduce operation delay. [[Means for Solving the Problem]]

[0006] To achieve the above objective, according to one aspect of this disclosure, the object identification device (500) includes: a first information acquisition unit (502) that acquires first target information, which is detection information of an object in a first range (R1); a second information acquisition unit (503) that acquires second target information, which is detection information of an object in a second range (R2a, R2b); a fusion unit (504) that generates a fusion target based on the first target information and the second target information; a ghost determination unit (505) that determines whether the fusion target corresponds to a real object or is a ghost; and the first The system includes a transition determination unit (506) that determines whether a fusion target is in a transition state detected in the overlapping range after being detected in the non-overlapping range, with the overlapping range of the first and second ranges being defined as the overlapping range (R3a, R3b) and the range outside the overlapping range being defined as the non-overlapping range (R4a, R4b), and a ghost mitigation unit (508) that relaxes the conditions for determining that a fusion target corresponds to a physical object compared to the case where it is determined not to be in a transition state, for a fusion target determined to be in a transition state.

[0007] For fusion targets that have been determined to be in a transition state, by relaxing the conditions for determining that they correspond to an actual entity, it becomes possible to cancel the ghost determination without waiting for the reliability of the fusion target to accumulate, thereby reducing operational delays in vehicle control and other systems.

[0008] From another perspective, the object identification program executed by the object identification device (500) includes, as processes executed by the object identification device, a process to acquire first target information, which is detection information of an object in a first range (R1); a process to acquire second target information, which is detection information of an object in a second range (R2a, R2b); a process to generate a fusion target based on the first target information and the second target information; a process to determine whether the fusion target corresponds to a real object or is a ghost; a process to determine whether the fusion target is in a transition state, having been detected in the non-overlapping range and then detected in the overlapping range, with the overlapping range of the first and second ranges designated as the overlapping range (R3a, R3b) and the range outside the overlapping range designated as the non-overlapping range (R4a, R4b); and a process to relax the conditions for determining that a fusion target corresponds to a real object, compared to the case where it is determined not to be in a transition state.

[0009] For fusion targets that have been determined to be in a transition state, by relaxing the conditions for determining that they correspond to an actual entity, it becomes possible to cancel the ghost determination without waiting for the reliability of the fusion target to accumulate, thereby reducing operational delays in vehicle control and other systems.

[0010] The reference numerals in parentheses attached to each component indicate an example of the correspondence between that component and the specific components described in the embodiments described later. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram of an in-vehicle system to which the object identification device according to the first embodiment is applied. [Figure 2] This diagram shows the detection range of the camera and radar sensor. [Figure 3] This diagram shows the detection range of the camera and radar sensor. [Figure 4] This is a block diagram of an object identification device. [Figure 5] This is a flowchart of the object identification process. [Figure 6] This figure shows an example of an object identification device in operation. [Figure 7] This figure shows an example of an object identification device in operation. [Modes for carrying out the invention]

[0012] The embodiments of this disclosure will be described below with reference to the drawings. In the following embodiments, parts that are the same or equivalent to each other will be denoted by the same reference numerals.

[0013] (First Embodiment) The first embodiment will now be described. The in-vehicle system 1 shown in Figure 1 is configured to perform various operations in a vehicle when mounted on that vehicle. Hereinafter, the vehicle on which the in-vehicle system 1 is mounted will be referred to as "the vehicle itself".

[0014] The in-vehicle system 1 is configured to perform various operations, including motion control operations and related notification operations, based on the detection results of objects around the vehicle using the camera 2 and radar sensors 3a and 3b mounted on the vehicle. Specifically, in this embodiment, the in-vehicle system 1 has the configuration of a so-called driving automation system. "Driving automation" is a concept that includes driver assistance and autonomous driving.

[0015] In other words, the in-vehicle system 1 is configured to achieve a level of driving automation corresponding to at least one of levels 1 to 5 as defined in the standard "SAE J3016" published by SAE International. SAE stands for Society of Automotive Engineers. Level X in "SAE J3016" will be simply referred to as "SAE Level X" below. X is one of 0 to 5. SAE Level 0 is called manual driving. SAE Level 1 is called driver assistance. SAE Level 2 is called advanced driver assistance. SAE Level 3 is called conditional automated driving. SAE Level 4 is called advanced automated driving. SAE Level 5 is called fully automated driving.

