Object recognition device and object recognition method

Abstract

The object recognition device of the present invention includes a temporary setting unit and an update processing unit. The temporary setting unit sets the position of at least one candidate point on the object based on the specifications of the out-of-vehicle information sensor that detects the object. The update processing unit corrects the position of the detection point relative to the out-of-vehicle information sensor when the out-of-vehicle information sensor detects the object based on the position of the candidate point on the object, and updates the track data representing the object track based on the corrected position of the detection point relative to the out-of-vehicle information sensor.

Description

Technical Field

[0001] The present invention relates to an object recognition device and an object recognition method. Background Art

[0002] Conventionally, an object recognition device is known which matches the position of a detection point when an object is detected by a sensor with a shape model of the object, and determines the position of a track point forming an object track based on the position of the detection point in the shape model of the object (for example, refer to Patent Document 1).

[0003] Prior Art Documents

[0004] Patent Documents

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 2017-215161 Summary of the Invention

[0006] Technical Problem to be Solved by the Invention

[0007] However, in the conventional object recognition device shown in Patent Document 1, depending on the resolution of the sensor, it is sometimes impossible to determine which position of the object the detection point is at. In this case, the position of the detection point cannot be matched with the shape model of the object, and thus the position of the track point in the object cannot be determined. As a result, the accuracy of the object track data representing the object track is reduced.

[0008] The present invention has been made to solve the above problems, and an object thereof is to obtain an object recognition device and an object recognition method capable of improving the accuracy of object track data.

[0009] Technical Means for Solving the Technical Problem

[0010] The object recognition device according to the present invention includes: a provisional setting unit that sets the position of at least one candidate point in the object based on the specifications of a sensor that detects the object; and an update processing unit that corrects the position of a detection point when the sensor detects the object with respect to the sensor based on the position of the candidate point in the object, and updates track data representing the object track based on the corrected position of the detection point with respect to the sensor.

[0011] Advantageous Effects of the Invention

[0012] According to the object recognition device of the present invention, the accuracy of object track data can be improved. Brief Description of the Drawings

[0013] Figure 1 It is a block diagram showing a functional configuration example of a vehicle control system according to Embodiment 1.

[0014] Figure 2 is a diagram showing an example of the relative positional relationship between a sensor and an object Figure 1 .

[0015] Figure 3 is a diagram showing an example of a candidate point that is the first candidate for the position of a detection point in a vehicle corresponding to a Figure 2 vehicle

[0016] Figure 4 is a diagram showing an example of a candidate point that is the second candidate for the position P of a detection point in a vehicle corresponding to a Figure 2 vehicle

[0017] Figure 5 is a diagram showing an example of a candidate point that is another candidate for the position of a detection point in a vehicle

[0018] Figure 6 is a diagram showing a setting example of the reliability of candidate points when N is a natural number Figures 3 to 5 .

[0019] Figure 7 is a diagram showing an example of Figure 1 track data

[0020] Figure 8 is a diagram showing an example of the correction of Figure 1 detection data

[0021] Figure 9 is a diagram showing an example of the update of Figure 8 track data based on Figure 7 detection data

[0022] Figure 10 is a diagram showing an example in which Figure 7 the track data also includes a direction

[0023] Figure 11 is a diagram showing an example in which Figure 7 the track data also includes a height

[0024] Figure 12 is a diagram showing an example in which Figure 7 the track data also includes an upper end position and a lower end position

[0025] Figure 13 is a flowchart explaining the processing related to an Figure 1 object recognition device

[0026] Figure 14 is a flowchart explaining the position correction processing in step S20 of Figure 13 .

[0027] Figure 15 It is a flowchart of a process branched when the determination result in the determination process in step S22 according to Figure 13 is Yes.

[0028] Figure 16 It is a flowchart of a process branched when the determination result in the determination process in step S51 according to Figure 15 is No and the determination result in the determination process in step S54 is Yes.

[0029] Figure 17 It is a flowchart of a process branched when the determination result in the determination process in step S51 according to Figure 15 in Embodiment 2 is No and the determination result in the determination process in step S54 is Yes.

[0030] Figure 18 It is a flowchart of a process branched when the determination result in the determination process in step S51 according to Figure 15 in Embodiment 3 is No and the determination result in the determination process in step S54 is Yes.

[0031] Figure 19 It is a flowchart of a process branched when the determination result in the determination process in step S51 according to Figure 15 in Embodiment 4 is No and the determination result in the determination process in step S54 is Yes.

[0032] Figure 20 It is a flowchart of the position correction process in step S20 according to Figure 13 in Embodiment 5.

[0033] Figure 21 It is a diagram showing an example of the hardware structure.

[0034] Figure 22 It is a diagram showing another example of the hardware structure. Specific Embodiments

[0035] Embodiment 1.

[0036] Figure 1 It is a block diagram showing an example of the functional structure of the vehicle control system according to Embodiment 1. As Figure 1 shown, the vehicle control system includes a plurality of vehicle exterior information sensors 1, a plurality of vehicle information sensors 2, an object recognition device 3, a notification control device 4, and a vehicle control device 5.

[0037] Each of the plurality of out-vehicle information sensors 1 is mounted on the vehicle. For example, among the plurality of out-vehicle information sensors 1, some of the out-vehicle information sensors 1 are individually mounted inside the front bumper, inside the rear bumper, and on the vehicle compartment side of the windshield. The out-vehicle information sensor 1 mounted inside the front bumper observes an object located in front of or on the side of the vehicle. The out-vehicle information sensor 1 mounted inside the rear bumper observes an object located behind or on the side of the vehicle.

[0038] In addition, the out-vehicle information sensor 1 mounted on the vehicle compartment side of the windshield is arranged next to the interior rearview mirror. The out-vehicle information sensor 1 next to the interior rearview mirror on the vehicle compartment side of the windshield observes an object located in front of the vehicle.

[0039] Thus, each of the plurality of out-vehicle information sensors 1 mounted on the vehicle is a sensor capable of acquiring information about an object around the vehicle as detection data dd. Each detection data dd about an object around the vehicle acquired by each of the plurality of out-vehicle information sensors 1 is integrated into detection data DD and generated. The detection data DD is generated in a data structure capable of being provided to the object recognition device 3. The detection data DD includes at least one piece of information related to the position P of at least one detection point DP relative to the out-vehicle information sensor 1.

[0040] The out-vehicle information sensor 1 observes an object by detecting an arbitrary point on the surface of the object as a detection point. Each detection point DP represents each point in the object observed by the out-vehicle information sensor 1 around the vehicle. For example, the out-vehicle information sensor 1 irradiates the surroundings of the vehicle with light as irradiation light and receives the reflected light reflected at each reflection point on the object. Each of these reflection points corresponds to each detection point DP.

[0041] In addition, according to the measurement principle of the out-vehicle information sensor 1, the information about the object observable at the detection point DP is different. As the types of the out-vehicle information sensor 1, a millimeter-wave radar, a laser sensor, an ultrasonic sensor, an infrared sensor, a camera, etc. can be used. In addition, the description of the ultrasonic sensor and the infrared sensor is omitted.

[0042] For example, millimeter-wave radars are respectively mounted on the front bumper and the rear bumper of the vehicle. The millimeter-wave radar has one transmitting antenna and a plurality of receiving antennas. The millimeter-wave radar can measure the distance and relative speed to an object. For example, the distance and relative speed to an object are measured by the FMCW (Frequency Modulation Continuous Wave) method. Therefore, based on the distance and relative speed to an object measured by the millimeter-wave radar, the position P of the detection point DP relative to the out-vehicle information sensor 1 and the speed V of the detection point DP can be observed.

[0043] In addition, in the following description, the speed V of the detection point DP can be the relative speed between the host vehicle and the object, or can be the speed based on the absolute position by further using GPS.

[0044] The millimeter-wave radar can measure the azimuth angle of the object. The azimuth angle of the object is measured based on the phase difference of each radio wave received by each of the multiple receiving antennas. Therefore, the direction θ of the object can be observed based on the azimuth angle of the object measured by the millimeter-wave radar.

[0045] Thus, by using the millimeter-wave radar, as information related to the object, in addition to the position P of the detection point DP relative to the vehicle external information sensor 1, the detection data DD including the speed V of the detection point DP and the direction θ of the object can also be observed. Among the position P of the detection point DP relative to the vehicle external information sensor 1, the speed V of the detection point DP, and the direction θ of the object, the speed V of the detection point DP and the direction θ of the object are respectively dynamic elements for determining the state of the object. Each of these dynamic elements is an object determination element.

[0046] In addition, in the FMCW-type millimeter-wave radar, when measuring the relative speed with the object, the frequency shift caused by the Doppler effect between the frequency of the transmitted signal and the frequency of the received signal, that is, the Doppler frequency, is detected. Since the detected Doppler frequency is proportional to the relative speed with the object, the relative speed can be derived from the Doppler frequency.

[0047] Furthermore, the speed resolution of the millimeter-wave radar is determined by the resolution of the Doppler frequency. The resolution of the Doppler frequency is the reciprocal of the observation time of the received signal. Therefore, the longer the observation time, the higher the resolution of the Doppler frequency. Therefore, the longer the observation time, the higher the speed resolution of the millimeter-wave radar.

[0048] For example, when the host vehicle is traveling on a highway, compared with the case where the host vehicle is traveling on an ordinary road, the observation time of the millimeter-wave radar is set longer. Therefore, the speed resolution of the millimeter-wave radar can be set higher. Therefore, in the case where the host vehicle is traveling on a highway, compared with the case where the host vehicle is traveling on an ordinary road, the change in speed can be observed faster. Thus, the objects around the host vehicle can be observed faster.

[0049] In addition, the range resolution of the millimeter-wave radar is defined as dividing the speed of light by the modulation frequency bandwidth. Therefore, the wider the modulation frequency bandwidth, the higher the range resolution of the millimeter-wave radar.

[0050] For example, when the vehicle is traveling in a parking lot, the modulation frequency bandwidth is set wider compared to when the vehicle is traveling on an ordinary road or a highway. Therefore, the distance resolution of the millimeter-wave radar can be set higher. When the distance resolution of the millimeter-wave radar is set higher, the minimum unit distance that can be detected becomes finer around the vehicle, so that adjacent objects arranged side by side can be distinguished from each other.

[0051] For example, when pedestrians and vehicles exist as objects around the vehicle, there is a state in which pedestrians with low reflection intensity and vehicles with high reflection intensity of the electromagnetic wave irradiated from the millimeter-wave radar coexist. Even in this state, the electromagnetic wave reflected from the pedestrian is not absorbed by the electromagnetic wave reflected from the vehicle, so that the pedestrian can be detected.

[0052] The laser sensor is installed outside the vehicle, for example, on the roof of the vehicle. As the laser sensor, for example, LIDAR (Light Detection And Ranging) is installed outside the vehicle on the roof of the vehicle. LIDAR has a plurality of light projecting units, one light receiving unit, and an arithmetic unit. The plurality of light projecting units are arranged at a plurality of angles in the vertical direction in front of the moving direction of the vehicle.

[0053] LIDAR adopts the TOF (Time Of Flight) method. Specifically, the plurality of light projecting units in LIDAR have a function of radially projecting laser light while rotating in the horizontal direction during a preset light projection time period. The light receiving unit in LIDAR has a function of receiving the reflected light from an object during a preset light receiving time period. The arithmetic unit in LIDAR has a function of obtaining the round-trip time that is the difference between the light projection time in the plurality of light projecting units and the light receiving time in the light receiving unit. The arithmetic unit in LIDAR has a function of obtaining the distance to the object based on this round-trip time.

[0054] LIDAR has a function of also measuring the direction to the object by obtaining the distance to the object. Therefore, from the measurement result measured by LIDAR, the position P of the detection point DP with respect to the vehicle exterior information sensor 1, the speed V of the detection point DP, and the direction θ of the object can be observed.

[0055] Thus, using LIDAR, as information related to the object, in addition to the position P of the detection point DP with respect to the vehicle exterior information sensor 1, detection data DD including the speed V of the detection point DP and the direction θ of the object can be observed. As described above, among the position P of the detection point DP with respect to the vehicle exterior information sensor 1, the speed V of the detection point DP, and the direction θ of the object, the speed V of the detection point DP and the direction θ of the object are respectively object determination elements.

[0056] In addition, the speed resolution of LIDAR is determined by the emission interval of the pulses that make up the laser. Therefore, the shorter the emission interval of the pulses that make up the laser, the higher the speed resolution of LIDAR.

[0057] For example, when the vehicle is traveling on a highway, compared with the case where the vehicle is traveling on an ordinary road, by setting the emission interval of the pulses that make up the laser irradiated by LIDAR to be shorter, the speed resolution of LIDAR can be set higher. Therefore, when the vehicle is traveling on a highway, compared with the case where the vehicle is traveling on an ordinary road, the change in speed can be observed faster. Thus, the objects around the vehicle can be observed faster.

