Object Tracking Device

Abstract

To accurately track a moving object at a distance or a small moving object. [Solution] The object tracking device 50 includes a memory unit 12 that stores moving point cloud data classified from point cloud data acquired by a lidar 5, a superposition unit 117 that offsets the position of each measurement point in the moving point cloud data included in past frames stored in the memory unit 12 based on the moving speed and moving direction of each measurement point, and when the moving point cloud data is classified from the point cloud data newly acquired by the lidar 5, superimposes the offset moving point cloud data of the past frame on the moving point cloud data, a detection unit 118 that detects a moving object based on the superimposed moving point cloud data, a vector calculation unit 119 that calculates the movement vector of the moving object based on the positions of the measurement point clouds corresponding to the moving object in the past frames and the current frame, and a tracking unit 120 that determines the movement trajectory of the moving object based on the movement vector.

Description

[Technical Field]

[0001] The present invention relates to an object tracking device that detects and tracks objects around a vehicle. [Background technology]

[0002] Known examples of this type of device include a device that detects and tracks moving objects using three-dimensional point cloud data acquired by a lidar (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7126633 Summary of the Invention [Problem to be solved by the invention]

[0004] However, if point cloud data is used directly for the detection process of moving objects, as in the device described in Patent Document 1, there is a risk that the detection of distant moving objects or small moving objects will be delayed, and these moving objects will not be tracked accurately. [Means for solving the problem]

[0005] An object tracking device according to one aspect of the present invention includes a detector that acquires point cloud data for each point cloud frame containing point cloud data at the same time, the point cloud data including three-dimensional position information and velocity information indicating relative movement velocity at measurement points on the surface of an object contained in the three-dimensional space by irradiating electromagnetic waves into three-dimensional space and receiving reflected waves; a calculation unit that calculates the absolute movement velocity of each of a plurality of measurement points corresponding to the point cloud data based on the velocity information; a classification unit that, when the point cloud data is acquired by the detector, classifies the point cloud data into moving point cloud data for which the absolute value of the absolute movement velocity calculated by the calculation unit is equal to or greater than a predetermined velocity, and static point cloud data other than the moving point cloud data; a memory unit that stores the moving point cloud data classified by the classification unit; a processing unit that performs processing to detect moving objects moving within the three-dimensional space; a vector calculation unit that calculates the movement vector of the moving object detected by the processing unit; and a trajectory acquisition unit that determines the movement trajectory of the moving object based on the movement vector calculated by the vector calculation unit. The processing unit performs an offset process to offset the position of each measurement point in the moving point cloud data corresponding to the past point cloud frame stored in the memory unit based on the moving speed and moving direction of each measurement point estimated based on the speed information of each measurement point, and when the moving point cloud data is classified by the classification unit from the point cloud data included in the new point cloud frame acquired by the detector, it performs an overlay process to overlay the moving point cloud data of the past point cloud frame that has been offset processed on the moving point cloud data, and further performs a process to detect a moving object based on the moving point cloud data after the overlay process, and the vector calculation unit calculates the movement vector of the moving object based on the positions of the measurement point clouds corresponding to the moving object in the past point cloud frame and the new point cloud frame. [Effects of the Invention]

[0006] According to the present invention, it is possible to track a moving object at a distance or a small moving object with high accuracy. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a block diagram showing the configuration of a main part of a vehicle control device including an object tracking device according to an embodiment of the present invention; [Figure 2A] FIG. 2 is a diagram showing an example of a three-dimensional object included in the three-dimensional space around the vehicle. [Figure 2B] FIG. 2B is a plan view of the moving object of FIG. 2A seen from above. [Figure 3A] A diagram showing multiple pedestrians passing by. [Figure 3B] FIG. 2 is a diagram showing an example of XYV data. [Figure 4A] FIG. 2 is a diagram showing an example of a three-dimensional space around the host vehicle. [Figure 4B] FIG. 4B is a diagram showing an example of XYV data corresponding to the three-dimensional space of FIG. 4A. [Figure 4C] FIG. 4B is a diagram showing an example of XYV data corresponding to the three-dimensional space of FIG. 4A. [Figure 5A] FIG. 10 is a diagram showing an example of a measurement point cloud of a past frame superimposed on XYV data of a current frame without offset processing. [Figure 5B] FIG. 10 is a diagram showing an example of superimposed XYV data. [Figure 6] FIG. 10 is a diagram for explaining detection of a moving object. [Figure 7] FIG. 10 is a diagram for explaining calculation of a movement vector of a moving object. [Figure 8] 4 is a flowchart showing an example of processing executed by a CPU of the controller of FIG. 1; DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. An object tracking device according to an embodiment of the present invention can be applied to a vehicle having an automatic driving function, i.e., an automatic driving vehicle. Note that a vehicle to which an object tracking device according to this embodiment is applied may be referred to as a host vehicle to distinguish it from other vehicles. The host vehicle may be an engine vehicle having an internal combustion engine (engine) as a driving source, an electric vehicle having a driving motor as a driving source, or a hybrid vehicle having an engine and a driving motor as driving sources. The host vehicle can run not only in an automatic driving mode in which no driving operation by the driver is required, but also in a manual driving mode in which the driver operates the vehicle.

[0009] When an autonomous vehicle is traveling in an autonomous driving mode (hereinafter referred to as autonomous traveling or autonomous traveling), it recognizes the external environment around the vehicle based on detection data from an onboard detector such as LiDAR (Light Detection and Ranging). Based on the recognition results, the autonomous vehicle generates a traveling trajectory (target trajectory) for a predetermined time from the current time, and controls the traveling actuators so that the vehicle travels along the target trajectory.

[0010] 1 is a block diagram showing the configuration of the main parts of a vehicle control device 100 including an object tracking device. The vehicle control device 100 has a controller 10, a communication unit 1, a positioning unit 2, an internal sensor group 3, a camera 4, a LIDAR 5, and a driving actuator AC. The vehicle control device 100 also has an object tracking device 50 that forms part of the vehicle control device 100. The object tracking device 50 detects objects around the vehicle based on detection data from the LIDAR 5.