[0016] In this embodiment, the in-vehicle system 1 is configured to continuously perform at least one of the longitudinal vehicle motion control subtasks and the lateral vehicle motion control subtasks included in the dynamic driving task. The longitudinal vehicle motion control subtasks are starting, accelerating and decelerating, and stopping. The lateral vehicle motion control subtask is steering. Specifically, the in-vehicle system 1 is configured to implement, for example, AEB and AES. AEB stands for Autonomous Emergency Braking and is also called collision damage mitigation brake. AES stands for Automatic Emergency Steering or Autonomous Emergency Steering and is also called automatic steering avoidance.

[0017] 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 photograph the area around 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 Camera 2. The front camera is configured to photograph the road surface ahead of the vehicle, objects located above the road surface, and the foreground in front of and to the front and sides of the vehicle.

[0018] The radar sensors 3a and 3b are configured to detect objects around the host vehicle based on transmission and reception results of radar waves, which are radio waves in the millimeter wave band. The radar sensor 3a is a front radar sensor for detecting objects in front of the host vehicle, and is mounted on the front end of the vehicle body of the host vehicle. The radar sensor 3b is a front-side radar sensor for detecting objects on the front side of the host vehicle, and is mounted on the front end of the vehicle body of the host vehicle. The in-vehicle system 1 includes two radar sensors 3b, and the two radar sensors 3b respectively detect objects on the right front side and the left front side of the host vehicle.

[0019] In FIGS. 2 and 3, the host vehicle is denoted by reference sign Vs. A range R1 is a detection range of a camera 2, and ranges R2a and R2b are detection ranges of the radar sensors 3a and 3b, respectively. In FIGS. 2 and 3, only the detection range of one of the radar sensors 3b is illustrated. In FIG. 2, a hatched range R3a is a range where the range R1 and the range R2a overlap, and a dotted hatched range R4a is a range outside the range R3a among the range R1 and the range R2a. In FIG. 3, a hatched range R3b is a range where the range R1 and the range R2b overlap, and a dotted hatched range R4b is a range outside the range R3b among the range R1 and the range R2b. The range R1 corresponds to a first range.

[0020] As will be described later, in the present embodiment, a fusion target is generated based on image target information and radar target information. When fusion is established by the image target information acquired from the camera 2 and the radar target information acquired from transmission / reception information of the radar sensor 3a, the range R2a corresponds to a second range, the range R3a corresponds to an overlapping range, and the range R4a corresponds to a non-overlapping range. When fusion is established by the image target information acquired from the camera 2 and the radar target information acquired from transmission / reception information of the radar sensor 3b, the range R2b corresponds to a second range, the range R3b corresponds to an overlapping range, and the range R4b corresponds to a non-overlapping range.

[0021] As shown in Figure 1, the in-vehicle system 1 includes a camera 2 and radar sensors 3a and 3b, as well as a vehicle status sensor 4, a vehicle control ECU 5, a motion control device 6, a notification device 7, and a communication device 8. ECU stands for Electronic Control Unit. The camera 2, radar sensors 3a and 3b, vehicle status sensor 4, vehicle control ECU 5, motion control device 6, notification device 7, and communication device 8 are connected via an in-vehicle network to enable the exchange of information or signals.

[0022] The vehicle condition sensor 4 is designed to detect various quantities related to the driving state of the vehicle. "Driving state" includes the vehicle's driving operation state, driving behavior state, and driving environment state. "Driving operation state" refers to the state of driving operation input to the vehicle by the vehicle's driver or vehicle control ECU 5, and includes, for example, accelerator opening, brake operation amount, steering amount, shift range, etc. "Driving behavior state" refers to the state related to the vehicle's motion or behavior, and includes, for example, vehicle speed, acceleration, yaw rate, etc. "Driving environment state" refers to the environment around the vehicle that is different from the object presence state detected by the camera 2 and radar sensors 3a and 3b, and includes, for example, illumination around the vehicle, weather, etc. In other words, the vehicle condition sensor 4 is a general term for well-known in-vehicle sensors such as the accelerator position sensor, vehicle speed sensor, and outside temperature sensor.

