Method for stabilizing track of queuing vehicle at intersection based on 4D millimeter wave radar

Abstract

The invention relates to a method for stabilizing a track of a queuing vehicle at an intersection based on a 4D millimeter wave radar, and the method comprises the steps: obtaining 4D millimeter wave radar point cloud data and road calibration information; preprocessing the millimeter wave radar point cloud data according to the intersection calibration information; dBSCAN clustering is carried out on the preprocessed 4D millimeter wave point cloud; associating the generated track with the clustered bounding box, and generating a new track from the unassociated clustering box; after the track enters the queuing area, queuing area track management is realized according to track indexes of front and back frames of lanes, K-Means clustering is performed on the point cloud of the queuing area according to the track index of the current frame of lanes, and the track of the queuing area is associated with the clustering after clustering; and outputting stable track information.

Description

Technical Field

[0001] The present invention belongs to the technical field of 4D millimeter wave radar, and in particular is a method for achieving track stabilization of vehicles queuing at an intersection based on a 4D millimeter wave radar. Background Art

[0002] In the field of intelligent transportation, the development of traffic perception technology is crucial. It not only provides real-time data for traffic management, but also supports intelligent driving and safe driving of vehicles. With the advancement of artificial intelligence, Internet of Things and sensor technology, traffic perception technology has made significant progress, especially in the perception capabilities of multiple dimensions such as vehicles, roads and air. Among them, 4D millimeter wave radar, as an important traffic perception tool, plays an increasingly important role in intelligent transportation systems because of its wide monitoring range, long-distance detection capability, beyond-visual-range perception capability and strong anti-interference ability.

[0003] At traffic intersections, 4D millimeter-wave radar multi-target tracking can provide effective vehicle location information and speed information, and count the length of vehicles queued at intersections and traffic flow. Track stability is one of the keys to successful target tracking, and maintaining track stability for queuing vehicles at intersections is a key issue for 4D millimeter-wave radar. Traditional millimeter-wave radar multi-target tracking can output stable tracks for moving targets. However, when the target vehicle enters the queue area at the intersection, the number of vehicle targets increases and they get closer to each other, the speed decreases, or even becomes zero, and the corresponding point clouds of the vehicles cannot be distinguished, resulting in a decrease in multi-target tracking performance. The accuracy and stability of tracking are difficult to guarantee, and track jumps and false targets occur frequently, which cannot meet the needs of multi-target tracking. Therefore, the core difficulty in maintaining the stability of the track of queued vehicles lies in how to cluster the millimeter-wave radar point cloud corresponding to the track into clusters corresponding to the track in the absence of speed dimension information. Summary of the invention

[0004] The present invention proposes a method for achieving track stabilization of vehicles queuing at an intersection based on 4D millimeter wave radar.

[0005] The technical solution to achieve the purpose of the present invention is: a method for stabilizing the track of vehicles queuing at an intersection based on a 4D millimeter wave radar, comprising:

[0006] Step 1: Obtain 4D millimeter wave radar point cloud data and road calibration information;

[0007] Step 2: Preprocess the millimeter wave radar point cloud data according to the road calibration information;

[0008] Step 3: Perform DBSCAN clustering on the preprocessed 4D millimeter wave point cloud to obtain a clustering box containing the center coordinate position, length, width, height and average radial velocity;

[0009] Step 4: Associate the generated tracks with the clustering boxes, and generate new tracks for the unassociated clustering boxes;

[0010] Step 5: Determine whether the generated track enters the queue area. If it enters the queue area, perform queue area track management, that is, jump to step 6. If it does not enter the queue area, jump to step 7.

[0011] Step 6: After the track enters the queue area, the track management of the queue area is realized according to the track index of the lanes of the previous and next two frames. Then, according to the track index of the lanes of the current frame, the point cloud of the queue area is clustered by K-Means. After clustering, the track of the queue area is associated with the cluster.

[0012] Step 7: Output stable track information.

[0013] Preferably, the specific method of step 2 for preprocessing the millimeter wave radar point cloud data according to the road calibration information is:

[0014] The region of interest is obtained from road calibration, and the region of interest includes the specific location coordinates of motor vehicle lanes, non-motor vehicle lanes and intersections. The specific location coordinates of the intersection use the left-hand coordinate system, and the 4D millimeter-wave radar is used as the coordinate origin. The point cloud of the 4D millimeter-wave radar is filtered, and the point cloud preprocessing is achieved by setting thresholds for the height and speed attributes of the non-ROI area.