[0011] The communication unit 1 communicates with various servers (not shown) via networks including wireless communication networks such as the Internet and mobile phone networks, and acquires map information, driving history information, traffic information, and the like from the servers periodically or at any timing. Networks include not only public wireless communication networks but also closed communication networks established for each specific management area, such as wireless LAN, Wi-Fi (registered trademark), and Bluetooth (registered trademark). The acquired map information is output to the memory unit 12, where it is updated. The positioning unit (GNSS unit) 2 has a positioning sensor that receives positioning signals transmitted from positioning satellites. The positioning satellites are artificial satellites such as GPS satellites and quasi-zenith satellites. The positioning unit 2 measures the current position (latitude, longitude, altitude) of the vehicle using the positioning information received by the positioning sensor.

[0012] The internal sensor group 3 is a collective term for a plurality of sensors (internal sensors) that detect the driving state of the host vehicle. For example, the internal sensor group 3 includes a vehicle speed sensor that detects the vehicle speed of the host vehicle, an acceleration sensor that detects the longitudinal acceleration and the lateral acceleration (lateral acceleration) of the host vehicle, a rotation speed sensor that detects the rotation speed of the driving source, a yaw rate sensor that detects the rotation angular velocity around the vertical axis of the center of gravity of the host vehicle, etc. The internal sensor group 3 also includes sensors that detect the driving operations of the driver in manual driving mode, such as operation of the accelerator pedal, operation of the brake pedal, operation of the steering wheel, etc.

[0013] The camera 4 has an imaging element such as a CCD or CMOS and captures images of the surroundings (front, rear, and sides) of the vehicle. The LIDAR 5 irradiates electromagnetic waves (reflected waves) into the three-dimensional space around the vehicle and detects the external environment around the vehicle based on the reflected waves. More specifically, the electromagnetic waves (laser light, etc.) irradiated by the LIDAR 5 are reflected at a point (measurement point) on the surface of an object, and the distance from the laser source to that point, the intensity of the reflected electromagnetic waves, the relative speed of the object located at that measurement point, etc. are measured. The LIDAR 5 is attached to a predetermined position (front) of the vehicle and scans the electromagnetic waves of the LIDAR 5 horizontally and vertically around the surroundings (front) of the vehicle to detect the position, shape, relative moving speed, etc. of objects ahead of the vehicle (moving objects such as other vehicles and stationary objects such as road surfaces and structures). The objects detected by the LIDAR 5, including people, are called objects. Therefore, moving objects include not only moving vehicles such as automobiles and bicycles, but also moving people (pedestrians, etc.). Note that, hereinafter, the above three-dimensional space is represented by an X axis along the traveling direction of the host vehicle, a Y axis along the width direction of the host vehicle, and a Z axis along the height direction of the host vehicle. Therefore, the above three-dimensional space may be referred to as an XYZ space.

[0014] Actuators AC are driving actuators for controlling the driving of the host vehicle. When the driving source is an engine, actuators AC include a throttle actuator that adjusts the opening of the engine's throttle valve (throttle opening). When the driving source is a driving motor, actuators AC include the driving motor. Actuators AC also include a brake actuator that operates the host vehicle's braking device and a steering actuator that drives the steering device.

[0015] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 includes a computer having an arithmetic unit 11 such as a CPU (microprocessor), a storage unit 12 such as a ROM and a RAM, and other peripheral circuits (not shown) such as an I / O interface. Note that although multiple ECUs with different functions, such as an engine control ECU, a traction motor control ECU, and a braking device ECU, can be provided separately, for convenience, the controller 10 is shown in FIG. 1 as a collection of these ECUs.

[0016] The memory unit 12 stores highly accurate, detailed map information (referred to as high-accuracy map information). The high-accuracy map information includes road position information, road shape (curvature, etc.) information, road gradient information, intersection and branch point position information, number of lanes (driving lanes), lane width and position information for each lane (information on lane center positions and lane boundary lines), position information of landmarks (traffic lights, signs, buildings, etc.) on the map, and road surface profile information such as road surface irregularities. The memory unit 12 also stores various control programs, information such as thresholds used in the programs, and setting information for on-board detectors such as the LIDAR 5.

[0017] The calculation unit 11 has, as its functional configuration, a data acquisition unit 111, an estimation unit 112, a calculation unit 113, a classification unit 114, a generation unit 115, a tentative detection unit 116, a superposition unit 117, a detection unit 118, a vector calculation unit 119, a tracking unit 120, and a driving control unit 121.

[0018] 1, the data acquisition unit 111, the estimation unit 112, the calculation unit 113, the classification unit 114, the generation unit 115, the tentative detection unit 116, the superposition unit 117, the detection unit 118, the vector calculation unit 119, and the tracking unit 120 are included in the object tracking device 50. Details of the data acquisition unit 111, the estimation unit 112, the calculation unit 113, the classification unit 114, the generation unit 115, the tentative detection unit 116, the superposition unit 117, the detection unit 118, the vector calculation unit 119, and the tracking unit 120 included in the object tracking device 50 will be described later.

[0019] In the autonomous driving mode, the driving control unit 121 generates a target trajectory based on the external environment surrounding the vehicle, including the size, position, and relative movement speed of an object detected by the detection unit 118, and the movement trajectory of the object determined by the tracking unit 120. Specifically, the driving control unit 121 generates a target trajectory to avoid collision or contact with an object or to follow the object. The driving control unit 121 controls the actuator AC so that the host vehicle travels along the target trajectory. Specifically, the driving control unit 121 controls the actuator AC along the target trajectory to adjust the accelerator opening and drive the braking device and the steering device. In the manual driving mode, the driving control unit 121 controls the actuator AC in accordance with a driving command (such as a steering operation) from the driver acquired by the internal sensor group 3.

[0020] The object tracking device 50 will now be described in detail. As described above, the object tracking device 50 includes a data acquisition unit 111, an estimation unit 112, a calculation unit 113, a classification unit 114, a generation unit 115, a tentative detection unit 116, a superposition unit 117, a detection unit 118, a vector calculation unit 119, and a tracking unit 120. The object tracking device 50 further includes a LIDAR 5.

[0021] The data acquisition unit 111 acquires four-dimensional data (hereinafter referred to as point cloud data) including position information indicating three-dimensional position coordinates of measurement points on the surface of an object at which reflected waves from the LIDAR 5 are obtained, and velocity information indicating the relative movement velocity of the measurement points, as detection data of the LIDAR 5. The point cloud data is acquired by the LIDAR 5 on a frame-by-frame basis, more specifically, at predetermined time intervals (time intervals determined by the frame rate of the LIDAR 5).

[0022] The estimation unit 112 estimates the absolute moving speed of the host vehicle based on the point cloud data acquired by the data acquisition unit 111. Here, the estimation of the absolute moving speed of the host vehicle by the estimation unit 112 will be described.