[0023] The vehicle control ECU 5 is configured to control the operation of various parts of the vehicle based on the object detection results using the camera 2 and radar sensors 3a and 3b, and the detection results of the vehicle's driving state using the vehicle state sensor 4. Specifically, the vehicle control ECU 5 is a driving automation ECU, also known as a driving assistance ECU or an automated driving ECU, and controls the above-mentioned detection results and driving assistance operations or automated driving operations and various accompanying notification operations based on those results.

[0024] In this embodiment, the vehicle control ECU 5 has a configuration as an in-vehicle microcomputer comprising at least a processor 51 and a memory 52. ​​The processor 51 comprises at least one arithmetic unit having a configuration as a CPU or MPU, and peripheral circuits (e.g., a timer circuit). The memory 52 includes at least RAM and ROM and / or non-volatile rewritable memory from among various non-transitional physical storage media such as ROM, RAM, and non-volatile rewritable memory. Non-volatile rewritable memory is a storage device that allows information to be rewritten when the power is on, but keeps information unrewritable when the power is off, and is, for example, flash memory.

[0025] In this embodiment, the vehicle control ECU 5 is configured such that the processor 51 reads a computer program from the memory 52 and executes it to realize a predetermined function for recognizing objects around the vehicle. The term "object" is a concept that includes not only three-dimensional "objects" but also two-dimensional detection targets such as road markings and road lane markings. The memory 52 stores the above-mentioned computer program along with various data necessary for its execution, such as initial values, maps, and lookup tables.

[0026] The motion control device 6 is configured as an on-board microcomputer that controls the operation of the vehicle's drive force generation mechanism, drive force transmission mechanism, braking mechanism, steering mechanism, etc., based on control signals generated and output by the vehicle control ECU 5. In other words, the motion control device 6 is provided to perform motion control of the vehicle in either the longitudinal or lateral direction, or both. More specifically, the motion control device 6 is configured to perform at least a portion of the motion control of the vehicle, such as starting, accelerating / deceleration, braking, stopping, and steering.

[0027] The notification device 7 is equipped with display devices, audio output devices, etc., for providing various information and warnings to the occupants of the vehicle. Display devices may include meters, meter displays, center information displays, head-up displays, electronic mirrors, etc.

[0028] The communication device 8 is an in-vehicle communication module, also known as a DCM, and is configured to communicate information with an external server Z via base stations in the vicinity of the vehicle using wireless communication compliant with communication standards such as LTE or 5G. DCM stands for Data Communication Module. LTE stands for Long Term Evolution. 5G stands for 5th Generation. The communication device 8 is configured to acquire various information such as road traffic information including congestion information and the latest map information from the external server Z and output it to the vehicle control ECU 5 and the notification device 7.

[0029] Figure 4 shows an example of the functional block configuration of the object identification device 500, which is realized by the processor 51 in the vehicle control ECU 5 shown in Figure 1 executing a computer program. Specifically, the object identification device 500 shown in Figure 4 is realized by the processor 51 reading and executing the object identification program according to this disclosure from the memory 52. ​​This object identification device 500 identifies objects included in the captured image based on the image captured by the camera 2 mounted on the vehicle, which is ahead of the vehicle's movement.

[0030] As shown in Figure 4, the object identification device 500, as a functional configuration realized by executing a computer program, includes a sensor information acquisition unit 501, an image target information acquisition unit 502, a radar target information acquisition unit 503, and a fusion unit 504. The object identification device 500 also includes a ghost detection unit 505, a transition detection unit 506, a relaxation detection unit 507, a ghost relaxation unit 508, and an identification information output unit 509. The image target information acquisition unit 502 corresponds to the first information acquisition unit, and the radar target information acquisition unit 503 corresponds to the second information acquisition unit.

[0031] The sensor information acquisition unit 501 acquires detection information from the vehicle condition sensor 4. Specifically, the sensor information acquisition unit 501 receives signals or information from the vehicle condition sensor 4 that correspond to the detection results of the vehicle's driving operation state, driving behavior state, and driving environment state, and stores them for a predetermined capacity.