[0058] In addition, the distance resolution of LIDAR is determined by the pulse width of the pulses that make up the laser. Therefore, the shorter the pulse width of the pulses that make up the laser, the higher the distance resolution of LIDAR.

[0059] For example, when the vehicle is traveling in a parking lot, compared with the case where the vehicle is traveling on an ordinary road or a highway, the pulse width of the pulses that make up the laser irradiated from LIDAR is set to be shorter. Thus, the distance resolution of LIDAR can be set to be higher. When the distance resolution of LIDAR is set to be higher, the minimum unit distance that can be detected becomes finer around the vehicle, so adjacent objects arranged side by side can be distinguished from each other.

[0060] For example, when pedestrians and vehicles exist as objects around the vehicle, there is a state where pedestrians with low reflection intensity and vehicles with high reflection intensity for the laser irradiated from LIDAR are mixed. Even in this state, the reflected light from the pedestrians is not absorbed by the reflected light from the vehicles, so the pedestrians can be detected.

[0061] The camera is installed beside the interior rearview mirror on the vehicle cabin side of the windshield. For example, a monocular camera is used as the camera. The monocular camera has a shooting element. The shooting element is, for example, a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal Oxide Semiconductor) image sensor. The monocular camera continuously detects the presence and distance of an object in units of pixels in a two-dimensional space orthogonal to the shooting direction of the shooting element. For example, the monocular camera includes a structure that adds primary color filters of red, green, and blue to the lens. Through such a structure, the distance can be obtained based on the parallax of the light split by the primary color filters. Therefore, from the measurement results measured by the camera, the position P of the detection point DP relative to the vehicle exterior information sensor 1, the width W of the object, and the length L of the object are observed.

[0062] As described above, according to the camera, as information related to the object, in addition to the position P of the detection point DP relative to the vehicle exterior information sensor 1, detection data DD including the width W and length L of the object can also be observed. Among the position P of the detection point DP relative to the vehicle exterior information sensor 1, the width W of the object, and the length L of the object, the width W and length L of the object are static elements that determine the size of the object. Each of these static elements is an object determination element.

[0063] In addition to the monocular camera, the camera can also use a TOF camera, a stereo camera, an infrared camera, etc.

[0064] The multiple vehicle information sensors 2 have the function of detecting vehicle information of the own vehicle such as vehicle speed, steering angle, and yaw rate as the own vehicle data cd. The own vehicle data cd is generated in a data structure that can be provided to the object recognition device 3.

[0065] The object recognition device 3 includes a time measurement unit 31, a data reception unit 32, a temporary setting unit 33, a prediction processing unit 34, a correlation processing unit 35, and an update processing unit 36. In addition, the time measurement unit 31, the data reception unit 32, the temporary setting unit 33, the prediction processing unit 34, the correlation processing unit 35, and the update processing unit 36 have functions implemented by a CPU that executes a program stored in a non-volatile memory or a volatile memory.

[0066] The time measurement unit 31 has the function of measuring the time of the object recognition device 3. The time measurement unit 31 generates the measured time as a common time CT. The common time CT is generated in a data structure that can be provided to the data reception unit 32.

[0067] The data reception unit 32 has the function of an input interface.

[0068] Specifically, the data receiving unit 32 has a function of receiving the detection data dd from each of the vehicle exterior information sensors 1. Each detection data dd is integrated by the data receiving unit 32 as the detection data DD. The data receiving unit 32 has a function of generating the detection data DD by associating the common time CT generated by the time measurement unit 31 with the detection data DD as the associated time RT RT . The detection data DD RT is generated in a data structure that can be respectively provided to the temporary setting unit 33 and the related processing unit 35.

[0069] When the detection data dd is received from the vehicle exterior information sensor 1, the data receiving unit 32 determines that the detection data dd can be obtained. The data receiving unit 32 sets the fault flag indicating a fault in the corresponding vehicle exterior information sensor 1 to 0, and generates the detection data DD RT .

[0070] Here, when the fault flag is set to 0, it indicates that no fault has occurred in the corresponding vehicle exterior information sensor 1. Here, when the fault flag is set to 0, it indicates that no fault has occurred in the corresponding vehicle exterior information sensor 1.

[0071] On the other hand, when the detection data dd is not received from the vehicle exterior information sensor 1, the data receiving unit 32 determines that the detection data dd cannot be obtained, sets the fault flag to 1, and does not generate the detection data DD RT .

[0072] When the detection data dd is received from the vehicle exterior information sensor 1, the data receiving unit 32 determines the validity of the detection data dd. When it is determined that the detection data dd is not valid, the data receiving unit 32 determines that the detection data dd cannot be obtained, and sets the validity flag indicating that the detection data dd corresponding to the corresponding vehicle exterior information sensor 1 is not valid to 0. When the data receiving unit 32 determines that the detection data dd is valid, it determines that the detection data dd can be obtained, and sets the above-mentioned validity flag to 1.

[0073] Thus, it is possible to refer to the determination result of whether the detection data dd has been obtained in the data receiving unit 32 by referring to at least one of the fault flag and the validity flag.

[0074] In addition, the data receiving unit 32 has a function of receiving the own vehicle data cd from the vehicle information sensor 2. The data receiving unit 32 has a function of generating the own vehicle data CD by associating the common time CT generated by the time measurement unit 31 with the own vehicle data cd as the associated time RT RT . The own vehicle data CD RT is generated in a data structure that can be provided to the prediction processing unit 34.

[0075] The temporary setting unit 33 has a function of setting the position HP of at least one candidate point DPH in the object based on the resolution of the vehicle exterior information sensor 1 that detects the object. The temporary setting unit 33 has a function of generating temporary setting data DH including the position HP of at least one candidate point DPH. The temporary setting data DH is generated in a data structure that can be provided by the temporary setting unit 33 to the relevant processing unit 35.

[0076] In addition, the resolution of the vehicle exterior information sensor 1 is included in the specifications of the vehicle exterior information sensor 1.

[0077] Specifically, according to the specifications of the vehicle exterior information sensor 1, attributes related to the operation setting of the vehicle exterior information sensor 1, attributes related to the configuration state of the vehicle exterior information sensor 1, etc. are determined. Attributes related to the operation setting of the vehicle exterior information sensor 1 are an observable measurement range, the resolution of the measurement range, the sampling frequency, etc. Attributes related to the configuration status of the vehicle exterior information sensor 1 are the possible configuration angles of the vehicle exterior information sensor 1, the durable ambient temperature of the vehicle exterior information sensor 1, the measurable distance between the vehicle exterior information sensor 1 and the observation object, etc.

[0078] The prediction processing unit 34 has a function of receiving the own vehicle data CD RT from the data receiving unit 32. The prediction processing unit 34 has a function of receiving the track data TD RT-1 from the update processing unit 36. The track data TD RT-1 is associated with the previous association time RT, which is the one before the current association time RT in the track data TD, that is, the association time RT - 1. The prediction processing unit 34 has the own vehicle data CD RT based on the association time RT and the track data TD RT-1 at the association time RT - 1, and generates prediction data TD RT of the track data TD RTpred at the association time RT through a known algorithm. A known algorithm is, for example, an algorithm such as a Kalman filter that can estimate the center point of an object with a time series change based on observed values.

[0079] The relevant processing unit 35 has a function of receiving the detection data DD RT , the temporary setting data DH including the position HP of the candidate point DPH, and the prediction data TD RT of the track data TD RTpred . The relevant processing unit 35 has a function of determining the detection data DD RT and the prediction data TD of the track data TD RTpredThe function of determining relevance. Use algorithms such as SNN (Simple Nearest Neighbor), GNN (Global Nearest Neighbor), and JPDA (Joint Probabilistic Data Association) to determine the detection data DD RT and the track data TD RT of the predicted data TD RTpred whether there is a relevant relationship.

[0080] Specifically, based on whether the Mahalanobis distance is included within the gate range to determine the detection data DD RT and the track data TD RT of the predicted data TD RTpred whether there is a relevant relationship. Based on the detection data DD RT the position P of the detection point DP included in it relative to the vehicle external information sensor 1 and the track data TD RT of the predicted data TD RTpred the position P of the center point of the object included in it to derive the Mahalanobis distance. When the derived Mahalanobis distance is included within the gate range, it is determined that the detection data DD RT and the track data TD RT of the predicted data TD RTpred have a relevant relationship. When the derived Mahalanobis distance is not included within the gate range, it is determined that the detection data DD RT and the track data TD RT of the predicted data TD RTpred have no relevant relationship.

[0081] The gate range is set to the observable range of the vehicle external information sensor 1. The observable range in the vehicle external information sensor 1 varies according to the type of the vehicle external information sensor 1. Therefore, the gate range varies according to the type of the vehicle external information sensor 1.

[0082] The correlation processing unit 35 has the function of determining the correspondence between the detection data DD RT and the track data TD RT of the predicted data TD RTpred when there is a correlation. The correlation processing unit 35 has the function of generating the correlation data RD RT and the track data TD RT of the predicted data TD RTpred when there is a corresponding relationship. The correlation processing unit 35 has the function of generating the correlation data RD RT which is the detection data DD RT the temporary setting data DH including the position HP of the candidate point DPH, and the track data TD RT RT ​Predicted data TD RTpred It is obtained by integrating with the data on the determined corresponding relationship. Related data RD RT It is generated into a data structure that can be provided by the related processing unit 35 to the update processing unit 36.

[0083] The update processing unit 36 has the function of receiving the related data RD RT The update processing unit 36 has the function of updating the track data TD based on the position P of the detection point DP and the position HP of the candidate point DPH RT The function of updating the track data TD RT The details of the function will be described later.

[0084] The notification control device 4 has the function of receiving the track data TD RT The notification control device 4 has the function of generating notification data based on the track data TD RT The notification data is data that determines the content of the notification, and is generated in a format corresponding to the device of the output destination. The notification control device 4 outputs the notification data to a display (not shown), thereby causing the display to notify the content of the notification data. Thus, the content of the notification data is visually notified to the driver in the vehicle compartment. The notification control device 4 outputs the notification data to a speaker, thereby causing the speaker to notify the content of the notification data. Thus, the content of the notification data is audibly notified to the driver in the vehicle compartment.

[0085] The vehicle control device 5 has the function of receiving the track data TD output by the update processing unit 36 RT The vehicle control device 5 has the function of controlling the operation of the vehicle based on the track data TD RT The vehicle control device 5 controls the operation of the vehicle based on the track data TD RT to avoid an object.

[0086] Figure 2 It shows Figure 1 An example of the relative position relationship between the out-of-vehicle information sensor 1 and the object.

[0087] Here, the point located at the center when observing the out-of-vehicle information sensor 1 from the front is set as the origin O. The horizontal axis in the left-right direction passing through the origin O is set as the Ys axis. In the Ys axis, when observing the out-of-vehicle information sensor 1 from the front, the right direction is set as the positive direction. The vertical axis in the up-down direction passing through the origin O is set as the Zs axis. In the Zs axis, when observing the out-of-vehicle information sensor 1 from the front, the up direction is set as the positive direction. The axis in the front-back direction passing through the origin O and orthogonal to the Ys axis and the Zs axis is set as the Xs axis. In the Xs axis, the front of the out-of-vehicle information sensor 1 is set as the positive direction.

[0088] AsFigure 2 As shown by the dashed line in Figure 2 , the observable range of the out-vehicle information sensor 1 is divided into a plurality of imaginary resolution units. The resolution units are determined based on the resolution of the out-vehicle information sensor 1. The resolution units are obtained by dividing the observable range of the out-vehicle information sensor 1 according to the angular resolution and the distance resolution of the out-vehicle information sensor 1. As described above, the angular resolution and the distance resolution of the out-vehicle information sensor 1 vary according to the measurement principle of the out-vehicle information sensor 1.

[0089] Each resolution unit is determined by the minimum detection range MR(i, j). Here, i determines the position of the resolution unit along the circumferential direction with respect to the origin O. j determines the position of the resolution unit along the radial direction of the concentric circles with respect to the origin O. Therefore, the number of i varies according to the angular resolution of the out-vehicle information sensor 1. Thus, as the angular resolution of the out-vehicle information sensor 1 becomes higher, the maximum number of i increases. On the other hand, the number of j varies according to the distance resolution of the out-vehicle information sensor 1. Thus, as the distance resolution of the out-vehicle information sensor 1 becomes higher, the maximum number of j increases. Regarding the positive and negative signs of i, the clockwise direction with respect to the Xs axis is set as the positive circumferential direction, and the counterclockwise direction with respect to the Xs axis is set as the negative circumferential direction.