[0023] First, the estimation unit 112 extracts point cloud data from the point cloud data acquired by the data acquisition unit 111, excluding information on measurement points corresponding to three-dimensional objects, that is, point cloud data corresponding to the road surface around the vehicle (hereinafter referred to as road surface point cloud data). The estimation unit 112 extracts the road surface point cloud data, that is, the measurement points P corresponding to the road surface, by the following equation (i): i (i=1,2,…,n) 4-dimensional data (x i , y i ,z i ,v i ) contains the position coordinates (x i , y i ,z i ) based on the relative movement speed v i The unit vector e indicates the direction of i Calculate.

[0024]

number

[0025] Next, the estimation unit 112 estimates the movement vector (movement speed (absolute movement speed) and movement direction) Vself of the host vehicle. Specifically, the estimation unit 112 sets, as an objective function L, a conversion equation for converting the relative movement speed vi of the measurement point Pi corresponding to the road surface into an absolute movement speed, and solves an optimization problem to optimize the objective function L so as to approach zero. Because the measurement points Pi are measurement points on the road surface, the absolute speed of each of these measurement points should be zero. Therefore, by optimizing the objective function L so as to approach zero, it is possible to estimate a correct Vself. Vself is expressed by velocity components in the X, Y, and Z axes as shown in the following equation (ii). The objective function L is expressed by the following equation (iii). By solving the above optimization problem, Vself is searched for so that the right-hand side of equation (iii) becomes zero. Note that Vself may be set to zero as an initial value, or Vself estimated in the previous frame may be set. Alternatively, a measurement point estimated to have an absolute speed of zero may be extracted using another method, and the extracted measurement point may be used as the measurement point Pi.

[0026]

number

number

[0027] In equation (iii), A is a matrix of unit vectors ei of n measurement points corresponding to the road surface, and is expressed by equation (iv). Also in equation (iii), V is a 1×n matrix representing the velocity components (relative movement velocities) of n measurement points Pi corresponding to the road surface, and is expressed by equation (v). The estimation unit 112 obtains Vself obtained by solving the optimization problem as an estimate of the absolute movement velocity of the host vehicle in the current frame.

[0028]

number

number

[0029] The calculation unit 113 calculates the absolute movement speeds of all measurement points, more specifically, all measurement points including measurement points corresponding to three-dimensional objects, based on the movement vector Vself of the host vehicle estimated by the estimation unit 112. Here, the calculated absolute movement speed of a measurement point becomes a negative value when the measurement point approaches the host vehicle, and becomes a positive value when the measurement point moves away from the host vehicle.

[0030] The classification unit 114 classifies the point cloud data acquired by the data acquisition unit 111 into moving point cloud data corresponding to measurement points where the absolute value of the absolute movement speed calculated by the calculation unit 113 is equal to or greater than a predetermined speed Th#V, and stationary point cloud data corresponding to measurement points where the absolute value is less than the predetermined speed Th#V.

[0031] The generating unit 115 generates speed-added data by adding the absolute movement speed calculated by the calculating unit 113 to the movement point cloud data. More specifically, the generating unit 115 adds the absolute movement speed corresponding to each measurement point to each piece of position information of each measurement point included in the movement point cloud data. The generating unit 115 stores the generated speed-added data in the storage unit 12 together with the frame ID of the current frame.

[0032] 2A and 2B are diagrams showing an example of a three-dimensional object contained in the three-dimensional space around the host vehicle. FIG. 2A shows a moving object (a bicycle CY and a person RD riding the bicycle CY) traveling ahead of the host vehicle in the direction of travel (X direction) of the host vehicle. FIG. 2B shows a plan view of the moving object in FIG. 2A as seen from above (Z direction). As shown in FIG. 2B, the maximum size of the three-dimensional object in the X and Y directions (Xmax and Ymax) can be recognized even without information about the height direction (Z direction) of the three-dimensional object.

[0033] Therefore, the generation unit 115 may convert the position information of each measurement point from three-dimensional to two-dimensional by projecting each measurement point onto a plane so as to remove information in the height direction from the position information of each measurement point corresponding to the moving point cloud data. Specifically, when the position coordinates of each measurement point are expressed in an XYZ coordinate system, the generation unit 115 may project each measurement point corresponding to the moving point cloud data onto an XY plane to convert the moving point cloud data into two-dimensional data (XY data) expressed in the XY coordinate system. In this case, the generation unit 115 generates three-dimensional speed-added data (XYV data) by adding an absolute moving speed to the XY data. The following description will be given taking as an example a case where the speed-added data generated by the generation unit 115 is XYV data.

[0034] The tentative detection unit 116 detects moving objects around the host vehicle based on the XYV data generated by the generation unit 115. More specifically, the tentative detection unit 116 executes a clustering process on the XYV data to detect a bounding box, which is a circumscribing area of ​​the moving object, from the XY plane.

[0035] Incidentally, objects that are far from the vehicle or small in size may not be detected or may be detected late in the clustering process because the number of point clouds (number of measurement points) measured by the lidar is small. Therefore, in order to prevent such missed detections and delays in detection, the provisional detection unit 116 lowers the threshold for the number of measurement points that are considered to be a point cloud and performs the clustering process. In the clustering process by the provisional detection unit 116 (hereinafter referred to as the provisional clustering process), a value Th0 that is smaller than a threshold Th1 used in the clustering process by the detection unit 118, which will be described later, is set as the threshold.

[0036] Hereinafter, the detection of a moving object by the tentative detection unit 116 may be referred to as tentative detection of a moving object. Note that the clustering process performed by the tentative detection unit 116 and the detection unit 118 may use any method, such as DBSCAN (Density-based spatial clustering of applications with noise) or the K-means method.

[0037] The provisional detection unit 116 detects the position and size of the moving object on the XY plane based on the position and size of the bounding box (circumscribed area) detected by the provisional clustering process. The provisional detection unit 116 stores the measurement point group corresponding to the detected moving object, i.e., information that can identify the measurement point group included in the detected bounding box, in the storage unit 12 as a provisional detection result.