[0032] The image target information acquisition unit 502 acquires image target information within range R1, that is, information regarding the results of detection and recognition of image targets. An "image target" is a target detected or recognized based on the captured image information acquired by the camera 2. In this embodiment, the image target information acquisition unit 502 acquires, or generates, image target information by performing image processing and image recognition processing on the captured image information received from the camera 2. The image target information corresponds to the first target information.

[0033] The radar target information acquisition unit 503 acquires radar target information in the ranges R2a and R2b, that is, radar target detection information. A "radar target" is a target detected based on the transmission and reception results of radar waves by radar sensors 3a and 3b. In this embodiment, the radar target information acquisition unit 503 acquires, or generates, radar target information by receiving the transmission and reception information of radar waves from radar sensors 3a and 3b and performing signal processing. The radar target information corresponds to the second target information.

[0034] The fusion unit 504 acquires object recognition information using so-called sensor fusion technology, which integrates image target information and radar target information. A target that is both an image target and a radar target, and in which the integration of image target information and radar target information is achieved, is referred to as a "fusion target." Since the image target recognition technology, the radar target detection or recognition technology, and the sensor fusion technology are already well-known technologies at the time of filing this application, further detailed explanations are omitted.

[0035] The ghost detection unit 505 determines whether the object detection information is real object detection information or ghost detection information. "Detection information" includes image target information, radar target information, and fusion information as a result of integrating these. "Real object detection information" is detection information corresponding to the detection of an object as a physical entity. In contrast, "ghost detection information" is detection information corresponding to the detection of a ghost that is not a physical entity. The determination that the detection information corresponds to ghost detection will be referred to as "ghost determination" below.

[0036] Here, "ghost" refers to the phenomenon in which detection information appears even though an object does not actually exist, and can also be called "false detection" or "misrecognition." The definition of such "ghost" is also described in the "FY2022 Demonstration and Support Project for CASE Response such as Unmanned Autonomous Driving (Advanced Mobility Service Research and Development and Social Demonstration Project for Autonomous Driving Level 4 etc. (Theme 1: Initiatives to realize autonomous driving services with remote monitoring only (Lv4) in limited areas and vehicles in FY2022))" published by the National Institute of Advanced Industrial Science and Technology (AIST) in June 2023.

[0037] The ghost detection unit 505 performs ghost detection based on the manner of initial detection of the object. "Initial detection" typically refers to the first detection of the object during the current trip, but also includes cases where the object is detected again after being lost. "Trip" refers to the period from when the vehicle's ignition switch is turned on until it is turned off. A lost state is when the continuous detection of the same object is interrupted.

[0038] For example, the following first and second affirmative conditions can be used as ghost detection conditions. The first affirmative condition is that the object is cut off from the captured image during initial detection. This cutoff determination can be performed, for example, by determining whether the lower edge of the detection rectangle or bounding box surrounding the object overlaps with the outer frame of the captured image. The second affirmative condition is that the distance to the object is less than or equal to a threshold distance (e.g., 8m) during initial detection. The ghost detection unit 505 then determines that the object detection information is ghost detection information when either the first or second affirmative condition is met.

[0039] Furthermore, the ghost detection unit 505 is configured to appropriately cancel the ghost detection depending on the driving scene of its own vehicle. For example, the following first to fifth negation conditions can be used to cancel the ghost detection, i.e., to deny the presence of a ghost.

[0040] The first rejection condition is that the detected object remains visible in the captured image for a predetermined period of time. The second rejection condition is that the moving speed of the detected object exceeds a threshold speed (e.g., 0 km / h). The third rejection condition is that the detected object is a fusion target, and the moving speed of the object detected by radar sensors 3a and 3b exceeds a threshold speed (e.g., 0 km / h). The threshold speed in the second rejection condition and the threshold speed in the third rejection condition may be the same or different.

[0041] The fourth rejection condition is that the vehicle's turning radius is below a threshold. The fifth rejection condition is that the detected object is a fusion target and that a threshold time has passed since sensor fusion was established. The ghost detection unit 505 is configured to cancel the ghost detection if any one of the first to fifth rejection conditions is met. Thus, the first and fifth rejection conditions are set so that the ghost detection is canceled as the reliability of the fusion target accumulates.

[0042] The transition determination unit 506 determines whether the fusion target is in a transition state detected in range R3a after being detected in range R4a, or in a transition state detected in range R3b after being detected in range R4b. For example, the following first to third transition conditions can be used as transition determination conditions.