[0090] When the out-vehicle information sensor 1 detects the vehicle Ca, the detection point DP(Ca) is included in the minimum detection range MR(3, 3). The minimum detection range MR(3, 3) is set to a size that only includes the rear left side of the vehicle Ca. Therefore, since the positional relationship between the position P of the detection point DP(Ca) and the vehicle Ca is determined, the position P of the detection point DP(Ca) on the vehicle Ca is determined to be at the rear left side of the vehicle Ca. In addition, since the detection point DP(Ca) is included in the minimum detection range MR(3, 3), the position P of the detection point DP(Ca) with respect to the out-vehicle information sensor 1 is determined to be the position P of the nearest point with the shortest distance from the out-vehicle information sensor 1 to the vehicle Ca.

[0091] On the other hand, when the out-vehicle information sensor 1 detects the vehicle Cb, the detection point DP(Cb) is included in the minimum detection range MR(2, 7). If compared along the radial direction of the concentric circles with respect to the origin O, the minimum detection range MR(2, 7) is farther from the origin O than the minimum detection range MR(3, 3). The minimum detection range MR(i, j), that is, the resolution unit is farther from the origin O along the radial direction of the concentric circles, the lower the angular resolution of the out-vehicle information sensor 1. Therefore, the angular resolution of the out-vehicle information sensor 1 in the minimum detection range MR(2, 7) is lower than the angular resolution of the out-vehicle information sensor 1 in the minimum detection range MR(3, 3).

[0092] In addition, the minimum detection range MR(2, 7) is set to a size that encompasses the entire rear of the vehicle Cb. Therefore, it is impossible to determine at which position P within the entire rear of the vehicle Cb the position P of the detection point DP(Cb) is located. Consequently, the positional relationship between the position P of the detection point DP(Cb) and the vehicle Cb cannot be determined. Thus, the position P of the detection point DP(Cb) on the vehicle Cb cannot be determined.

[0093] Therefore, a process for determining the position P of the detection point DP(Cb) on the vehicle Cb will be described.

[0094] Figure 3 is a diagram showing an example of a candidate point DPH(1) that is the first candidate for the position P of the detection point DP(C Figure 2 ) corresponding to the vehicle Ca of model1 on the vehicle C model1 ). When the out-of-vehicle information sensor 1 detects the vehicle C model1 as an object, the detection point DP(C model1 ) is included in the minimum detection range MR(3, 3). The minimum detection range MR(3, 3) is set to a size that encompasses only the left rear of the vehicle C model1 . Therefore, as described above, the nearest point is assumed to be the position P of the detection point DP(C model1 ) on the vehicle C model1 . When the nearest point is assumed to be the position P of the detection point DP(C model1 ) on the vehicle C model1 , the position HP of the candidate point DPH(1) becomes the first candidate for the position P of the detection point DP(C model1 ) on the vehicle C model1 .

[0095] In other words, in Figure 3 an example, the position HP of the candidate point DPH(1) is the first candidate for the position P of the detection point DP(C model1 ) on the vehicle C model1 .

[0096] Figure 4 is a diagram showing an example of a candidate point DPH(2) that is the second candidate for the position P of the detection point DP(C Figure 2 ) corresponding to the vehicle Cb of model1 on the vehicle C model1 . When the out-of-vehicle information sensor 1 detects the vehicle C model1 as an object, the detection point DP(C model1 ) is included in the minimum detection range MR(2, 7). The minimum detection range MR(2, 7) is set to encompass the vehicle C model1The size of the entire rear. Therefore, as described above, it is impossible to determine which position P of the detection point DP(C model1 ) in the vehicle C model1 is among the entire rear of the vehicle C. When it is impossible to determine which position P of the detection point DP(C model1 ) in the vehicle C model1 is among the entire rear of the vehicle C, the position HP of the candidate point DPH(2) becomes the second candidate for the position P of the detection point DP(C model1 ) on the vehicle C. The position HP of the candidate point DPH(2) is assumed to be the central point of the rear surface of the rear part of the vehicle C model1 . The central point of the rear surface is the point located at the center when observing the rear part of the vehicle C model1 from the front. model1 That is, in

[0097] one example, the position HP of the candidate point DPH(2) is the second candidate for the position P of the detection point DP(C Figure 4 ) on the vehicle C model1 . model1

[0098] Figure 5 is a diagram showing an example of the candidate point DPH(3) that represents another candidate for the position P of the detection point DP(C model1 ) in the vehicle C model1 . When the vehicle exterior information sensor 1 detects the vehicle C model1 as an object, the detection point DP(C model1 ) is included in the minimum detection range MR(-1, 7). For example, compared with the minimum detection range MR(-1, 3), the minimum detection range MR(-1, 7) is farther from the origin O. Therefore, the angular resolution of the vehicle exterior information sensor 1 in the minimum detection range MR(-1, 7) is lower than that of the vehicle exterior information sensor 1 in the minimum detection range MR(-1, 3).

[0099] Specifically, the minimum detection range MR(-1, 7) is set to include the size of the entire front of the vehicle C model1 . Therefore, it is impossible to determine which position P of the detection point DP(C model1 ) in the vehicle C model1 is among the entire front of the vehicle C. When it is impossible to determine which position P of the detection point DP(C model1 ) in the vehicle C model1 is among the entire front of the vehicle C, the position HP of the candidate point DPH(3) becomes another candidate for the position P of the detection point DP(C model1 ) on the vehicle C. The position HP of the candidate point DPH(3) is assumed to be the vehicle C model1 . model1 ​The central point on the front surface of the front part. The central point on the front surface is the point located at the center when the vehicle C is observed from the front. model1 When looking at the front part of the vehicle.

[0100] In other words, in Figure 5 One example, the position HP of the candidate point DPH(3) is another candidate for the position P of the detection point DP(C model1 ) on the vehicle C. model1 )

[0101] Refer to Figure 3 And Figure 4 , when the out-vehicle information sensor 1 is a millimeter-wave radar that monitors the front of the own vehicle, the respective positions HP of the candidate point DPH(1) and the candidate point DPH(2) become candidates for the position P of the detection point DP(C model1 ) on the vehicle C. model1 )

[0102] In addition, refer to Figure 4 , if the out-vehicle information sensor 1 is a camera that monitors the front of the own vehicle, the position HP of the candidate point DPH(2) becomes a candidate for the position P of the detection point DP(C model1 ) on the vehicle C. model1 )

[0103] In addition, if referring to Figure 3 And Figure 5 , then when the out-vehicle information sensor 1 is a millimeter-wave radar that monitors the rear of the own vehicle, the respective positions HP of the candidate point DPH(1) and the candidate point DPH(3) become candidates for the position P of the detection point DP(C model1 ) on the vehicle C. model1 )

[0104] Thus, in the case where there are multiple candidate points DPH for the position P of the detection point DP(C model1 ), if the process of selecting one candidate point DPH from the multiple candidate points DPH(N) is not performed, the position P of the detection point DP(C model1 ) in the vehicle C cannot be determined. Therefore, the process of selecting one candidate point DPH from the multiple candidate points DPH(N) and adopting it as the candidate for the position P of the detection point DP(C model1 ) in the vehicle C will be described. model1 ) in the vehicle C. model1 )

[0105] Figure 6 Is a diagram showing an example of setting the reliability DOR(N) of the candidate point DPH(N) when N is a natural number. In Figures 3 to 5 One example, the position HP of the candidate point DPH(3) is another candidate for the position P of the detection point DP(C Figure 6In one example, for the reliability DOR(N), a real number greater than or equal to 0 and less than or equal to 1 is set. As described above, if the out-vehicle information sensor 1 is a millimeter-wave radar that monitors the front of the own vehicle, the candidate points DPH(1) and DPH(2) become the detection points DP(C model1 on vehicle C model1 ).

[0106] Therefore, by comparing the reliability DOR(1) for the candidate point DPH(1) and the reliability DOR(2) for the candidate point DPH(2), either the candidate point DPH(1) or the candidate point DPH(2) is selected and set as the candidate for the position P of the detection point DP(C model1 on vehicle C model1 ). Thus, either the candidate point DPH(1) or the candidate point DPH(2) is adopted.

[0107] Specifically, as described above, the further the resolution unit is from the origin O along the radial direction of the concentric circles, the lower the angular resolution of the out-vehicle information sensor 1. In other words, the closer the resolution unit is to the origin O along the radial direction of the concentric circles, the higher the angular resolution of the out-vehicle information sensor 1.

[0108] Therefore, if the distance from the out-vehicle information sensor 1 to the detection point DP(C model1 ) is short, the rear part of vehicle C model1 will not be buried in the resolution unit. Therefore, if the distance from the out-vehicle information sensor 1 to the detection point DP(C model1 ) is short, the reliability DOR is high.

[0109] In other words, the reliability DOR of the candidate point DPH is obtained based on the distance from the out-vehicle information sensor 1 to the detection point DP.

[0110] Therefore, when the distance from the out-vehicle information sensor 1 to the detection point DP(C model1 ) is less than Figure 6 the determination threshold distance D TH1 , the reliability DOR(1) for the candidate point DPH(1) is set to 1, and the reliability DOR(2) for the candidate point DPH(2) is set to 0. At this time, the reliability DOR(1) is higher than the reliability DOR(2), so the reliability DOR(1) is selected. When the reliability DOR(1) is selected and set, the candidate point DPH(1) corresponding to the reliability DOR(1) is adopted. The position HP of the candidate point DPH(1) in vehicle C model1 is the position P of the nearest point in vehicle C model1 .

[0111] Therefore, based on the position HP of the candidate point DPH(1) adopted, it is assumed that vehicle C model1 the position P of the detection point DP(C model1 ) on vehicle C model1 is located at the position P of the nearest point on vehicle C

[0112] In other words, when the distance from the out-of-vehicle information sensor 1 to the detection point DP(C model1 ) is less than Figure 6 the determination threshold distance D TH1 among the multiple candidate points DPH(N), the position HP of the candidate point DPH(1) is adopted as the candidate for the position P of the detection point DP(C model1 ) on vehicle C model1 . Thus, it is assumed that the position P of the detection point DP(C model1 ) on vehicle C model1 is located at the position P of the nearest point on vehicle C model1 .

[0113] On the other hand, if the distance from the out-of-vehicle information sensor 1 to the detection point DP(C model1 ) is far, the rear part of vehicle C model1 will also be buried in the resolution unit. Therefore, if the distance from the out-of-vehicle information sensor 1 to the detection point DP(C model1 ) is far, the reliability DOR is low.

[0114] Therefore, when the distance from the out-of-vehicle information sensor 1 to the detection point DP(C model1 ) is Figure 6 the determination threshold distance D TH2 or more, the reliability DOR(1) for the candidate point DPH(1) is set to 0, and the reliability DOR(2) for the candidate point DPH(2) is set to 1. At this time, since the reliability DOR(2) is higher than the reliability DOR of the reliability DOR(1), the reliability DOR(2) is selected. When the reliability DOR(2) is selected and set, the candidate point DPH(2) corresponding to the reliability DOR(2) is adopted. The position HP of the candidate point DPH(2) in vehicle C model1 is the position P of the center point of the rear surface on vehicle C model1 .

[0115] Therefore, based on the position HP of the candidate point DPH(2) adopted, it is assumed that vehicle C model1 the position P of the detection point DP(C model1 ) on vehicle C model1 is located at the position P of the center point of the rear surface on vehicle C

[0116] In other words, when the distance from the out-of-vehicle information sensor 1 to the detection point DP(Cmodel1 ) is the distance of Figure 6 The determination threshold distance D TH2 In the above case, among the multiple candidate points DPH(N), the position HP of the candidate point DPH(2) is used as the vehicle C model1 The detection point DP(C model1 ) as the candidate for the position P. Thus, assuming the vehicle C model1 The detection point DP(C model1 ) is located at the position P of the vehicle C model1 At the position P of the central point of the rear surface on.

[0117] In addition, Figure 6 The determination threshold distance D TH1 Is set to the distance from the origin O along the radial direction of the concentric circle and includes Figure 3 Or Figure 5 The distance of the minimum detection range MR(3, 3). That is, Figure 6 The determination threshold distance D TH1 Is set to the distance from the origin O along the radial direction of the concentric circle and includes Figure 3 , Figure 4 And Figure 5 The distance of the minimum detection range MR(i, 3).

[0118] On the other hand, Figure 6 The determination threshold distance D TH2 Is set to the distance from the origin O along the radial direction of the concentric circle and includes Figure 4 The distance of the minimum detection range MR(2, 7). That is, Figure 6 The determination threshold distance D TH2 Is set to the distance from the origin O along the radial direction of the concentric circle and includes Figure 3 , Figure 4 And Figure 5 The distance of the minimum detection range MR(i, 7).