[0038] Here, the provisional detection of moving objects by the provisional detection unit 116 will be described. FIG. 3A is a diagram showing a situation in which multiple pedestrians are passing by. Here, detection data from a lidar installed in the concourse AS of FIG. 3A is used as an example, rather than detection data from a lidar mounted on a vehicle. FIG. 3A shows the concourse AS as seen from the viewpoint of the lidar. FIG. 3A shows pedestrians HM32 and HM34 moving (walking) in the same direction (X-axis direction) along the extension direction of the concourse AS, and pedestrians HM31, HM33, and HM35 moving (walking) in the opposite direction. Note that the absolute values ​​of the absolute movement speeds of pedestrians HM31 to HM35 are equal to or greater than a predetermined speed Th#V.

[0039] 3B is a diagram showing an example of three-dimensional data (XYV data) generated by the generation unit 115. FIG. 3B shows XYV data obtained by adding the absolute movement speeds of pedestrians HM31 to HM35 to two-dimensional data obtained by projecting measurement point clouds (clusters) PC1 to PC5 corresponding to pedestrians HM31 to HM35 in FIG. 3A onto the XY plane. In FIG. 3B, the measurement point cloud of each pedestrian is depicted in a color according to the absolute movement speed of each pedestrian. For simplicity of explanation, it is assumed that the absolute movement speeds of pedestrians HM31, HM33, and HM35 are equal to each other. It is also assumed that the absolute movement speeds of pedestrians HM32 and HM34 are equal to each other. Therefore, in Figure 3B, the measurement point clouds PC1, PC3, and PC5 corresponding to pedestrians HM31, HM33, and HM35 are drawn in the same color (black), and the measurement point cloud PC3 corresponding to pedestrians HM32 and HM34 is drawn in a different color (white).

[0040] FIG. 3B also shows bounding boxes B1 to B5 detected by the provisional clustering process. Bounding boxes B1 to B5 correspond to measurement point clouds PC1 to PC5, respectively. As described above, the provisional detection unit 116 performs clustering by lowering the threshold for the number of measurement points considered to be a point cloud, so as to prevent oversight of moving objects. Therefore, bounding box B5 corresponding to measurement point cloud PC5, which contains only a few measurement points (two points in the figure), is also detected. Furthermore, in the clustering process for XYV data, speed information is taken into account in classifying measurement points. Therefore, measurement point clouds PC2 and PC3 corresponding to pedestrians HM32 and HM33 moving at different absolute movement speeds are not recognized as a single measurement point cloud even if they are close to each other, but are recognized as separate measurement point clouds. As a result, bounding boxes B2 and B3 corresponding to measurement point clouds PC2 and PC3 are detected, respectively, as shown in FIG. 3B.

[0041] The superimposing unit 117 estimates the amount of movement of the moving object detected by the tentative detection unit 116 from a past frame (e.g., the previous frame) to the current frame. The superimposing unit 117 superimposes the XYV data of the current frame and the XYV data of the past frame based on the estimated amount of movement. The XYV data generated by this superimposition is called superimposed speed-added data or superimposed XYV data.

[0042] Here, the generation of the superimposed XYV data will be described. First, the superimposing unit 117 estimates the movement vector (absolute movement speed and movement direction) of the moving object detected by the provisional detection unit 116 using the following equation (vi). Hereinafter, the moving object detected by the provisional detection unit 116 may be referred to as a provisionally detected object.

[0043]

number

[0044] In equation (vi), Vmodel is a movement vector of the measurement points corresponding to the tentatively detected object. When the number of measurement points constituting the tentatively detected object is m, (v xi , v yi , v zi ) (i=1, 2, ..., m). Vself is the movement vector of the vehicle estimated by the estimation unit 112 using equation (iii). A is a matrix of unit vectors ei of n measurement points corresponding to the road surface used to estimate Vself. V is a 1 × n matrix representing the velocity components (relative movement velocities) of n measurement points corresponding to the road surface used to estimate Vself.

[0045] Superimposing unit 117 associates the calculated movement vector Vmodel with the frame ID of the current frame together with information (identifier) ​​that can identify the corresponding tentatively detected object, and stores the vector in storage unit 12. When tentative detection unit 116 detects multiple moving objects, superimposing unit 117 calculates a movement vector corresponding to each moving object (tenantly detected object). Each calculated movement vector is stored in storage unit 12 together with information (identifier) ​​that can identify the corresponding tentatively detected object.

[0046] Next, superimposition unit 117 reads out from storage unit 12 the movement vector of the tentatively detected object that has been stored in association with the frame ID of the past frame. Superimposition unit 117 calculates the amount of movement of the tentatively detected object from the past frame to the current frame by multiplying the velocity component of the movement vector of the tentatively detected object read out from storage unit 12 by the elapsed time from the past frame to the current frame. Based on the calculated amount of movement and the direction indicated by the movement vector, superimposition unit 117 executes offset processing to offset (translate) the measurement point cloud that corresponds to the tentatively detected object and is included in the XYV data of the past frame.

[0047] If the XYV data of the past frame includes measurement point clouds corresponding to multiple tentatively detected objects, offset processing is performed on each of the measurement point clouds corresponding to each tentatively detected object. The superimposing unit 117 superimposes the offset-processed measurement point clouds on the XYV data of the current frame to generate superimposed XYV data.

[0048] The superimposing unit 117 may generate superimposed XYV data by superimposing the measurement point clouds of multiple past frames on the XYV data of the current frame. For example, if frame n (n: frame number) is the current frame, the superimposed XYV data may be generated by superimposing the measurement point clouds of the provisionally detected object included in the XYV data of frames n-1, n-2, and n-3 on the XYV data of frame n.

[0049] In this case, the superimposing unit 117 uses the above formula (vi) to calculate the movement vector mv of the provisionally detected object corresponding to each of the frames n-1, n-2, and n-3. n-1 ,mv n-2 ,mv n-3 Then, the superimposing unit 117 calculates the calculated motion vector mv n-1 ,mv n-2 ,mv n-3 Each velocity component is multiplied by the travel time T, T × 2, and T × 3 to obtain the movement amount MA of the provisionally detected object between frame n and frames n-1, n-2, and n-3. n-1 ,MA n-2 ,MA n-3 are calculated respectively.

[0050] The superimposing unit 117 calculates the motion vector mv n-1 ,mv n-2 ,mv n-3 direction and movement amount MA n-1 ,MA n-2 ,MA n-3Based on this, offset processing is performed on each of the measurement point clouds of the provisionally detected object corresponding to frames n-1, n-2, and n-3. Superimposing unit 117 superimposes the offset-processed measurement point clouds of the provisionally detected object in frames n-1, n-2, and n-3 on the XYV data of frame n, respectively, to generate superimposed XYV data.