[0015] Preferably, in step 3, DBSCAN clustering is performed on the preprocessed 4D millimeter wave point cloud, and a specific method for outputting a bounding box including the center coordinate position, length, width, height and average radial velocity is as follows:

[0016] DBSCAN clustering is performed based on the three-dimensional coordinate position and relative radial velocity in the preprocessed millimeter-wave radar point cloud information. A radar point cloud is selected as the core point. The difference between the three-dimensional coordinate position and the relative radial velocity between the point and the adjacent radar point cloud is calculated to see whether it meets the clustering parameters. If the clustering parameters are met, the adjacent radar points are judged as qualified adjacent points, and the number of adjacent points is calculated. After finding the adjacent points of the radar point cloud, the adjacent points are used as core points to continue to find adjacent points. The steps of finding adjacent points are repeated until all adjacent points are found, and a cluster containing n points is obtained.

[0017] According to the characteristics of millimeter wave radar point cloud, two groups of clustering parameters are set with 80m of road as the boundary. The specific parameters within 80m are:

[0018]

[0019] 80m away:

[0020]

[0021] Among them, x core ,y core , z core Indicates the three-dimensional distance of the core point relative to the millimeter-wave radar, vr core Indicates the relative radial velocity of the core point relative to the millimeter wave radar, x border ,y border , z border Indicates the three-dimensional distance of the nearby point relative to the millimeter-wave radar, vr core Indicates the relative radial velocity of the nearby point relative to the millimeter-wave radar;

[0022] Select the maximum and minimum values ​​in the x direction in the cluster, that is, x max ,x min , and the maximum and minimum values ​​in the y direction, that is, y max ,y min , use these four points to get the cluster bounding box;

[0023] The center coordinate x of the bounding box cneter =(x max +x min ) / 2,y cneter =(y max +y min ) / 2, the length of the bounding box is length = x max -x min , width = y max -y min , find the maximum and minimum values ​​in the z direction in the cluster box, that is, z max ,z min , height = z max -z min , add the relative radial velocities of all radar points in the cluster frame to get vr total , the average radial velocity vr is obtained according to the number of radar points in the cluster box mean =vr total / n.

[0024] Preferably, step 4 associates the generated track with the clustered point cloud clusters, and the specific method for generating new tracks from the unassociated clusters is:

[0025] Perform global matching on clusters and tracks, calculate the association scores between clusters and tracks, select a group of clusters and tracks with the largest association scores for association; for clusters without corresponding tracks, create a new track.

[0026] Preferably, the association score between the cluster and the track is composed of a weighted distance score, an area score and a speed score, and the calculation process is:

[0027] The distance score is calculated according to the following formula:

[0028]

[0029] Among them, x c is the distance of the clustering box in the x direction, x t is the distance of the track in the x direction, y c is the distance of the clustering box in the y direction, y t is the distance of the track in the y direction, dist cri is the preset distance threshold;

[0030] The area score is calculated according to the following formula:

[0031]

[0032] Among them, area c is the area of ​​the clustering box, area t is the area of ​​the track, min represents the minimum value, and max represents the maximum value;

[0033] The speed score is calculated according to the following formula:

[0034]

[0035] Among them, VR c is the average radial velocity of the cluster box, vr t is the average radial velocity of the track, vr cri is the preset speed threshold;

[0036] The association score is calculated according to the following formula:

[0037] score total =0.4×score distance +0.2×score area +0.4×score velocity .

[0038] Preferably, in step 6, after the track enters the queuing area, the track management of the queuing area is implemented according to the track indexes of the lanes of the previous and next two frames, and then the point cloud of the queuing area is clustered by K-Means according to the track index of the lane of the current frame. After clustering, the specific method of associating the track of the queuing area with the cluster is as follows:

[0039] Step 6.1: When the track enters the queuing area, a lane track index is established to store the lane track index number of the current frame, thus realizing the mapping from track to lane;

[0040] Step 6.2: Search the lane track index of the previous frame, compare it with the lane track index of the current frame, and perform lost track query;

[0041] Step 6.3: Check the lost track target. If the track is valid, recall the lost target track and repeat step 6.1;

[0042] Step 6.4: Search the lane track index of the current frame, compare it with the lane track index of the previous frame, and find the newly added track;

[0043] Step 6.5: Check the newly added track. If the track is invalid, delete the false track and repeat step 6.1;

[0044] Step 6.6: Perform K-Means clustering on the queuing area point cloud;

[0045] Step 6.7: Associate the queuing area tracks with the clusters.