[0119] In other words, the determination threshold distance D TH2 Is set to a distance farther from the origin O than the determination threshold distance D TH1 . Specifically, the reliability DOR(1) is set to 1 when it is less than the determination threshold distance D TH1 , and starts to decrease when it is above the determination threshold distance D TH1 , and is set to 0 when it is above the judgment threshold distance D TH2 . On the other hand, the reliability DOR(2) is set to 0 when it is less than the determination threshold distance D TH1 , and starts to increase when it is above the determination threshold distance D TH1 , and at the judgment threshold distance D TH2is set to 1 when it is above. Thus, the reliability DOR(1) and the reliability DOR(2) are respectively set to show opposite trends when less than the determination threshold distance D TH1 and the determination threshold distance D TH2 above. The determination threshold distance D is respectively determined based on the ratio of the distance resolution to the angle resolution of the vehicle exterior information sensor 1 TH1 above and less than the determination threshold distance D TH2 for the reliability DOR(1) and the reliability DOR(2).

[0120] Figure 7 is a diagram showing an example of the track data TD Figure 1 The track data TD includes the position P of the center point on the vehicle C model2 the speed V of the center point on the vehicle C model2 the width W of the vehicle C model2 and the length L of the vehicle C model2 These four. Among the position P of the center point on the vehicle C model2 the speed V of the center point on the vehicle C model2 the width W of the vehicle C model2 and the length L of the vehicle C model2 Among these four, the speed V of the center point on the vehicle C model2 the width W of the vehicle C model2 and the length L of the vehicle C model2 These three are object determination elements. The position P of the center point on the vehicle C model2 and the speed V of the center point on the vehicle C model2 represent the state of an object that can be observed by a millimeter wave radar or a lidar. The width W of the vehicle C model2 and the length L of the vehicle C model2 represent the size of an object that can be observed by a camera.

[0121] Therefore, the track data TD is data formed by integrating the observation results of multiple different types of vehicle exterior information sensors 1. For example, the track data TD is configured as vector data such as TD(P, V, W, L).

[0122] Figure 8 is a diagram showing a correction example of the detection data DD Figure 1 Each object determination element included in the detection data DD corresponds to each object determination element included in the track data TD. Specifically, the position P of the detection point DP relative to the vehicle exterior information sensor 1, the speed V of the detection point DP, the width W of the vehicle C model2 and the length L of the vehicle C model2 Among these, the speed V of the detection point DP, the width W of the vehicle C model2 and the width W of the vehicle Cmodel2 The length L is included in the detection data DD as an object determination element.

[0123] Therefore, for example, like the track data TD, the detection data DD is constituted as vector data such as DD(P, V, W, L).

[0124] Figure 8 In one example, after the position P of the detection point DP in the detection data DD before correction relative to the vehicle exterior information sensor 1 is determined based on the position HP of the candidate point DPH(1), as the corrected detection data DD before it is corrected to the center point on the object. Based on this detection data DD after the corrected position P of the detection point DP included therein relative to the vehicle exterior information sensor 1, after the track data TD is updated. Figure 7 That is to say, the update processing unit 36 corrects the position P of the detection point DP relative to the vehicle exterior information sensor 1 based on the position HP of the candidate point DPH on the object, and updates the track data TD representing the object track based on the corrected position P of the detection point DP relative to the vehicle exterior information sensor 1.

[0125] Specifically, when the number of candidate points DPH corresponding to one detection point DP is multiple, as a previous stage of updating the track data TD representing the object track, the update processing unit 36 corrects the position P of the detection point DP relative to the vehicle exterior information sensor 1 based on the respective reliability DORs of the multiple candidate points DPH and the respective positions HP of the multiple candidate points DPH on the object.

[0126] More specifically, the update processing unit 36 corrects the position P of the detection point DP relative to the vehicle exterior information sensor 1 based on the position HP of the candidate point DPH with the highest reliability DOR among the multiple candidate points DPH on the object.

[0127] For example, when the candidate point DPH with the highest reliability DOR is the candidate point DPH(1), the candidate point DPH(1) is adopted. The position HP of the candidate point DPH(1) is, as described above, the position P of the nearest point on the vehicle C

[0128] model2 Thus, it is assumed that the position P of the detection point DP on the vehicle C becomes the position P of the nearest point on the vehicle C model2 model2 model2 model2

[0129] In Figure 8 one example, this nearest point corresponds to the left rear end on the vehicle C model2 model2 model2 ​The coordinates of the position P at the left rear end on the [vehicle] are based on the origin O of the vehicle exterior information sensor 1. Vehicle C model2 The coordinates of the position P at the left rear end on the [vehicle] are determined by the coordinates of the detection point DP relative to the position P of the vehicle exterior information sensor 1. If the coordinates of the position P at the left rear end on Vehicle C model2 are determined, then by using the width W and length L of Vehicle C detected by the vehicle exterior information sensor 1, the correction amount from the position P at the left rear end on Vehicle C model2 to the center point on Vehicle C is accurately determined. Thus, the position P of the center point on Vehicle C is determined via the position HP of the candidate point DPH(1) from the position P of the detection point DP model2 on Vehicle C model2 to the position P of the center point on Vehicle C model2 .

[0130] Specifically, in the position P of the detection point DP relative to the vehicle exterior information sensor 1 included in the detection data DD before correction before , the position P in the Xs-axis direction Xs is added to 1 / 2 of the length L of Vehicle C model2 . Further, in the position P of the detection point DP relative to the vehicle exterior information sensor 1 included in the detection data DD before correction before , from the position P in the Ys-axis direction Ys is subtracted 1 / 2 of the width W of Vehicle C model2 . As a result, the position P of the center point on Vehicle C is determined via the position HP of the candidate point DPH from the position P of the detection point DP model2 .

[0131] In addition, for example, when the candidate point DPH with the highest reliability DOR is the candidate point DPH(2), the candidate point DPH(2) is adopted. The position HP of the candidate point DPH(2) is, as described above, the position P of the center point of the rear surface. Thus, assuming that the position P of the detection point DP on Vehicle C model2 is the position P of the center point of the rear surface on Vehicle C model2 .

[0132] Therefore, the position P of the center point of the rear surface on Vehicle C model2 is based on the origin O of the vehicle exterior information sensor 1. The position P of the center point of the rear surface on Vehicle C model2 is determined by the coordinates of the detection point DP relative to the position P of the vehicle exterior information sensor 1. If the coordinates of the position P of the center point of the rear surface on Vehicle C model2 are determined, then by using the width W detected by the vehicle exterior information sensor 1 and the length L of Vehicle C detected by the vehicle exterior information sensor 1, the correction amount from Vehicle C model2 to the center point on Vehicle C is accurately determined. Thus, from the position P of the center point of the rear surface on Vehicle C model2 to the center point on Vehicle C model2The position P of the central point on the rear surface to the vehicle C model2 The correction amount of the central point on the vehicle C. Thus, the position P of the central point on the vehicle C is determined from the position P of the detection point DP via the position HP of the candidate point DPH(2). model2 The position P of the central point on the vehicle C.

[0133] Specifically, in the position P included in the detection data DD before correction before the position P in the Xs-axis direction, add half of the length L of the vehicle C Xs to the position P included in the detection data DD before correction model2 In addition, for the position P in the Ys-axis direction among the positions P included in the detection data DD before correction before Since the candidate point DPH(2) is adopted, it remains unchanged. As a result, the position P of the central point on the vehicle C is determined from the position P of the detected detection point DP via the position HP of the candidate point DPH(2). Ys The position P of the central point on the vehicle C. model2 The position P of the central point on the vehicle C.

[0134] In other words, the update processing unit 36 assumes the position P of the detection point DP in the object as the position HP of the selected candidate point DPH. Thus, the position P of the detection point DP on the object is determined as the position HP of the candidate point DPH. As a result, by determining the positional relationship between the object and the position P of the detection point DP, the position P of the detection point DP on the object is determined.

[0135] In addition, the position P of the detection point DP relative to the vehicle exterior information sensor 1 is observed. Therefore, if the positional relationship between the position P of the detection point DP on the object and the position P of the center point of the object is determined, the position P of the detection point DP relative to the vehicle exterior information sensor 1 can be corrected to the position P of the center point of the object.

[0136] Therefore, the update processing unit 36 obtains the correction amount for correcting the position P of the detection point DP determined in the object to the position P of the center point of the object.

[0137] The update processing unit 36 corrects the position P of the detection point DP in the object to the position P of the center point of the object by using the obtained correction amount. Thus, the update processing unit 36 corrects the position P of the detection point DP relative to the vehicle exterior information sensor 1. The update processing unit 36 updates the track data TD representing the object track based on the corrected position P of the detection point DP relative to the vehicle exterior information sensor 1.

[0138] However, as described above in detail, depending on the type of the vehicle exterior information sensor 1, specifically, depending on the measurement principle of the vehicle exterior information sensor 1, the object determination elements included in the observable detection data DD are different. The object determination elements determine at least one of the state and size of the object as described above.

[0139] Therefore, the update processing unit 36 corrects the position P of the detection point DP with respect to the vehicle exterior information sensor 1 based on an object determination factor that determines at least one of the state and size of the object. The update processing unit 36 updates the track data TD based on the corrected position P of the detection point DP with respect to the vehicle exterior information sensor 1.

[0140] For example, when the detection data DD includes only the position P of the detection point DP with respect to the vehicle exterior information sensor 1 and the speed V of the detection point DP, it is assumed that the position P of the detection point DP is the position HP of the candidate point DPH. Thus, via the position HP of the candidate point DPH, the position P of the detection point DP and the vehicle C model2 are determined in terms of their positional relationship. As a result, since the position P of the detection point DP on the vehicle C model2 is determined, via the position P of the detection point DP on the vehicle C model2 the correction amount for correcting the position P of the detection point DP with respect to the vehicle exterior information sensor 1 to the position P of the center point on the vehicle C model2 is obtained. Using this correction amount, the position P of the detection point DP on the vehicle C model2 is corrected to the position P of the center point on the vehicle C model2 to correct the position P of the detection point DP with respect to the vehicle exterior information sensor 1. The position P of this center point is the corrected position P of the detection point DP with respect to the vehicle exterior information sensor 1. The track data TD is updated based on the position P of this center point.

[0141] In addition, for example, when the detection data DD includes only the position P of the detection point DP with respect to the vehicle exterior information sensor 1, the speed V of the detection point DP, and the vehicle width W of the vehicle C model2 for the position P of the detection point DP in the Ys-axis direction Ys it is determined as the position P of the center point in the Ys-axis direction of the vehicle C model2 and for the position P of the detection point DP in the Xs-axis direction Xs it is assumed to be the position P in the Xs-axis direction of the candidate point DPH Xs . Thus, via the position P of the center point in the Ys-axis direction on the vehicle C model2 and the position P in the Xs-axis direction of the candidate point DPH Xs the position P of the detection point DP and the vehicle C model2 are determined in terms of their positional relationship. As a result, since the position P of the detection point DP on the vehicle C model2 is determined, therefore via the position P of the detection point DP on the vehicle C model2 the correction amount for correcting the position P of the detection point DP with respect to the vehicle exterior information sensor 1 to the position P of the center point on the vehicle C model2 is obtained. Using this correction amount, bymodel2 The position P of the detection point DP on the vehicle C is corrected to model2 The position P of the detection point DP relative to the vehicle exterior information sensor 1 is corrected based on the position P of the center point on the vehicle exterior information sensor 1. The position P of the center point is the corrected position P of the detection point DP relative to the vehicle exterior information sensor 1. The track data TD is updated based on the position P of the center point.

[0142] In addition, for example, the detection data DD only includes the position P of the detection point DP relative to the vehicle exterior information sensor 1, the speed V of the detection point DP, and the vehicle C. model2 In the case of a length L, for the position P of the detection point DP in the Xs axis direction Xs , determined to be vehicle C model2 The position P of the central point in the Xs axis direction, the position P of the detection point DP in the Ys axis direction Ys , the Ys-axis position P of the candidate point DPH is determined Ys Thus, through vehicle C model2 The position P of the center point in the Xs-axis direction and the position P of the candidate point DPH in the Ys-axis direction Ys , determine the position P of the detection point DP and the vehicle C model2 As a result, due to the positional relationship of vehicle C model2 The position of the detection point DP on the vehicle C is determined, so model2 The position P of the detection point DP on the vehicle C is obtained and the position P of the detection point DP relative to the vehicle exterior information sensor 1 is corrected to model2 The correction amount is calculated by calculating the correction amount of the position P of the center point on the vehicle C. model2 The position P of the detection point DP on the vehicle C is corrected to model2 The position P of the detection point DP relative to the vehicle exterior information sensor 1 is corrected based on the position P of the center point on the vehicle exterior information sensor 1. The position P of the center point is the corrected position P of the detection point DP relative to the vehicle exterior information sensor 1. The track data TD is updated based on the position P of the center point.