[0051] When the host vehicle 101 is traveling, the superimposing unit 117 further executes an offset rotation process to offset and rotate the measurement point cloud of the tentatively detected object included in the XYV data of the past frames based on the orientation angle difference and movement vector of the host vehicle 101 between frames. The movement vector of the host vehicle 101 represents the movement direction of a representative point (such as the center of gravity) of the host vehicle 101 between frames and the movement speed in that movement direction. The orientation angle difference of the host vehicle 101 is the angular difference between the orientation in the current frame and the orientation (direction of travel) of the host vehicle 101 in the past frame. The orientation angle difference and movement vector of the host vehicle 101 can be estimated by executing a predetermined scan matching process to superimpose the still point cloud data of the past frame on the still point cloud data of the current frame.

[0052] 4A is a diagram showing an example of a three-dimensional space around the vehicle. In FIG. 4A, the up-down direction (X-axis direction) represents the direction of movement (direction of travel) of the vehicle 101. The lateral direction (left-right direction in the figure) and height direction (direction from back to front in the figure) relative to the X-axis direction represent the Y-axis direction and Z-axis direction.

[0053] FIG. 4A shows the host vehicle 101 and objects present around the host vehicle 101 at time t1. Objects SB1 to SB6 are stationary objects, and objects MB1 and MB2 are moving objects. The stationary objects SB1 to SB6 include the road surface on which the host vehicle 101 is traveling, structures such as walls and median strips installed on the side of the road, and other vehicles parked on the shoulder of the road. Moving objects include other vehicles and pedestrians. For simplicity of explanation, it is assumed that the host vehicle 101 is stopped.

[0054] Figures 4B and 4C are diagrams showing an example of XYV data corresponding to the three-dimensional space of Figure 4A, generated by generation unit 115. Note that the XYV data generated by generation unit 115 does not actually include measurement point groups N1 to N6 corresponding to stationary objects SB1 to SB6, but in Figures 4B and 4C, those measurement points are shown in consideration of ease of viewing the drawings. The same applies to Figures 5A, 5B, 6, and 7, which will be described later.

[0055] Fig. 4B shows the XYV data of a past frame (frame at time t1). Fig. 4C shows the XYV data of a current frame (frame at time t2, frame time T after time t1). In Figs. 4B and 4C, the up-down direction (X-axis direction) represents the direction of movement (direction of travel) of the host vehicle 101. The direction lateral to the X-axis direction (left-right direction in the figure) represents the Y-axis direction.

[0056] In Figures 4B and 4C, regions N1 to N6 schematically represent measurement point clouds corresponding to stationary objects SB1 to SB6, more specifically, the positions and sizes of the measurement point clouds. Regions M11 and M12 in Figure 4B schematically represent measurement point clouds corresponding to moving objects MB1 and MB2, more specifically, the positions and sizes of the measurement point clouds. Regions M13 and M14 in Figure 4B are measurement points or measurement point clouds that do not correspond to either moving object MB1 or MB2, and represent noise. Arrows mv11 to mv14 in Figure 4B schematically represent the movement vector Vmodel of measurement point clouds M1 to M4 estimated using equation (vi) above.

[0057] Regions M21 and M22 in Fig. 4C represent measurement point clouds corresponding to moving objects MB1 and MB2, more specifically, the positions and sizes of the measurement point clouds. Region M23 in Fig. 4C represents noise, which is a measurement point or measurement point cloud that does not correspond to either moving object MB1 or MB2.

[0058] 5A and 5B are diagrams showing examples of measurement point clouds of a past frame superimposed on the XYV data of a current frame. Fig. 5A shows an example of XYV data of a current frame on which measurement point clouds M11 to M14 of a moving object included in the XYV data of a past frame are superimposed without offset processing. Fig. 5B shows an example of XYV data of a current frame on which measurement point clouds M11 to M14 of a moving object included in the XYV data of a past frame are superimposed after being offset processing, i.e., superimposed XYV data generated by the superimposing unit 117.

[0059] In Fig. 5A, areas M11p-M14p indicated by dashed lines schematically represent the measurement point groups M11-M14 of past frames superimposed on the current frame. In Fig. 5B, areas M11o-M14o indicated by dashed lines schematically represent the measurement point groups M11-M14 of past frames superimposed on the current frame. The measurement point groups M11o-M14o in Fig. 5B are offset in the direction of the movement vectors mv11-mv14 from the measurement point groups M11p-M14p in Fig. 5A by the movement amount obtained by multiplying the velocity component of the movement vectors mv11-mv14 by the frame time T.

[0060] Since each measurement point in the XYV data of a previous frame has speed information indicating a relative movement speed, the movement speed and movement direction of each measurement point can be estimated based on the speed information. Therefore, the superimposing unit 117 may offset each measurement point in the XYV data of the previous frame based on the speed information of each measurement point. Then, the superimposing unit 117 may superimpose each offset measurement point on the XYV data of the current frame to generate superimposed XYV data.

[0061] 6 is a diagram for explaining the detection of moving objects by the detection unit 118. The detection unit 118 performs a clustering process on the superimposed XYV data (FIG. 5B) generated by the superimposition unit 117 to detect moving objects around the host vehicle.

[0062] In the superimposed XYV data of Fig. 5B, measurement point group M11o overlaps measurement point group M21, so in this clustering process, measurement point group M11o and measurement point group M21 are recognized as a single measurement point group. As a result, even if the number of measurement points in either measurement point group M11o or measurement point group M21 is less than threshold value Th1, as long as the total number of measurement points is equal to or greater than threshold value Th1, a bounding box B10 enclosing both measurement point groups is detected, as shown in Fig. 6. Similarly, a bounding box B20 enclosing measurement point group M12o and measurement point group M22 is detected.

[0063] The detection unit 118 detects the position and size of the moving objects (objects MB1 and MB2 in FIG. 4A) in three-dimensional space (XYZ space) based on the positions and sizes of the detected bounding boxes B10 and B20.

[0064] As described above, by offsetting the measurement point cloud of a moving object provisionally detected in the previous frame and overlaying it on the XYV data of the current frame (Figure 5B), the number of measurement points corresponding to the moving object can be increased. As a result, even moving objects that do not have enough corresponding measurement points within a single frame, such as distant moving objects or small moving objects, can be detected early. Furthermore, of the measurement point clouds from past frames overlaid on the current frame, measurement point clouds that are not included in either bounding box, such as measurement point clouds M13o and M14o in Figure 6, can be determined to be noise.