[0043] The first transition condition is that the elapsed time since the fusion was completed is less than a certain amount of time. For example, a counter is incremented each time a fusion is completed, and the first transition condition is met when the counter is less than a threshold.

[0044] The second transition condition is that an object that was previously detected only as a radar target in the object identification process is now detected as a fusion target. When the second transition condition is met, the transition determination unit 506 turns on the transition flag and holds it until fusion is no longer possible. The third transition condition is that this transition flag is still ON.

[0045] The transition determination unit 506 determines that the fusion target is in a transition state when the first transition condition and at least one of the second and third transition conditions are met.

[0046] The relaxation determination unit 507 determines whether or not the ghost determination can be relaxed. The relaxation of the ghost determination means relaxing the conditions under which a fusion target determined to be in a transition state is determined to correspond to an actual object, compared to the case where it is determined not to be in a transition state. For example, the following first to fourth relaxation conditions can be used as relaxation determination conditions.

[0047] The first relaxation condition is that the number of times the object has been detected as a radar target in ranges R4a and R4b is greater than the threshold. This first relaxation condition is used because a high number of detections as a radar target indicates a low probability of false detection.

[0048] The second relaxation condition is that the absolute value of the velocity of the radar target detected in ranges R4a and R4b is greater than the threshold, or the moving object flag of the radar target is greater than the threshold. The radar target information acquisition unit 503 determines whether or not an object is moving based on the results of transmitting and receiving radar waves by radar sensors 3a and 3b. The "moving object flag" indicates the result of this determination and is included in the radar target information. This second relaxation condition is used to perform the relaxation of ghost detection only for moving objects.

[0049] The third relaxation condition is that the fusion target has a velocity vector that is moving towards the vehicle. For example, the third relaxation condition is met when the product of the velocity and position of the fusion target in the left-right direction of the vehicle is less than 0. This third relaxation condition is used to exclude fusion targets moving away from the vehicle from the relaxation of ghost detection.

[0050] The fourth relaxation condition is that the ghost of the radar target is denied. The radar target information acquisition unit 503 performs ghost detection of the radar target separately from the ghost detection unit 505, based on the transmission and reception results of radar waves by the radar sensors 3a and 3b. The fourth relaxation condition is met when the radar target information acquisition unit 503 denies the ghost of the radar target. This fourth relaxation condition is used to improve the accuracy of ghost detection by excluding fusion targets for which ghost detection has been confirmed from the relaxation of ghost detection.

[0051] The relaxation determination unit 507 determines that, for a fusion target determined to be in a transition state, relaxation of the ghost determination is possible if all of the first to fourth relaxation conditions are met.

[0052] The ghost mitigation unit 508 is designed to mitigate ghost detection. Specifically, the ghost mitigation unit 508 releases the ghost detection when the mitigation detection unit 507 determines that a fusion target that has been detected as a ghost by the ghost detection unit 505 can be mitigated.

[0053] The identification information output unit 509 generates object identification information based on the processing results from the image target information acquisition unit 502, the radar target information acquisition unit 503, the fusion unit 504, the ghost detection unit 505, and the ghost mitigation unit 508. The identification information output unit 509 also outputs the generated object identification information to applications for automated driving operations in the vehicle control ECU 5, as well as to the motion control device 6 and the notification device 7.

[0054] The operation of this embodiment will be explained with reference to Figure 5. In the following description, the apparatus configuration according to this embodiment, and the method and program executed thereunder, may be collectively referred to as "this embodiment." The processor 51 reads and starts the computer program according to this embodiment from the memory 52, thereby repeatedly executing the object identification method according to this embodiment at a predetermined interval. Once such a program is started, the processor 51 executes the processing from step S101 onward.

[0055] First, in step S101, the processor 51 acquires captured image information from camera 2, radar wave transmission and reception information from radar sensors 3a and 3b, and sensor information from vehicle condition sensor 4.

[0056] In the subsequent step S102, the processor 51 performs sensor fusion, which integrates the image target information and the radar target information using the information acquired in step S101.