[0143] For example, the detection data DD only includes the position P of the detection point DP relative to the vehicle exterior information sensor 1, the speed V of the detection point DP, and the vehicle C. model2 In the case of width W and length L, the position P of the detection point DP in the Ys axis direction is Ys , determined to be vehicle C model2 The position P of the center point in the Ys-axis direction on the detection point DP is Xs , determined to be vehicle C model2 The position P of the center point in the Xs axis direction. model2 The position P of the center point in the Ys-axis direction and the vehicle Cmodel2 The position P of the central point in the Xs-axis direction on the vehicle C is determined by the position P of the detection point DP and the vehicle C model2 As a result, due to the positional relationship of vehicle C model2 The position P of the detection point DP on the vehicle C is determined, so model2 The position P of the detection point DP on the vehicle C is obtained and the position P of the detection point DP relative to the vehicle exterior information sensor 1 is corrected to model2 The correction amount is calculated by calculating the correction amount of the position P of the center point on the vehicle C. model2 The position P of the detection point DP on the vehicle C is corrected to model2 The position P of the detection point DP relative to the vehicle exterior information sensor 1 is corrected based on the position P of the center point on the vehicle exterior information sensor 1. The position P of the center point is the corrected position P of the detection point DP relative to the vehicle exterior information sensor 1. The track data TD is updated based on the position P of the center point.

[0144] The track data TD is updated through tracking processing such as least squares method, Kalman filter, particle filter, etc.

[0145] In addition, instead of using the position HP of the candidate point DPH with the highest reliability DOR, the position HP of the candidate point DPH obtained by weighted averaging the positions P of multiple candidate points DPH using the reliability DOR may be used. Specifically, the update processing unit 36 ​​weighted averages the positions P of multiple candidate points DPH in the object according to the respective reliability DORs, thereby correcting the position P of the detection point DP relative to the vehicle exterior information sensor 1.

[0146] Next, an example of changing the update content of the track data TD by combining the object identification element included in the detection data DD and the object identification element included in the track data TD will be described. Figure 9 It is shown based on Figure 8 The detection data DD Figure 7 Figure 1 shows an example of updating the track data of . Figure 9 In one example, a setting value is individually set in advance corresponding to the object identification factor that cannot be acquired from the vehicle exterior information sensor 1. In addition, when the object identification factor cannot be acquired from the vehicle exterior information sensor 1, it is processed as if there is no object identification factor.

[0147] When the update processing unit 36 ​​is able to obtain at least one of the width W and length L of the object as an object identification factor from the external vehicle information sensor 1, if the detection data DD and the track data TD are correlated, the track data TD is updated based on the object identification factor obtained from the external vehicle information sensor 1.

[0148] On the other hand, when the update processing unit 36 cannot obtain at least one of the width W and the length L of the object as an object determination factor from the vehicle exterior information sensor 1, it determines the value of the object determination factor that cannot be obtained from the vehicle exterior information sensor 1 based on the set value that is separately preset in advance for each of the width W and the length L corresponding to the object and that corresponds to the object determination factor that cannot be obtained from the vehicle exterior information sensor 1.

[0149] Figure 10 is a diagram showing an example in which Figure 7 the track data TD also includes the direction θ. The width W of the vehicle C model2 is the size of the vehicle C perpendicular to the direction θ of the vehicle C. model2 The length L of the vehicle C model2 is the size of the vehicle C parallel to the direction θ of the vehicle C. model2 The length L of the vehicle C model2 is the size of the vehicle C parallel to the direction θ of the vehicle C. model2

[0150] According to the measurement principle of the vehicle exterior information sensor 1, when the direction θ of the vehicle C can be obtained, the direction θ of the vehicle C is added as an object determination factor of the detection data DD. According to the measurement principle of the vehicle exterior information sensor 1, when the direction θ of the vehicle C cannot be obtained, the direction θ is set according to the vehicle C, that is, the ground speed of the object changes the direction θ. model2 The direction θ of the vehicle C model2 is added as an object determination factor of the detection data DD. According to the measurement principle of the vehicle exterior information sensor 1, when the direction θ of the vehicle C cannot be obtained, according to the vehicle C model2 that is, the ground speed of the object changes the direction θ of the setting. model2

[0151] When the ground speed of the object is not zero, the direction θ of the vehicle C model2 is observable, so the direction as the ground speed vector can be obtained. On the other hand, when the ground speed of the object is zero, that is, when the object is a stationary object, the initial angle 0 [deg] is included in the temporary setting data DH as a preset set value.

[0152] Figure 11 is a diagram showing an example in which Figure 7 the track data TD also includes the height H. The direction θ of the vehicle C model2 is parallel to the road surface RS and perpendicular to the height H of the vehicle C. model2

[0153] According to the measurement principle of the vehicle exterior information sensor 1, when the height H of the vehicle C can be obtained, the height H of the vehicle C is added as an object determination factor of the detection data DD. According to the measurement principle of the vehicle exterior information sensor 1, when the height H of the vehicle C cannot be obtained, the initial height 1.5 [m] is included in the temporary setting data DH as a preset set value. model2 The height H of the vehicle C model2 is added as an object determination factor of the detection data DD. According to the measurement principle of the vehicle exterior information sensor 1, when the height H of the vehicle C cannot be obtained, the initial height 1.5 [m] is included in the temporary setting data DH as a preset set value. model2 ​​​​

[0154] Figure 12 shows that Figure 7 The track data TD also includes the upper end Z H position and the lower end Z L position of an example. Among them, the upper end Z H position ≥ the lower end Z L position. Here, when the lower end Z L position is greater than 0 [m], it is determined that the object is an object existing above the object such as a signboard or a road sign.

[0155] When the positions of the upper end Z H and the lower end Z L can be obtained according to the measurement principle of the out-of-vehicle information sensor 1, the positions of the upper end Z H and the lower end Z L are added as detection elements of the detection data DD. When the positions of the upper end Z H and the lower end Z L cannot be obtained according to the measurement principle of the out-of-vehicle information sensor 1, the initial upper end Z HDEF = 1.5 [m] and the initial lower end Z LDEF = 0 [m] are included in the temporary setting data DH as preset setting values.

[0156] Figure 13 is a flowchart for explaining the processing performed by Figure 1 the object recognition device 3. In step S11, the time measurement unit 31 determines whether the current time has reached the processing time tk. When it is determined by the time measurement unit 31 that the current time has reached the processing time tk, the processing in step S11 transfers to the processing in step S12. When it is determined by the time measurement unit 31 that the current time has not reached the processing time tk, the processing in step S11 continues.

[0157] In step S12, the data receiving unit 32 receives the detection data dd from each out-of-vehicle information sensor 1. Then, the processing in step S12 transfers to the processing in step S13.

[0158] In step S13, the data receiving unit 32 associates the time when the detection data dd is received from each out-of-vehicle information sensor 1 as the current correlation time RT with the detection data DD. Then, the processing in step S13 transfers to the processing in step S14.

[0159] In step S14, the data receiving unit 32 marks all the out-of-vehicle information sensors 1 as unused. Then, the processing in step S14 transfers to the processing in step S15.

[0160] In step S15, the data receiving unit 32 determines whether there is an unused vehicle exterior information sensor 1. When the data receiving unit 32 determines that there is an unused vehicle exterior information sensor 1, the process of step S15 transfers to the process of step S16. When the data receiving unit 32 determines that there is no unused vehicle exterior information sensor 1, the process of step S15 does not transfer to other processes and the process ends.

[0161] In step S16, the prediction processing unit 34 calculates prediction data TD of the track data TD at the current association time RT based on the track data TD at the previous association time RT. RTpred Next, the process of step S16 transfers to the process of step S17.

[0162] In step S17, the temporary setting unit 33 selects the used vehicle exterior information sensor 1. Next, the process of step S17 transfers to the process of step S18.

[0163] In step S18, the temporary setting unit 33 sets the position HP of at least one candidate point DPH on the object detected by the selected vehicle exterior information sensor 1 based on the resolution of the selected vehicle exterior information sensor 1. Next, the process of step S18 transfers to the process of step S19.

[0164] In step S19, the correlation processing unit 35 determines the detection data DD RT and the prediction data TD of the track data TD RTpred whether they are correlated. When the correlation processing unit 35 determines that the detection data DD RT and the prediction data TD of the track data TD RTpred are correlated, the process of step S19 transfers to the process of step S20. When the correlation processing unit 35 determines that the detection data DD RT and the prediction data TD of the track data TD RTpred are not correlated, the process of step S19 transfers to the process of step S22.

[0165] In step S20, the update processing unit 36 uses Figure 14 to perform the position correction process described later. Next, the process of step S20 transfers to the process of step S21.

[0166] In step S21, the update processing unit 36 updates the track data TD at the current association time RT based on the corrected position P of the detection point DP with respect to the vehicle exterior information sensor 1 at the current association time RT. Next, the process of step S21 transfers to the process of step S22.

[0167] In step S22, the temporary setting unit 33 determines whether the detection data DD includes object determination elements. When the temporary setting unit 33 determines that the detection data DD includes object determination elements, the processing of step S22 transfers to the processing of step S51 Figure 15 described later. When the temporary processing unit 33 determines that the detection data DD does not include object determination elements, the processing of step S22 transfers to the processing of step S23.

[0168] In step S23, the data reception unit 32 marks the selected vehicle exterior information sensor 1 as used. Then, the processing of step S23 transfers to the processing of step S15.

[0169] Figure 14 is a flowchart Figure 13 of the position correction process in step S20. In step S31, the update processing unit 36 determines whether the number of candidate points DPH is multiple. When the update processing unit 36 determines that the number of candidate points DPH is multiple, the processing in step S31 transfers to the processing in step S32. When the update processing unit 36 determines that the number of candidate points DPH is not multiple, the processing of step S31 transfers to the processing of step S37.

[0170] In step S32, the update processing unit 36 obtains the reliability DOR of each of the multiple candidate points DPH based on the distance from the selected vehicle exterior information sensor 1 to the detection point DP. Then, the processing of step S32 transfers to the processing of step S33.

[0171] In step S33, the update processing unit 36 determines whether to perform weighted averaging. When the temporary setting unit 33 determines to perform weighted averaging, the processing of step S33 transfers to the processing of step S34. When the temporary setting unit 33 determines not to perform weighted averaging, the processing of step S33 transfers to the processing of step S36.

[0172] In step S34, the update processing unit 36 performs weighted averaging on the positions P of the multiple candidate points DPH in the object according to the respective reliabilities DOR, thereby obtaining the correction amount of the position P of the detection point DP relative to the vehicle exterior information sensor 1. Then, the processing of step S34 transfers to the processing of step S35.

[0173] In step S35, the update processing unit 36 corrects the position P of the detection point DP included in the detection data DD at the current association time RT relative to the vehicle exterior information sensor 1 based on the correction amount of the position P of the detection point DP relative to the vehicle exterior information sensor 1. Then, the processing of step S35 does not transfer to other processing, and the position correction process ends.

[0174] In step S36, the update processing unit 36 obtains a correction amount of the position P of the detection point DP with respect to the vehicle external information sensor 1 based on the position HP of the candidate point DPH having the highest reliability DOR among the positions HP of the plurality of candidate points DPH. Subsequently, the processing of step S36 transfers to the processing of step S35.

[0175] In step S37, the update processing unit 36 adopts the set candidate point DPH. Subsequently, the processing of step S37 transfers to the processing of step S38.

[0176] In step S38, the update processing unit 36 obtains a correction amount of the position P of the detection point DP with respect to the vehicle external information sensor 1 based on the position HP of the adopted candidate point DPH. Subsequently, the processing of step S38 transfers to the processing of step S35.

[0177] Figure 15 is a flowchart illustrating the processing branched according to the case where the determination result in the determination processing in step S22 according to Figure 13 is yes. In step S51, the temporary setting unit 33 determines whether the detection data dd received from the selected vehicle external information sensor 1 includes the speed V of the detection point DP. When the temporary setting unit 33 determines that the detection data dd received from the selected vehicle external information sensor 1 includes the speed V of the detection point DP, the processing of step S51 transfers to the processing of step S52. When the temporary setting unit 33 determines that the detection data dd received from the selected vehicle external information sensor 1 does not include the speed V of the detection point DP, the processing of step S51 transfers to the processing using Figure 16 step S81 described later.