[0065] The vector calculation unit 119 calculates the movement vector of the moving object detected by the detection unit 118. First, the vector calculation unit 119 performs a determination process for identifying the same object between frames (between a past frame and a current frame) for the moving object detected by the detection unit 118. In this determination process, it is determined that the measurement point cloud of the current frame (hereinafter referred to as the current measurement point cloud) included in the bounding box detected by the detection unit 118 and the measurement point cloud of the past frame superimposed on the current frame (hereinafter referred to as the superimposed measurement point cloud) correspond to the same moving object. In the example of FIG. 6, it is determined that the current measurement point cloud M21 and the superimposed measurement point cloud M11o included in the bounding box B10 correspond to the same moving object. Furthermore, it is determined that the current measurement point cloud M22 and the superimposed measurement point cloud M12o included in the bounding box B20 correspond to the same moving object.

[0066] Based on the result of the above determination process, vector calculation unit 119 calculates the movement vector of the moving object detected by detection unit 118. Fig. 7 is a diagram for explaining the calculation of the movement vector of the moving object by vector calculation unit 119.

[0067] First, the vector calculation unit 119 superimposes the XYV data of the past frame on the XYV data of the current frame, as shown in Fig. 7. In Fig. 7, the XYV data of the past frame (frame at time t1) is indicated by a dashed line, and the XYV data of the current frame (frame at time t2) is indicated by a solid line. Note that when the host vehicle 101 is traveling, the vector calculation unit 119 performs an offset rotation process on the XYV data of the past frame based on the movement vector and azimuth angle difference of the host vehicle 101 before superimposing.

[0068] 7 are measurement point groups M11p to M14p of past frames superimposed on the current frame. Representative points G11p, G12p, G21, and G22 represent the centers of gravity of measurement point groups M11p, M12p, M21, and M22. Representative points G11p, G12p, G21, and G22 may be points other than the centers of gravity.

[0069] The vector calculation unit 119 calculates a movement vector MV1 based on the positional relationship between the representative point G21 of the measurement point group M21 and the representative point G11p of the measurement point group M11p that is determined to correspond to the same moving object as the measurement point group M21. The movement vector MV1 indicates the movement speed and movement direction of the moving object corresponding to the measurement point group M11p and the measurement point group M21 from the previous frame to the current frame.

[0070] Similarly, the vector calculation unit 119 calculates a movement vector MV2 of the moving object corresponding to the measurement point group M12p and the measurement point group M22 based on the positional relationship between the representative points G12p and G22. The vector calculation unit 119 stores the calculated movement vectors MV1 and MV2 in the storage unit 12 together with information (identifier) ​​that can identify the corresponding moving object.

[0071] When a movement vector (movement vectors MV1 and MV2 in FIG. 7) corresponding to a moving object (objects MB1 and MB2 in FIG. 4A) detected by the detection unit 118 is stored in the memory unit 12, the tracking unit 120 sets the moving object as a tracking target. Based on the movement vector of the moving object set as a tracking target (hereinafter referred to as the tracked object), the tracking unit 120 calculates a movement trajectory of the tracked object between frames (from the past frame to the current frame). While the tracked object is being detected by the detection unit 118, the tracking unit 120 tracks the movement path of the tracked object by accumulating the movement trajectory calculated for each frame.

[0072] 8 is a flowchart showing an example of processing executed by the calculation unit 11 of the controller 10 in FIG. 1 in accordance with a predetermined program. The processing shown in this flowchart is repeated at a predetermined cycle while the vehicle control device 100 is running. More specifically, the processing is repeated at a cycle according to the frame rate of the rider 5.

[0073] First, in step S1, the external environment surrounding the vehicle is detected. Specifically, an irradiation command is sent to the LIDAR 5, and point cloud data (detection data) including position information and speed information of measurement points at which reflected waves of electromagnetic waves irradiated from the LIDAR 5 in response to the irradiation command are obtained is acquired. In step S2, the point cloud data acquired in step S1 is classified into moving point cloud data and stationary point cloud data.

[0074] Next, the processing of steps S3 to S8 is executed on the moving point cloud data. Note that the controller 10 also executes predetermined processing on the stationary point cloud data, but the explanation thereof will be omitted.

[0075] In step S3, absolute moving speeds are added to the position information of each measurement point included in the moving point cloud data to generate speed-added data (XYV data), and in step S4, a provisional clustering process is performed on the XYV data generated in step S3. As a result, moving objects around the host vehicle 101 are provisionally detected. The provisional detection results of the moving objects are stored in the storage unit 12 together with the generated XYV data in association with the frame ID of the current frame. The provisional detection results include information that can identify the measurement point cloud corresponding to the provisionally detected moving object.

[0076] In step S5, the motion vector of the moving object provisionally detected in step S4 is estimated using the above formula (vi). The estimated motion vector is stored in the storage unit 12 as part of the provisional detection result, together with information (identifier) ​​that can identify the corresponding moving object.

[0077] In step S6, based on the provisional detection result of the previous frame stored in memory unit 12, the measurement point cloud corresponding to the previously provisionally detected moving object is offset and superimposed on the XYV data generated in step S3 (XYV data of the current frame). More specifically, based on the provisional detection result, the measurement point cloud corresponding to the previously provisionally detected moving object is acquired from the XYV data of the previous frame, and the acquired measurement point cloud is offset based on the movement vector of the moving object. Then, the offset measurement point cloud is superimposed on the XYV data of the current frame. As a result, superimposed XYV data is generated.

[0078] In step S7, a clustering process is performed on the superimposed XYV data generated in step S6. The positions and sizes of the bounding boxes detected by this clustering process are detected as the positions and sizes of moving objects around the host vehicle.

[0079] Finally, in step S8, the movement vector of the moving object detected in step S7 is estimated (calculated). More specifically, the movement vector is calculated based on the positions of the measurement point cloud of the current frame (current measurement point cloud) contained in the bounding box detected in step S7 and the positions in the previous frame of the measurement point cloud of the previous frame (superimposed measurement point cloud) superimposed on the current frame, which are contained in the bounding box.

[0080] As described above, each measurement point of the XYV data has speed information indicating the relative movement speed, and therefore each measurement point may be offset based on that speed information. That is, without executing the processes of steps S4 and S5, in step S6, each measurement point of the XYV data of the previous frame may be offset based on the speed information of each measurement point. Then, each offset measurement point may be superimposed on the XYV data generated in step S3 to generate superimposed XYV data.