[0057] In the following step S103, the processor 51 determines whether or not fusion was achieved in step S102, that is, whether or not a fusion target was generated. If it is determined that fusion was achieved, the process proceeds to step S104. If it is determined that fusion was not achieved, the process proceeds to step S108.

[0058] In step S104, the processor 51 performs a ghost determination on the fusion target generated in step S103 using the first and second affirmative conditions and the first to fifth negative conditions described above. In the following step S105, the processor 51 determines whether the fusion target is in a transition state or not. If it is determined that the fusion target is in a transition state, the process proceeds to step S106. If it is determined that the fusion target is not in a transition state, the process proceeds to step S108.

[0059] In step S106, the processor 51 determines whether or not it is possible to relax the ghost detection for the fusion target. If it is determined that it is possible to relax the ghost detection, the process proceeds to step S107. If it is determined that it is not possible to relax the ghost detection, the process proceeds to step S108.

[0060] In step S107, the processor 51 performs a relaxation of the ghost detection criteria. After step S107, the process moves to step S108. In step S108, the processor 51 outputs identification information about the detected target.

[0061] The effects of this embodiment will now be explained. In Figures 6 and 7, other vehicles are indicated by the symbol Vt. Figure 6 shows a scene such as a head-on collision where another vehicle Vt enters the front from the side, outside the image field of view of the camera 2 of the vehicle Vs, while the vehicle Vs is moving forward. Figure 7 shows a scene where another vehicle Vt behind the vehicle Vs cuts in front of the vehicle Vs from an adjacent lane, such as by changing lanes, while the vehicle Vs is moving forward.

[0062] In these scenes, the other vehicle Vt is detected in range R4b and then detected as a fusion target in range R3b, so it is determined to be in a transition state in step S105, and the process moves to step S106. If it is determined in step S106 that the ghost detection can be mitigated, then even if it was detected as a ghost in step S104, the ghost detection is canceled in step S107.

[0063] As a result, in step S108, object identification information including the determination result that the fusion target corresponds to a physical object is output to the motion control device 6, etc., and the motion control of the vehicle Vs is used to avoid contact with other vehicles Vt. In this way, when predetermined conditions are met for an object in a transition state, the ghost determination can be canceled without waiting for the reliability of the fusion target to accumulate, thereby reducing the operating delay of the motion control device 6.

[0064] As explained above, in this embodiment, the conditions for determining that a fusion target is in a transition state correspond to an entity are relaxed. This makes it possible to cancel the ghost determination without waiting for the reliability of the fusion target to accumulate, for example, thus reducing operational delays in vehicle control and other systems.

[0065] (Other embodiments) Furthermore, this disclosure is not limited to the embodiments described above and can be modified as appropriate. Also, it goes without saying that, in the embodiments described above, the elements constituting the embodiments are not necessarily essential unless explicitly stated as particularly essential or considered fundamentally essential. Furthermore, in the embodiments described above, when numerical values ​​such as the number, numerical values, quantities, or ranges of the components of the embodiments are mentioned, the embodiments are not limited to those specific numbers unless explicitly stated as particularly essential or considered fundamentally limited to a specific number. Also, when the shapes, positional relationships, etc., of the components are mentioned in the embodiments described above, the embodiments are not limited to those shapes, positional relationships, etc., unless explicitly stated or considered fundamentally limited to specific shapes, positional relationships, etc.

[0066] Object detection sensors other than camera 2 are not limited to radar sensors 3a and 3b. That is, for example, laser radar sensors may be used instead of or in conjunction with radar sensors 3a and 3b. Laser radar sensors may also be called LiDAR sensors. LiDAR is an abbreviation for Light Detection and Ranging or Laser Imaging Detection and Ranging.

[0067] The computer program according to this disclosure, which 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 8. V2X is an abbreviation for VehicletoX. Alternatively, such a computer program can be downloaded or upgraded via terminal equipment installed at the vehicle's manufacturing plant, repair shop, dealership, etc. The storage location for such a computer program may be a memory card, optical disk, magnetic disk, etc.