[0178] In step S52, the correlation processing unit 35 determines whether the detection data DD RT and the predicted data TD of the track data TD RTpred are correlated. When the correlation processing unit 35 determines that the detection data DD RT and the predicted data TD of the track data TD RTpred are correlated, the processing of step S52 transfers to the processing of step S53. When the correlation processing unit 35 determines that the detection data DD RT and the predicted data TD of the track data TD RTpred are not correlated, the processing of step S52 transfers to the processing of step S54.

[0179] In step S53, the update processing unit 36 updates the speed V of the center point on the object included in the track data TD at the current association time RT based on the speed V of the detection point DP at the current association time RT. Subsequently, the processing of step S53 transfers to the processing of step S54.

[0180] In step S54, the temporary setting unit 33 determines whether the detection data dd received from the selected vehicle exterior information sensor 1 contains other object identification elements. If the temporary setting unit 33 determines that the detection data dd received from the selected vehicle exterior information sensor 1 contains other object identification elements, the processing of step S54 is transferred to the user. Figure 16 The processing of step S81 will be described later. When the temporary setting unit 33 determines that the detection data dd received from the selected vehicle exterior information sensor 1 does not include other object identifying elements, the processing of step S54 is transferred to the processing of step S55.

[0181] In step S55, the data receiving unit 32 marks the selected vehicle exterior information sensor 1 as used. Then, the process of step S55 returns to Figure 13 The process of step S15.

[0182] Figure 16 It is explained based on Figure 15 The flowchart of the process that branches when the determination result of the determination process in step S51 is NO and when the determination result of the determination process in step S54 is YES. In step S81, the temporary setting unit 33 determines whether at least one of the remaining object identification elements, i.e., the width W and the length L of the object, contained in the detection data dd received from the selected vehicle exterior information sensor 1 has been acquired as the object identification element from the vehicle exterior information sensor 1. When the temporary setting unit 33 determines that at least one of the remaining object identification elements, i.e., the width W and the length L of the object, contained in the detection data dd received from the selected vehicle exterior information sensor 1 has been acquired as the object identification element from the vehicle exterior information sensor 1, the process of step S81 is transferred to the process of step S82. When the temporary setting unit 33 determines that at least one of the remaining object identification elements, i.e., the width W and the length L of the object, contained in the detection data dd received from the selected vehicle exterior information sensor 1 has not been acquired as the object identification element from the vehicle exterior information sensor 1, the process of step S81 is transferred to the process of step S85.

[0183] In step S82, the correlation processing unit 35 determines the detection data DD RT and the predicted data TD of the track data TD RTpred Whether there is correlation. The correlation processing unit 35 determines whether the detection data DD RT and the predicted data TD of the track data TD RTpred If there is a correlation, the process of step S82 is transferred to the process of step S83. RT and the predicted data TD of the track data TD RTpred If there is no correlation, the process of step S82 is transferred to the process of step S84.

[0184] In step S83, the update processing unit 36 updates the object determination elements included in the track data TD at the current association time RT that correspond to the object determination elements obtained from the vehicle external information sensor 1 among the width W and length L of the object at the current association time RT. Subsequently, the processing of step S83 proceeds to the processing of step S84.

[0185] In step S84, the data reception unit 32 marks the selected vehicle external information sensor 1 as having been used. Subsequently, the processing of step S84 returns Figure 13 to the processing of step S15.

[0186] In step S85, the update processing unit 36 determines the object determination elements that cannot be obtained from the vehicle external information sensor 1 based on the set values that are separately set in advance corresponding to the width W and length L of the object and that correspond to the object determination elements that cannot be obtained from the vehicle external information sensor 1. Subsequently, the processing of step S85 proceeds to the processing of step S86.

[0187] In step S86, the update processing unit 36 updates the object determination elements included in the track data TD at the current association time RT that correspond to the determined object determination elements based on the values of the determined object determination elements. Subsequently, the processing of step S86 proceeds to the processing of step S84.

[0188] According to the above description, in the object recognition device 3, the temporary setting unit 33 sets the position HP of at least one candidate point DPH in the object based on the specifications of the vehicle external information sensor 1 that has detected the object. Further, in the object recognition device 3, the update processing unit 36 corrects the position of the detection point DP relative to the vehicle external information sensor 1 when the vehicle external information sensor 1 has detected the object based on the position HP of the candidate point DPH on the object. The update processing unit 36 updates the track data TD representing the object track based on the corrected position P of the detection point DP relative to the vehicle external information sensor 1.

[0189] As described above, the out-vehicle information sensor 1 has different resolutions according to the specifications of the out-vehicle information sensor 1. Therefore, the update processing unit 36 corrects the position P of the detection point DP based on the position of the candidate point DPH at the previous stage of updating the track data TD. The temporary setting unit 33 sets the position HP of at least one candidate point DPH on the object based on the specifications of the out-vehicle information sensor 1 that has detected the object at the previous stage of the update processing unit 36 correcting the position P of the detection point DP. Therefore, based on the corrected position P of the detection point DP relative to the out-vehicle information sensor 1 that corrects the deviation caused by the resolution included in the specifications of the out-vehicle information sensor 1, the track data TD can be updated. Thereby, the accuracy of the track data TD of the object can be improved.

[0190] When the number of candidate points DPH corresponding to one detection point DP is plural, the update processing unit 36 corrects the position P of the detection point DP relative to the out-vehicle information sensor 1 based on the respective reliability DORs of the plurality of candidate points DPH and the respective positions P of the plurality of candidate points DPH on the object. Therefore, the position P of the detection point DP relative to the out-vehicle information sensor 1 is corrected on the basis of also considering the reliability DOR of the position HP of the candidate point DPH. Thereby, each of the plurality of candidate points DPH can be effectively utilized.

[0191] In addition, the update processing unit 36 corrects the position P of the detection point DP relative to the out-vehicle information sensor 1 based on the position HP of the candidate point DPH having the highest reliability DOR among the positions HP of the plurality of candidate points DPH in the object.

[0192] If the number of candidate points DPH in one object is plural, the respective setting accuracies of the positions HP of the plurality of candidate points DPH in one object may be different. Thus, the update processing unit 36 corrects the position P of the detection point DP relative to the out-vehicle information sensor 1 based on the position HP of the candidate point DPH having the largest reliability DOR among the positions HP of the plurality of candidate points DPH in one object. Therefore, the position HP of the candidate point DPH having the highest setting accuracy in one object can be utilized. Thereby, the position HP of the candidate point DPH having the highest setting accuracy among the positions HP of the plurality of candidate points DPH in one object set based on the resolution of the same out-vehicle information sensor 1 can be utilized.

[0193] In addition, the update processing unit 36 performs weighted averaging on the respective positions P of the plurality of candidate points DPH in one object according to the respective reliability DORs, thereby correcting the position P of the detection point DP relative to the out-vehicle information sensor 1.

[0194] If there are multiple candidate points DPH in an object, the setting accuracies of the positions HP of the multiple candidate points DPH in one object are different. Therefore, the update processing unit 36 performs weighted averaging on the positions HP of the multiple candidate points DPH on one object, thereby correcting the position P of the detection point DP with respect to the vehicle external information sensor 1. Therefore, among the multiple candidate points DPH on one object, the influence of the candidate point DPH with a lower reliability DOR is weakened, and the influence of the candidate point DPH with a higher reliability DOR is enhanced. On this basis, the position P of the detection point DP with respect to the vehicle external information sensor 1 can be corrected. Thus, the position P of the detection point DP with respect to the vehicle external information sensor 1 can be corrected on the basis of reflecting the respective reliabilities DOR of the positions HP of the multiple candidate points DPH in one object set according to the resolution of the same vehicle external information sensor 1.

[0195] In addition, the update processing unit 36 obtains each reliability DOR based on the distance from the vehicle external information sensor 1 to the detection point DP.

[0196] The resolution of the vehicle external information sensor 1 becomes different resolutions according to the distance from the vehicle external information sensor 1 to the detection point DP of the detection point DP. For example, when the vehicle external information sensor 1 is composed of a millimeter wave radar, if the distance to the detection point DP is relatively close, the possibility that the detection point DP is the nearest point is relatively high. On the other hand, if the distance to the detection point DP is relatively far, the detection point DP will be buried in the resolution unit. Thus, the detection point DP is assumed to be a reflection point reflected from the center of the object. Therefore, the update processing unit 36 obtains each reliability based on the distance from the vehicle external information sensor 1 to the detection point DP. Thus, the reliability DOR can be obtained based on the performance of the vehicle external information sensor 1.

[0197] In addition, when the update processing unit 36 cannot obtain at least one of the width W and the length L of the object as an object determination element from the vehicle external information sensor 1, the value of the object determination element that cannot be obtained from the vehicle external information sensor is determined based on the set value corresponding to the object determination element that cannot be obtained from the vehicle external information sensor among the set values separately set in advance corresponding to the width W and the length L of the object.

[0198] Therefore, even if the width W and the length L of the object cannot be obtained from the vehicle external information sensor 1, the error can be suppressed and the track data TD can be updated. Thus, the relative position relationship between the own vehicle and the object will not deviate significantly, and therefore the reduction of the autonomous driving accuracy of the own vehicle can be suppressed to the minimum.

[0199] Embodiment 2.

[0200] In Embodiment 2, the description of the same or identical configurations and functions as those in Embodiment 1 is omitted. The difference between Embodiment 2 and Embodiment 1 lies in that according toFigure 15 The process branches based on the case where the determination result of the determination process in step S51 is NO and the case where the determination result of the determination process in step S54 is YES. Other configurations are the same as those in Embodiment 1. That is, other configurations are the same as or equivalent to the configurations and functions in Embodiment 1, and the same reference numerals are assigned to these parts.

[0201] Figure 17 This describes the process according to Embodiment 2 based on Figure 15 This is a flowchart of the process that branches based on the case where the determination result of the determination process in step S51 is NO and the case where the determination result of the determination process in step S54 is YES. In step S91, the temporary setting unit 33 determines whether at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, i.e., the width W, length L, and direction θ of the object, has been obtained from the out-of-vehicle information sensor 1 as an object determination element. When the temporary setting unit 33 determines that at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, i.e., the width W, length L, and direction θ of the object, has been obtained from the out-of-vehicle information sensor 1 as an object determination element, the process of step S91 transfers to the process of step S92. When the temporary setting unit 33 determines that at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, i.e., the width W, length L, and direction θ of the object, cannot be obtained from the out-of-vehicle information sensor 1 as an object determination element, the process of step S91 transfers to the process of step S95.

[0202] In step S92, the correlation processing unit 35 determines whether the detection data DD RT and the predicted data TD of the track data TD RTpred are correlated. When the correlation processing unit 35 determines that the detection data DD RT and the predicted data TD of the track data TD RTpred are correlated, the process of step S92 transfers to the process of step S93. When the correlation processing unit 35 determines that the detection data DD RT and the predicted data TD of the track data TD RTpred are not correlated, the process of step S92 transfers to the process of step S94.

[0203] In step S93, the update processing unit 36 updates the object determination element corresponding to the object determination element obtained from the out-of-vehicle information sensor 1 among the object determination elements included in the track data TD at the current association time RT based on the object determination element of the width W, length L, and direction θ of the object obtained from the out-of-vehicle information sensor 1 at the current association time RT. Then, the process of step S93 transfers to the process of step S94.

[0204] In step S94, the data receiving unit 32 marks the selected vehicle exterior information sensor 1 as used. Then, the process of step S94 returns to Figure 13 the process of step S15.

[0205] In step S95, the update processing unit 36 determines the object determination elements that cannot be obtained from the vehicle exterior information sensor 1 based on the set values corresponding to the object determination elements that cannot be obtained from the vehicle exterior information sensor 1 among the set values separately set in advance corresponding to the width W, length L, and direction θ of the object. Then, the process of step S95 transfers to the process of step S96.

[0206] In step S96, the update processing unit 36 updates the object determination elements corresponding to the determined object determination elements among the object determination elements included in the track data TD at the current association time RT based on the values of the determined object determination elements. Then, the process of step S96 transfers to the process of step S94.

[0207] As described above, in the object recognition device 3, when the update processing unit 36 cannot obtain at least one of the width W, length L, and direction θ of the object as the object determination elements from the vehicle exterior information sensor 1, the update processing unit 36 determines the values of the object determination elements that cannot be obtained from the vehicle exterior information sensor 1 based on the set values corresponding to the object determination elements that cannot be obtained from the vehicle exterior information sensor 1 among the set values separately set in advance corresponding to the width W, length L, and direction θ of the object.

[0208] Therefore, even if the width W, length L, and direction θ of the object cannot be obtained from the vehicle exterior information sensor 1, errors can be suppressed and the track data TD can be updated. As a result, the relative positional relationship between the host vehicle and the object will not deviate significantly, and thus the reduction in the host vehicle's autonomous driving accuracy can be suppressed to the minimum.

[0209] Embodiment 3.