[0081] According to the embodiment described above, the following advantageous effects are achieved. (1) The object tracking device 50 includes a lidar 5 that acquires point cloud data, frame by frame, that includes three-dimensional position information and velocity information indicating relative movement velocity at measurement points on the surface of an object contained in the three-dimensional space, by irradiating electromagnetic waves into a three-dimensional space and receiving reflected waves, i.e., for each point cloud frame that includes the point cloud data at the same time; a calculation unit 113 that calculates the absolute movement velocity of each of the multiple measurement points corresponding to the point cloud data based on the velocity information; a classification unit 114 that classifies the point cloud data, when acquired by the lidar 5, into moving point cloud data whose absolute value of the absolute movement velocity calculated by the calculation unit 113 is equal to or greater than a predetermined velocity, and stationary point cloud data other than the moving point cloud data; a memory unit 12 that stores the moving point cloud data classified by the classification unit 114; a processing unit that performs processing to detect moving objects moving in the three-dimensional space; a vector calculation unit 119 that calculates the movement vector of the moving object detected by the processing unit; and a tracking unit 120 as a trajectory acquisition unit that determines the movement trajectory of the moving object based on the movement vector calculated by the vector calculation unit 119. The processing unit performs offset processing to offset the position of each measurement point in the moving point cloud data included in the past point cloud frames stored in the memory unit 12 based on the moving speed and moving direction of each measurement point estimated based on the speed information of each measurement point, and when the classifying unit classifies the moving point cloud data from new point cloud data acquired by the LIDAR 5, performs superposition processing to superimpose the offset-processed moving point cloud data of the past frame on the moving point cloud data, and performs processing to detect a moving object based on the superposition processing moving point cloud data. The vector calculation unit 119 calculates a movement vector of the moving object based on the positions of the measurement point clouds corresponding to the moving object in the past point cloud frames and the new point cloud frames.

[0082] More specifically, the processing unit performs a clustering process on the moving point cloud data after the overlay process, and detects the position and size of the cluster (measurement point cloud included in the bounding box) detected by the clustering process as the position and size of the moving object, and the vector calculation unit 119 calculates the movement vector of the moving object based on the position before offset processing of the measurement point cloud included in the cluster corresponding to the past point cloud frame and the position of the measurement point cloud included in the cluster corresponding to the new point cloud frame.

[0083] This configuration allows for early detection of distant or small objects and for accurate tracking of these moving objects. Furthermore, the offset processing described above allows for accurate detection of moving objects that move significantly between frames. This allows for continued tracking without losing sight of the moving object, even if the position of the moving object to be tracked changes significantly between frames.

[0084] (2) When the classification unit 114 classifies the moving point cloud data from the new point cloud data acquired by the LIDAR 5, the processing unit executes a tentative clustering process as a first clustering process on the moving point cloud data, in which the minimum number of points in a cluster to be detected is set to a first predetermined number. Furthermore, in an offset process, the processing unit offsets the positions of each measurement point belonging to a cluster included in the moving point cloud data of a past frame based on the moving speed and moving direction of the cluster estimated based on the speed information of each measurement point. Furthermore, in a superposition process, the processing unit superimposes the data of each measurement point belonging to a cluster from the moving point cloud data of the past frame that has been subjected to the offset process on the moving point cloud data classified from the new point cloud data. Furthermore, the processing unit executes a clustering process as a second clustering process on the moving point cloud data after the superposition process, in which the minimum number of points is set to a second predetermined number greater than the first predetermined number. Furthermore, the processing unit detects the position and size of a moving object in three-dimensional space based on the position and size of the cluster detected by the second clustering process. This enables distant objects and small objects to be detected quickly and accurately.

[0085] (3) The LIDAR 5 is mounted on a moving object. The above-mentioned velocity information is first velocity information, and the object tracking device 50 further includes an estimation unit 112 as a velocity acquisition unit that acquires second velocity information indicating the absolute velocity of the moving object. The calculation unit 113 calculates the absolute velocity of each of the multiple measurement points corresponding to the point cloud data based on the first velocity information and the second velocity information. The classification unit 114 classifies the point cloud data into moving point cloud data if the absolute value of the absolute velocity calculated by the calculation unit 113 is equal to or greater than a predetermined velocity. This allows for early detection of distant objects or small objects even when the LIDAR is mounted on a moving object.

[0086] The above-described embodiment can be modified in various ways. Modifications will be described below. In the above-described embodiment, a LIDAR 5 as a detector is mounted on a vehicle and irradiates electromagnetic waves into a three-dimensional space around the vehicle and receives reflected waves to acquire point cloud data including three-dimensional position information and velocity information indicating the relative movement velocity of measurement points on the surface of an object included in the three-dimensional space. However, the detector may be something other than a LIDAR. Specifically, the detector may be a 4D imaging radar that irradiates millimeter-wave radio waves and receives reflected waves to acquire four-dimensional information (point cloud data) including the distance, azimuth angle, elevation angle, and relative movement velocity of measurement points on the surface of an object included in the three-dimensional space. Furthermore, the moving body on which the detector is mounted may be something other than a vehicle, such as a self-propelled robot.

[0087] In addition, in the above embodiment, an object tracking device that constitutes part of the vehicle control device 100 is used as an example, but the object tracking device and the detector equipped in the object tracking device may be provided outside the vehicle or may be a stationary type.

[0088] In the above embodiment, the superimposing unit 117 and the detecting unit 118 function as processing units, and perform the offset processing before performing the superimposing processing. However, the processing units may perform the offset processing before performing the superimposing processing.

[0089] In the above embodiment, the generation unit 115 converts the moving point cloud data obtained by the classification unit 114 into two-dimensional data, adds absolute moving speeds to the two-dimensional moving point cloud data to generate three-dimensional speed-added data (XYV data), and the provisional detection unit 116 and the detection unit 118 perform clustering processing on the XYV data to detect moving objects around the vehicle. However, if precision in the cluster size in three-dimensional space (XYZ space) is required, the clustering processing described above may be performed on the XYZ space. Specifically, the generation unit may add absolute moving speeds to the moving point cloud data obtained by the classification unit 114 to generate four-dimensional speed-added data (hereinafter referred to as XYZV data). In this case, the provisional detection unit 116 and the detection unit 118 perform clustering processing on the XYZV data.