[0068] Each of the above functional configurations and processes may be implemented by a dedicated computer provided by configuring a processor 51 and memory 52 programmed to execute one or more functions embodied by a computer program. Alternatively, each of the above functional configurations and processes may be implemented by a dedicated computer provided by configuring a processor 51 with one or more dedicated hardware logic circuits. Alternatively, each of the above functional configurations and processes may be implemented by one or more dedicated computers configured by a combination of one or more processors 51 programmed to execute one or more functions, one or more memories 52, and one or more other processors 51 configured with one or more hardware logic circuits. Furthermore, the computer program may be stored in a computer-readable non-transitional substantial storage medium as instructions to be executed by the computer. That is, each of the above functional configurations and processes can also be represented as a computer program including procedures for implementing it, or as a non-transitional substantial storage medium storing said computer program.

[0069] The detection or recognition of image targets may be performed by the ECU installed in camera 2, or by the vehicle control ECU 5. That is, the image target information acquisition unit 502 may receive image target information from the ECU installed in camera 2, or it may generate it itself. The same applies to the radar target information acquisition unit 503.

[0070] Similar expressions such as "acquisition," "calculation," "estimation," "detection," and "detection" can be appropriately substituted for each other within the limits of what is technically consistent. Similarly, "exceeding the threshold" and "above the threshold" can be appropriately substituted for each other within the limits of what is technically consistent. The same applies to "below the threshold" and "below the threshold."

[0071] The ghost detection criteria may be modified to mitigate the ghost detection process. For example, the threshold velocity for the third negation condition may be set to 0 km / h for fusion targets in the transition state, and to a value greater than 0 km / h for fusion targets not in the transition state. Alternatively, the negation condition for ghost detection may be that the number of times an object has been detected as a radar target is greater than a threshold, and for fusion targets in the transition state, this threshold may be smaller than the threshold used for fusion targets not in the transition state. [Explanation of symbols]

[0072] 500 Object Identification Devices 502 Image Target Information Acquisition Unit 503 Radar Target Information Acquisition Unit 504 Fusion Unit 505 Ghost detection unit 506 Transition judgment section 508 Ghost Mitigation Section

Claims

1. Object identification device (500), A first information acquisition unit (502) acquires first target information, which is detection information of an object in the first range (R1), A second information acquisition unit (503) acquires second target information, which is detection information of an object in the second range (R2a, R2b), A fusion unit (504) that generates a fusion target based on the first target information and the second target information, A ghost determination unit (505) that determines whether the fusion target corresponds to a real object or is a ghost, A transition determination unit (506) determines whether the fusion target is in a transition state detected in the overlapping range after being detected in the non-overlapping range, with the overlapping range being defined as the overlapping range (R3a, R3b) among the first range and the second range, and the range outside the overlapping range being defined as the non-overlapping range. An object identification device comprising: a ghost mitigation unit (508) that relaxes the conditions under which a fusion target determined to be in the transition state corresponds to a physical object, compared to the case where it is determined not to be in the transition state.

2. The object identification device according to claim 1, wherein the ghost mitigation unit changes the determination of a fusion target that has been determined to be a ghost by the ghost determination unit and has been determined to be in the transition state by the transition determination unit, from being a ghost to corresponding to an actual object.

3. The object identification device according to claim 1, wherein the ghost mitigation unit relaxes the conditions for fusion targets that are determined to be in the transition state and have been detected in the non-overlapping range more times than a threshold.

4. The object identification device according to claim 1, wherein the ghost mitigation unit relaxes the conditions for the fusion target which is determined to be in the transition state and whose velocity detected in the non-overlapping range is greater than the threshold.

5. An object identification program executed by an object identification device (500), The processing performed by the object identification device is: A process to acquire first target information, which is the detection information of an object in the first range (R1), The process involves acquiring second target information, which is detection information for objects in the second range (R2a, R2b), A process for generating a fusion target based on the first target information and the second target information, A process to determine whether the fusion target corresponds to a real object or a ghost, The process involves determining whether the fusion target is in a transition state detected in the overlapping range after being detected in the non-overlapping range, with the overlapping range of the first and second ranges being defined as the overlapping range (R3a, R3b) and the range outside the overlapping range being defined as the non-overlapping range (R4a, R4b), and then determining whether the fusion target is in a transition state detected in the overlapping range after being detected in the non-overlapping range. An object identification program that includes a process for relaxing the conditions under which a fusion target determined to be in the transition state corresponds to an actual object, compared to the case where it is determined not to be in the transition state.

Images