[0210] In Embodiment 3, the description of the structures and functions that are the same as or equivalent to those in Embodiment 1 and Embodiment 2 is omitted. The difference between Embodiment 3 and Embodiment 1 and Embodiment 2 lies in the processes branched according to Figure 15 the case where the determination result of the determination process in step S51 is no and the case where the determination result of the determination process in step S54 is yes. The other structures are the same as those in Embodiment 1 and Embodiment 2. That is, the other structures are the structures and functions that are the same as or equivalent to those in Embodiment 1 and Embodiment 2, and the same reference numerals are assigned to these parts.

[0211] Figure 18 This is to explain the content related to Embodiment 3 according to Figure 15Flowchart of the process branched in the case where the determination result of the determination process in step S51 is NO and the case where the determination result of the determination process in step S54 is YES. In step S101, the temporary setting unit 33 determines whether at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, i.e., the width W, length L, direction θ, and height H of the object, has been obtained from the out-of-vehicle information sensor 1 as an object determination element. When the temporary setting unit 33 determines that at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, i.e., the width W, length L, direction θ, and height H of the object, has been obtained from the out-of-vehicle information sensor 1 as an object determination element, the process of step S101 transfers to the process of step S102. When the temporary setting unit 33 determines that at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, i.e., the width W, length L, direction θ, and height H of the object, has not been obtained from the out-of-vehicle information sensor 1 as an object determination element, the process of step S101 transfers to the process of step S105.

[0212] In step S102, the correlation processing unit 35 determines whether the detection data DD RT and the predicted data TD of the track data TD RTpred are correlated. When the correlation processing unit 35 determines that the detection data DD RT and the predicted data TD of the track data TD RTpred are correlated, the process of step S102 transfers to the process of step S103. When the correlation processing unit 35 determines that the detection data DD RT and the predicted data TD of the track data TD RTpred are not correlated, the process of step S102 transfers to the process of step S104.

[0213] In step S103, the update processing unit 36 updates the object determination element corresponding to the object determination element obtained from the out-of-vehicle information sensor 1 among the object determination elements included in the track data TD at the current association time RT based on the object determination elements of the width W, length L, direction θ, and height H of the object obtained from the out-of-vehicle information sensor 1 at the current association time RT. Then, the process of step S103 transfers to the process of step S104.

[0214] In step S104, the data reception unit 32 marks the selected out-of-vehicle information sensor 1 as used. Then, the process of step S104 returns Figure 13 to the process of step S15.

[0215] In step S105, the update processing unit 36 determines the object determination element that cannot be obtained from the vehicle external information sensor 1 based on the set value corresponding to the object determination element that cannot be obtained from the vehicle external information sensor 1 among the set values separately set in advance corresponding to the width W, length L, direction θ, and height H of the object. Subsequently, the process of step S105 transfers to the process of step S106.

[0216] In step S106, the update processing unit 36 updates the object determination element corresponding to the determined object determination element among the object determination elements included in the track data TD at the current associated time RT based on the value of the determined object determination element. Subsequently, the process of step S106 transfers to the process of step S104.

[0217] As described above, in the object recognition device 3, when the update processing unit 36 cannot obtain at least one of the width W, length L, direction θ, and height H of the object from the vehicle external information sensor 1 as the object determination element, it determines the value of the object determination element that cannot be obtained from the vehicle external information sensor 1 based on the set value corresponding to the object determination element that cannot be obtained from the vehicle external information sensor 1 among the set values separately set in advance corresponding to the width W, length L, direction θ, and height H of the object.

[0218] Therefore, even if the width W, length L, direction θ, and height H of the object cannot be obtained from the vehicle external information sensor 1, it is possible to suppress errors and update the track data TD. As a result, the relative positional relationship between the host vehicle and the object will not deviate significantly, and thus the reduction in the automatic driving accuracy of the host vehicle can be suppressed to the minimum.

[0219] Embodiment 4.

[0220] In Embodiment 4, for the same or equivalent structures and functions as those in Embodiment 1, Embodiment 2, and Embodiment 3, their descriptions are omitted. The difference between Embodiment 4 and Embodiment 1, Embodiment 2, and Embodiment 3 lies in the processes branched according to the case where the determination result of the determination process in step S51 is NO and the case where the determination result of the determination process in step S54 is YES. Other structures are the same as those in Embodiment 1, Embodiment 2, and Embodiment 3. That is, other structures are the same or equivalent structures and functions as those in Embodiment 1, Embodiment 2, and Embodiment 3, and the same reference numerals are assigned to these parts. Figure 15 The following is an explanation of the processes branched according to the case where the determination result of the determination process in step S51 of Embodiment 4 is NO and the case where the determination result of the determination process in step S54 is YES.

[0221] Figure 19 This is an explanation of what Embodiment 4 relates to according to Figure 15A flowchart of a process branched based on the case where the determination result of the determination process in step S51 is NO and the case where the determination result of the determination process in step S54 is YES. In step S111, the temporary setting unit 33 determines whether at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, namely, the width W, length L, direction θ, upper end Z H of the position P and the lower end Z L of the position P has been obtained from the out-of-vehicle information sensor 1 as an object determination element. The temporary setting unit 33 determines whether at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, namely, the width W, length L, direction θ, upper end Z H of the position P and the lower end Z L of the position P has been obtained from the out-of-vehicle information sensor 1 as an object determination element. When at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, namely, the width W, length L, direction θ, upper end Z H of the position P and the lower end Z L of the position P has been obtained from the out-of-vehicle information sensor 1 as an object determination element, the process of step S111 transfers to the process of step S112. The temporary setting unit 33 determines whether at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, namely, the width W, length L, direction θ, upper end Z H of the position P and the lower end Z L of the position P has not been obtained from the out-of-vehicle information sensor 1 as an object determination element. When at least one of the remaining object determination elements included in the detection data dd received from the selected out-of-vehicle information sensor 1, namely, the width W, length L, direction θ, upper end Z

[0222] In step S112, the relevant processing unit 35 determines whether the detection data DD RT and the predicted data TD of the track data TD RTpred are correlated. When the relevant processing unit 35 determines that the detection data DD RT and the predicted data TD of the track data TD RTpred are correlated, the process of step S112 transfers to the process of step S113. When the relevant processing unit 35 determines that the detection data DD RT and the predicted data TD of the track data TD RTpred are not correlated, the process of step S112 transfers to the process of step S114.

[0223] In step S113, the update processing unit 36 updates the object determination elements included in the track data TD at the current association time RT corresponding to the object determination elements obtained from the out-of-vehicle information sensor 1 based on the object determination elements of the width W, length L, direction θ, upper end Z H of the position and the lower end Z L of the position that have been obtained from the out-of-vehicle information sensor 1. Then, the process of step S113 transfers to the process of step S114.

[0224] In step S114, the data receiving unit 32 marks the selected vehicle exterior information sensor 1 as used. Then, the process of step S114 returns Figure 13 to the process of step S15.

[0225] In step S115, the update processing unit 36 determines the object determination elements that cannot be obtained from the vehicle exterior information sensor 1 based on the set values separately set in advance corresponding to the width W, length L, direction θ, upper end Z H of the position and the lower end Z L of the position corresponding to the object determination elements that cannot be obtained from the vehicle exterior information sensor 1. Then, the process of step S115 transfers to the process of step S116.

[0226] In step S116, the update processing unit 36 updates the object determination elements corresponding to the determined object determination elements in the track data TD at the current association time RT based on the values of the determined object determination elements. Then, the process of step S116 transfers to the process of step S114.

[0227] As described above, in the object recognition device 3, when the update processing unit 36 cannot obtain at least one of the width W, length L, direction θ, upper end Z H of the position and the lower end Z L of the position of the object as object determination elements from the vehicle exterior information sensor 1, based on the set values separately set in advance corresponding to the width W, length L, direction θ, upper end Z H of the position and the lower end Z L of the position corresponding to the object determination elements that cannot be obtained from the vehicle exterior information sensor 1, it determines the values of the object determination elements that cannot be obtained from the vehicle exterior information sensor 1.

[0228] Therefore, even if at least one of the width W, length L, direction θ, upper end Z H of the position and the lower end Z L of the position of the object cannot be obtained from the vehicle exterior information sensor 1, it is possible to suppress errors and update the track data TD. Thus, the relative position relationship between the host vehicle and the object will not deviate significantly, and therefore, the reduction in the host vehicle's autonomous driving accuracy can be suppressed to the minimum.

[0229] In addition, if in addition to the width W, length L, direction θ of the object, the position of the upper end Z H and the position of the lower end Z L are also corrected, it is possible to determine whether the object is a stationary object. The stationary object is, for example, a signboard. The stationary object can be a road sign. Therefore, the type of the object can be determined. Thus, the accuracy of the host vehicle's autonomous driving can be further improved.

[0230] Embodiment 5

[0231] In Embodiment 5, for the same or equivalent structures and functions as those in Embodiment 1, Embodiment 2, Embodiment 3, and Embodiment 4, their descriptions are omitted. The difference between Embodiment 5 and Embodiment 1 is that a plurality of candidate points DPH are screened. Other structures are the same as those in Embodiment 1, Embodiment 2, Embodiment 3, and Embodiment 4. That is, other structures are the same or equivalent structures and functions as those in Embodiment 1, Embodiment 2, Embodiment 3, and Embodiment 4, and the same reference numerals are assigned to these parts.

[0232] Figure 20 It illustrates another example of the position correction process in step S20 related to Embodiment 5 Figure 13 The flowchart. In step S161, the update processing unit 36 determines whether the number of candidate points DPH is plural. When the update processing unit 36 determines that the number of candidate points DPH is plural, the process of step S161 transfers to the process of step S162. When the update processing unit 36 determines that the number of candidate points DPH is not plural, the process of step S161 transfers to the process of step S170.

[0233] In step S162, the update processing unit 36 refers to the update log of the track data TD. Then, the process of step S162 transfers to the process of step S163.

[0234] In step S163, the update processing unit 36 determines whether the type of the vehicle exterior information sensor 1 obtained by observing the detection data DD at the current association time RT is different from the type of the vehicle exterior information sensor 1 obtained by observing the detection data DD at the previous association time RT. When the update processing unit 36 determines that the type of the vehicle exterior information sensor 1 obtained by observing the detection data DD at the current association time RT is different from the type of the vehicle exterior information sensor 1 obtained by observing the detection data DD at the previous association time RT, the process of step S163 transfers to the process of step S164. When the update processing unit 36 determines that the type of the vehicle exterior information sensor 1 obtained by observing the detection data DD at the current association time RT is not different from the type of the vehicle exterior information sensor 1 obtained by observing the detection data DD at the previous association time RT, that is, when the type of the vehicle exterior information sensor 1 obtained by observing the detection data DD at the current association time RT is the same as the type of the vehicle exterior information sensor 1 obtained by observing the detection data DD at the previous association time RT, the process of step S163 transfers to the process of step S168.

[0235] In step S164, the update processing unit 36 is based on the prediction data TD of the track data TD RTpredThe accuracy of each of a plurality of candidate points DPH is determined based on the position P of the center point on the object included in [the relevant content] and the position P of the detection point DP included in the detection data DD relative to the vehicle external information sensor 1. Subsequently, the process of step S164 transfers to the process of step S165.

[0236] In step S165, the update processing unit 36 discards the candidate point DPH with the lowest accuracy among the plurality of candidate points DPH. Subsequently, the process of step S165 transfers to the process of step S166.

[0237] In step S166, the update processing unit 36 adopts the candidate point DPH with the highest accuracy among the candidate points DPH that have not been discarded. Subsequently, the process of step S166 transfers to the process of step S167.

[0238] In step S167, the update processing unit 36 corrects the position P of the detection point DP included in the detection data DD at the current association time RT relative to the vehicle external information sensor 1 based on the position HP of the adopted candidate point DPH. Subsequently, the process of step S167 does not transfer to other processes, and the position correction process ends.

[0239] In step S168, the update processing unit 36 calculates the reliability DOR of the candidate point DPH. Subsequently, the process of step S168 transfers to the process of step S169.

[0240] In step S169, the update processing unit 36 adopts the candidate point DPH based on the reliability DOR. Subsequently, the process of step S169 transfers to the process of step S167.

[0241] In step S170, the update processing unit 36 adopts the set candidate point DPH. Subsequently, the process of step S170 transfers to the process of step S167.

[0242] For example, when the vehicle external information sensor 1 is a camera, the detection data dd includes the position P of the detection point DP relative to the vehicle external information sensor 1, the speed V of the detection point DP, and the width W of the object. In addition, when the vehicle external information sensor 1 is a camera, the candidate point DPH(2) becomes a candidate for the position P of the detection point DP on the object. Thus, according to the processes of step S161, step S170, and step S167, based on the position HP of the candidate point DPH(2), the position P of the detection point DP relative to the vehicle external information sensor 1 is corrected.