[0090] In the above embodiment, the estimation unit 112 as a speed acquisition unit selects a measurement point Pi as a representative measurement point from the remaining measurement points excluding measurement points corresponding to a three-dimensional object from the multiple measurement points, and estimates the absolute movement speed of the host vehicle based on the position information and speed information of the representative measurement point extracted from the point cloud data acquired by the data acquisition unit 111, and acquires the estimation result as the second speed information. However, the speed acquisition unit may acquire the measurement result of the absolute movement speed of the host vehicle acquired by a measuring instrument included in the internal sensor group 3 as the second speed information. In this case, the object tracking device 50 includes at least a vehicle speed sensor among the internal sensor group 3 as a measuring instrument. Furthermore, the speed acquisition unit may calculate and acquire the absolute movement speed of the host vehicle based on the current position of the host vehicle measured by the positioning unit 2. In this case, the object tracking device 50 includes the positioning unit 2.

[0091] In the above embodiment, the driving control unit 121 controls the driving of the vehicle so as to avoid a collision with or contact with an object detected by the detection unit 118. However, the driving control unit 121 may serve as an output unit and output information (image information, etc.) indicating the position and size of the object detected by the detection unit 118 as a detection result to a display device (not shown). The driving control unit 121 may also serve as an alarm unit and predict the possibility of a collision with or contact with a moving object based on the size, position, and moving speed of the moving object detected by the detection unit 118. When the possibility of a collision with or contact with a moving object is equal to or greater than a predetermined level, the driving control unit 121 may alarm the occupants of the vehicle with information (video information or audio information) calling attention to the collision with or contact with the moving object detected by the detection unit 118 via a display or speaker (not shown) provided in the vehicle control device 100.

[0092] Furthermore, in the above embodiment, the object tracking device 50 is applied to an autonomous vehicle, but the object tracking device 50 can also be applied to vehicles other than autonomous vehicles. For example, the object tracking device 50 can also be applied to a manually driven vehicle equipped with an ADAS (Advanced Driver-Assistance Systems).

[0093] The above description is merely an example, and the present invention is not limited to the above-described embodiment and modifications, as long as the features of the present invention are not impaired. One or more of the above-described embodiment and modifications can be arbitrarily combined, and modifications can also be combined with each other. [Explanation of symbols]

[0094] 5 Lidar, 10 Controller, 11 Calculation unit, 12 Memory unit, 111 Data acquisition unit, 112 Estimation unit, 113 Calculation unit, 114 Classification unit, 115 Generation unit, 116 Temporary detection unit, 117 Superposition unit, 118 Detection unit, 119 Vector calculation unit, 120 Tracking unit, 121 Travel control unit, 50 Object tracking device, 100 Vehicle control device, AC actuator

Claims

1. a detector that irradiates electromagnetic waves into a three-dimensional space and receives reflected waves to acquire point cloud data including three-dimensional position information and velocity information indicating relative movement velocity at measurement points on a surface of an object included in the three-dimensional space for each point cloud frame including the point cloud data at the same time; a calculation unit that calculates, based on the velocity information, an absolute movement velocity of each of the plurality of measurement points corresponding to the point cloud data; a classification unit that, when the point cloud data is acquired by the detector, classifies the point cloud data into moving point cloud data in which the absolute value of the absolute moving speed calculated by the calculation unit is equal to or greater than a predetermined speed, and stationary point cloud data other than the moving point cloud data; a storage unit that stores the movement point cloud data classified by the classification unit; a processing unit that performs processing to detect a moving object moving within the three-dimensional space; a vector calculation unit that calculates a movement vector of the moving object detected by the processing unit; a trajectory acquisition unit that determines a movement trajectory of the moving object based on the movement vector calculated by the vector calculation unit, the processing unit executes an offset process to offset the positions of each measurement point in the moving point cloud data corresponding to the past point cloud frame stored in the storage unit based on the moving speed and moving direction of each measurement point estimated based on the speed information of each measurement point; when the moving point cloud data is classified by the classification unit from the point cloud data included in the new point cloud frame acquired by the detector, the processing unit executes a superposition process to superimpose the moving point cloud data of the past point cloud frame that has been subjected to the offset process on the moving point cloud data; and further executes a process to detect the moving object based on the moving point cloud data after the superposition process. The object tracking device is characterized in that the vector calculation unit calculates the movement vector of the moving object based on the positions of the measurement point clouds corresponding to the moving object in the past point cloud frame and the new point cloud frame.

2. 2. The object tracking device according to claim 1, The processing unit performing a clustering process on the moving point cloud data after the superposition process, and detecting the positions and sizes of the clusters detected by the clustering process as the position and size of the moving object; an object tracking device characterized in that the vector calculation unit calculates the movement vector of the moving object based on the positions before the offset processing of the measurement point group corresponding to the past point cloud frame included in the cluster and the positions of the measurement point group corresponding to the new point cloud frame included in the cluster.

3. 2. The object tracking device according to claim 1, The processing unit When the moving point cloud data is classified by the classification unit from the new point cloud data acquired by the detector, a first clustering process is performed on the moving point cloud data, with a minimum number of points in a cluster to be detected set to a first predetermined number; In the offset processing, the positions of the measurement points belonging to the clusters included in the movement point cloud data of the past point cloud frame are offset based on the movement speed and movement direction of the clusters estimated based on the speed information of the measurement points; In the overlay processing, data of each measurement point belonging to the cluster among the moving point cloud data of the past point cloud frame subjected to the offset processing is overlaid on the moving point cloud data classified from the new point cloud data, a second clustering process is performed on the moving point cloud data after the superposition process, the second clustering process being performed by setting the minimum number of points to a second predetermined number greater than the first predetermined number; an object tracking device for detecting the position and size of the moving object in the three-dimensional space based on the positions and sizes of the clusters detected by the second clustering process;

4. 2. The object tracking device according to claim 1, The object tracking device is characterized in that the detector is mounted on a moving body.

5. 5. The object tracking device according to claim 4, the speed information is first speed information, a speed acquisition unit that acquires second speed information indicating an absolute moving speed of the moving object, the calculation unit calculates the absolute movement speed of each of the plurality of measurement points corresponding to the point cloud data based on the first speed information and the second speed information; The classification unit classifies the measurement points, whose absolute values ​​of the absolute movement speeds calculated by the calculation unit are equal to or greater than the predetermined speed, into the movement point cloud data.

6. 6. The object tracking device according to claim 1, An object tracking device characterized in that the detector is a lidar or radar.

Images