[0243] On the other hand, when the out-vehicle information sensor 1 is a millimeter-wave radar, the detection data dd includes the position P of the detection point DP relative to the out-vehicle information sensor 1 and the speed V of the detection point DP. In addition, when the out-vehicle information sensor 1 is a millimeter-wave radar, the candidate points DPH(1) and DPH(2) respectively become candidates for the position P of the detection point DP on the object.

[0244] Here, since there is a correlation between the detection data dd of the camera and the track data TD, after performing the processes of step S161, step S170, and step S167, the correlation between the detection data dd of the millimeter-wave radar and the track data TD may also hold.

[0245] Moreover, based on the position P of the detection point DP relative to the out-vehicle information sensor 1 and the position P of the center point on the object, it is sometimes determined that the accuracy of the candidate point DPH(1) is higher than the accuracy of the candidate point DPH(2). In the case where such accuracy is determined, according to the processes of step S164, step S165, and step S166, the candidate point DPH(2) is discarded from the candidates for the position P of the detection point DP on the object, and the candidate point DPH(1) is adopted.

[0246] According to the above description, in the object recognition device 3, the update processing unit 36 discards a part of the multiple candidate points DPH based on the update log of the track data TD.

[0247] The update log of the track data TD includes a log in which at least the position P of the center point of the object is updated along with the movement of the object. The log in which the position P of the center point of the object is updated is associated with the out-vehicle information sensor 1 that detected the object. Therefore, if the update log of the track data TD is referred to, the type of the out-vehicle information sensor 1 used when the position P of the detection point DP relative to the out-vehicle information sensor 1 is corrected can be referred to via the log in which the position P of the center point of the object is updated. Thus, if the type of the out-vehicle information sensor 1 when the object is detected at the detection point DP is determined, the candidate point DPH used when correcting the position P of the detection point DP relative to the out-vehicle information sensor 1 can be determined.

[0248] As described above, if the out-vehicle information sensor 1 is composed of a millimeter-wave radar, the nearest point and the central point are considered as candidate points DPH. In addition, as described above, if the out-vehicle information sensor 1 is composed of a monocular camera, the central point is considered as the candidate point DPH.

[0249] Here, the accuracy of each of the multiple candidate points DPH is determined based on the position P of the center point of the object and the position P of the detection point DP relative to the out-of-vehicle information sensor 1. The position P of the center point of the object and the position P of the detection point DP relative to the out-of-vehicle information sensor 1 change according to the trajectory of the object. For example, according to the positional relationship between the position P of the center point of the object and the position P of the detection point DP relative to the out-of-vehicle information sensor 1, when the Euclidean distance between the position P of the center point of the object and the position P of the detection point DP relative to the out-of-vehicle information sensor 1 is less than Figure 6 the determination threshold distance D TH1 the candidate point DPH with high accuracy is regarded as the closest point to the center point. In this case, the center point in the candidate point DPH is discarded, and the closest point is adopted.

[0250] In addition, Figure 6 the determination threshold distance D TH1 is set within the range where the position P of the detection point DP is not buried by the resolution unit of the out-of-vehicle information sensor 1.

[0251] Furthermore, if the object is a moving object in front of the host vehicle, the center point is the rear center point of the object. If the object is a moving object behind the host vehicle, the center point is the front surface center point of the object.

[0252] Based on the above description, the update processing unit 36 discards a part of the multiple candidate points DPH based on the update log of the trajectory data TD. Thus, the candidate points DPH with high accuracy can be used for the update of the trajectory data TD.

[0253] In addition, in each of the embodiments, a processing circuit for executing the processing of the object recognition device 3 is included. The processing circuit may be dedicated hardware or a CPU (also referred to as a Central Processing Unit: central processing unit, central processing device, processing device, arithmetic device, microprocessor, microcomputer, processor, DSP) that executes a program stored in a memory.

[0254] Figure 21 is a diagram illustrating an example of a hardware structure. In Figure 21 the processing circuit 201 is connected to the bus 202. When the processing circuit 201 is dedicated hardware, the processing circuit 201 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, an ASIC, an FPGA, or a combination thereof. The functions of each part of the object recognition device 3 can be respectively implemented by the processing circuit 201, or the functions of each part can be collectively implemented by the processing circuit 201.

[0255] Figure 22 is a diagram illustrating another example of a hardware structure. In Figure 22In it, the processor 203 and the memory 204 are connected to the bus 202. When the processing circuit is a CPU, the functions of the respective parts of the object recognition device 3 are implemented by software, firmware, or a combination of software and firmware. The software or firmware is expressed in the form of a program and stored in the memory 204. The processing circuit reads out and executes the program stored in the memory 204, thereby implementing the functions of the respective parts. That is, the object recognition device 3 includes a memory 204 for storing the following program, and when this program is executed by the processing circuit, it finally executes the steps of the control time measurement unit 31, the data reception unit 32, the temporary setting unit 33, the prediction processing unit 34, the correlation processing unit 35, and the update processing unit 36. In addition, it can be said that these programs cause a computer to execute the steps or methods for executing the time measurement unit 31, the data reception unit 32, the temporary setting unit 33, the prediction processing unit 34, the correlation processing unit 35, and the update processing unit 36. Here, the memory 204 is equivalent to a non-volatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM, EEPROM, or a magnetic disk, a floppy disk, an optical disk, a compact disc, a mini disc, a DVD, etc.

[0256] In addition, a part of the functions of the respective parts of the object recognition device 3 can be implemented by dedicated hardware, and another part can be implemented by software or firmware. For example, the function of the temporary setting unit 33 can be implemented by a processing circuit as dedicated hardware. In addition, the processing circuit reads out and executes the program stored in the memory 204, thereby being able to implement the function of the correlation processing unit 35.

[0257] Thus, the processing circuit can implement the above-mentioned various functions by using hardware, software, firmware, or a combination thereof.

[0258] Above, in Embodiment 1, an example of the processing for obtaining whether there is a correlation between the detection data DD RT and the track data TD RT by using the SNN algorithm, the GNN algorithm, the JPDA algorithm, etc. RTpred has been described, but it is not particularly limited thereto.

[0259] For example, it is possible to determine whether there is a correlation between the detection data DD RT and the predicted data TD RT of the track data TD RTpred by whether the difference between each detection element included in the detection data DD RT and each track element included in the predicted data TD RT of the track data TD RTpred is within a predetermined error amount e.

[0260] Specifically, the correlation processing unit 35 derives the detection data DD RTThe distance difference between the position P included in the vehicle exterior information sensor 1 and the predicted data TD of the track data TD RT of the predicted data TD RTpred and the position P included therein.

[0261] The correlation processing unit 35 derives the detection data DD RT The speed V included in the track data TD RT of the predicted data TD RTpred and the speed difference between the speed V included therein.

[0262] The correlation processing unit 35 derives the detection data DD RT The azimuth angle included in the track data TD RT of the predicted data TD RTpred and the azimuth difference between the azimuth angles included therein.

[0263] The correlation processing unit 35 obtains the square root of the sum of the squares of the distance difference, the speed difference, and the azimuth difference. When the obtained square root exceeds the error amount e, the correlation processing unit 35 determines that there is no correlation. When the obtained square root is less than or equal to the error amount e, the correlation processing unit 35 determines that there is a correlation. Through such a determination process, it is also possible to determine whether there is a correlation between the detection data DD RT and the track data TD RT of the predicted data TD RTpred or not.

[0264] In addition, for example, the ground speed of the detection point DP can be obtained based on the speed V of the detection point DP. If the ground speed of the detection point DP is obtained, when it is determined that the object detected by the vehicle exterior information sensor 1 is the vehicle C model2 the vehicle C may not be included in the object determination elements of the detection data DD model2 in terms of the width W and the length L. In this case, the width W of the vehicle C model2 is set to 2 [m], and the length L of the vehicle C model2 is set to 4.5 [m]. The width W and the length L of the vehicle C set in this way are also set values separately set in advance corresponding to the object determination elements that cannot be obtained from the vehicle exterior information sensor 1. model2

[0265] In addition, the update processing unit 36 can update the track data TD based on the speed V of the detection point DP when the vehicle exterior information sensor 1 detects an object. Thus, the track data TD can be updated based on the speed V of the detection point DP that takes into account the observation results observed by the vehicle exterior information sensor 1. Thus, the relative position relationship between the host vehicle and the object can be accurately grasped, and the accuracy of the host vehicle's autonomous driving can be further improved.

[0266] ​In addition, the processes of step S81 to step S86 shown in Figure 16 Embodiment 1, the processes of step S91 to step S96 shown in Figure 17 Embodiment 2, the processes of step S101 to step S106 shown in Figure 18 Embodiment 3, and the processes of step S111 to step S116 shown in Figure 19 Embodiment 4 can be executed in parallel by the CPU, respectively.

[0267] Reference Signs Explanation

[0268] 1 Out-of-vehicle information sensor, 2 Vehicle information sensor, 3 Object recognition device, 4 Notification control device, 5 Vehicle control device, 31 Time measurement unit, 32 Data reception unit, 33 Temporary setting unit, 34 Prediction processing unit, 35 Correlation processing unit, 36 Update processing unit.

Claims

1. An object recognition device, characterized in that, comprising: a temporary setting unit that sets positions of at least one candidate point on the object based on specifications of a sensor that detects the object; and an update processing unit that corrects a position of a detection point relative to the sensor when the sensor detects the object based on positions of the candidate points on the object, and updates track data representing a track of the object based on the corrected position of the detection point relative to the sensor.

2. The object recognition device according to claim 1, characterized in that, the temporary setting unit sets positions of at least one of the candidate points on the object based on a resolution included in the specifications of the sensor that detects the object.

3. The object recognition device according to claim 1 or 2, characterized in that, when a number of the candidate points corresponding to one detection point is multiple, the update processing unit corrects the position of the detection point relative to the sensor based on respective reliabilities of the multiple candidate points and positions of the multiple candidate points on the object.

4. The object recognition device according to claim 3, characterized in that, the update processing unit corrects the position of the detection point relative to the sensor based on a position of the candidate point having the highest reliability among positions of the multiple candidate points on the object.

5. The object recognition device according to claim 3, characterized in that, the update processing unit corrects the position of the detection point relative to the sensor by performing weighted averaging on positions of the multiple candidate points on the object according to respective reliabilities.

6. The object recognition device according to any one of claims 3 to 5, characterized in that, the update processing unit obtains respective reliabilities based on a distance from the sensor to the detection point.

7. The object recognition device according to any one of claims 3 to 6, characterized in that, the update processing unit discards a part of the candidate points among the multiple candidate points based on an update log of the track data.

8. The object recognition device according to any one of claims 1 to 7, characterized in that, the update processing unit corrects the position of the detection point relative to the sensor based on an object determination factor that determines at least one of a state and a size of the object.

9. The object recognition device according to claim 8, characterized in that, when at least one of a width and a length of the object cannot be obtained from the sensor as the object determination factor, the update processing unit determines a value of the object determination factor that cannot be obtained from the sensor based on a set value that is separately set in advance corresponding to the width and the length of the object and corresponds to the object determination factor that cannot be obtained from the sensor.

10. The object recognition device according to claim 8, characterized in that, When at least one of the width, length, and orientation of the object cannot be obtained from the sensor as the object determination element, the update processing unit determines the value of the object determination element that cannot be obtained from the sensor based on the set value corresponding to the object determination element that cannot be obtained from the sensor among the set values separately set in advance corresponding to the width, length, and orientation of the object.

11. The object recognition device according to claim 8, wherein: When at least one of the width, length, orientation, and height of the object cannot be obtained from the sensor as the object determination element, the update processing unit determines the value of the object determination element that cannot be obtained from the sensor based on the set value corresponding to the object determination element that cannot be obtained from the sensor among the set values separately set in advance corresponding to the width, length, orientation, and height of the object.

12. The object recognition device according to claim 8, wherein: When at least one of the width, length, orientation, position of the upper end, and position of the lower end of the object cannot be obtained from the sensor as the object determination element, the update processing unit determines the value of the object determination element that cannot be obtained from the sensor based on the set value corresponding to the object determination element that cannot be obtained from the sensor among the set values separately set in advance corresponding to the width, length, orientation, position of the upper end, and position of the lower end of the object.

13. An object recognition method, wherein: comprising: a step of setting the position of at least one candidate point on the object based on the specifications of the sensor that detects the object; and a step of correcting the position of the detection point of the sensor when detecting the object with respect to the sensor based on the position of the candidate point on the object, and updating the track data representing the track of the object based on the corrected position of the detection point with respect to the sensor.

Images