[0046] Compared with the prior art, the present invention has the following significant advantages: the present invention solves the problem of unstable tracking track of queuing vehicles at intersections by 4D millimeter-wave radar target tracking in traffic scenarios, forms a stable track before entering the queuing area, and recalls or deletes the track according to the mutual comparison of the previous and next frames after entering the queuing area, thereby realizing track management of the queuing area at the intersection; through the managed track, K-Means clustering is performed on the radar point cloud of the queuing area, and then the queuing area is associated, so that the track of the queuing area can be associated with the corresponding point cloud, reconstructs the observation of the track of the queuing area, and realizes the stability of the track of the queuing area.

[0047] The present invention is described in further detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of a method for realizing track stabilization of vehicles queuing at an intersection based on 4D millimeter wave radar according to the present invention.

[0049] Figure 2 It is a schematic diagram of the queuing area track management process.

[0050] Figure 3 It is a schematic diagram of the queue area clustering process. DETAILED DESCRIPTION

[0051] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0052] See also Figure 1As shown, a method for stabilizing the track of vehicles queuing at intersections based on 4D millimeter-wave radar is designed to use the point cloud provided by the 4D millimeter-wave radar to continuously track moving targets that have not entered the queuing area to generate a stable prior track. When the moving target enters the queuing area, the lane track management of the queuing area is performed, and the track of the vehicles in the queuing area is accurately matched with the clustered point cloud, so as to achieve accurate tracking and track stabilization of the queuing vehicles. The method comprises the following steps:

[0053] Step 1: Obtain 4D millimeter wave radar point cloud data and road calibration information;

[0054] Step 2: Preprocess the millimeter wave radar point cloud data according to the road calibration information;

[0055] Step 3: Perform DBSCAN clustering on the preprocessed 4D millimeter wave point cloud and output a clustering box containing the center coordinate position, length, width, height and average radial velocity;

[0056] Step 4: Associate the generated tracks with the clustering boxes, and generate new tracks for the unassociated clustering boxes;

[0057] Step 5: Determine whether the generated track enters the queue area. If it enters the queue area, perform queue area track management, that is, jump to step 6. If it does not enter the queue area, jump to step 7.

[0058] Step 6: After the track enters the queue area, the track management of the queue area is realized according to the track index of the lanes of the previous and next two frames. Then, according to the track index of the lanes of the current frame, the point cloud of the queue area is clustered by K-Means. After clustering, the track of the queue area is associated with the cluster.

[0059] Step 7: Output stable track information.

[0060] As a preferred embodiment of the present invention, the road calibration information includes the yaw angle, pitch angle, roll angle, radar height, and specific location coordinates of the motor vehicle lane, non-motor vehicle lane and intersection.

[0061] The 4D millimeter wave radar is arranged at the intersection.

[0062] As a preferred embodiment of the present invention, step 2 is specifically:

[0063] The specific location coordinates of the region of interest (ROI), i.e., motor vehicle lanes, non-motor vehicle lanes, and intersections, are obtained from road calibration. The location coordinates use a left-handed coordinate system with the 4D millimeter-wave radar as the coordinate origin. The point cloud of the 4D millimeter-wave radar is filtered based on this information, and point cloud preprocessing is achieved by setting thresholds for non-ROI areas, heights, speeds, and other attributes. When the coordinates of the radar point cloud are in the non-ROI area or the point cloud height in the ROI area is greater than 5m and the point cloud speed is within 0-1m / s, an invalid mark is given to the point, and these point clouds are not used in subsequent steps to achieve filtering.

[0064] As a preferred embodiment of the present invention, the step 3 is specifically as follows:

[0065] DBSCAN clustering is performed based on the three-dimensional coordinate position and relative radial velocity in the preprocessed millimeter-wave radar point cloud information. A radar point cloud is selected as the core point, and the difference between the three-dimensional coordinate position and the relative radial velocity between the point and the adjacent radar point cloud is calculated to see whether it meets the clustering parameters. If the clustering parameters are met, the adjacent radar points are judged as qualified adjacent points, and the number of adjacent points is calculated. After finding the adjacent points of the radar point cloud, the adjacent points are used as core points to continue finding adjacent points. This step is repeated until all adjacent points are found and a cluster containing n points is obtained.

[0066] According to the characteristics of millimeter wave radar point cloud, two groups of clustering parameters are set with 80m of road as the boundary. When the distance of radar point cloud in x direction is less than 80m, the following clustering parameters are used:

[0067]

[0068] When the distance in the x direction of the radar point cloud is greater than 80m, the following clustering parameters are used:

[0069]

[0070] Among them, x core ,y core , z core Indicates the three-dimensional distance of the core point relative to the millimeter-wave radar, vr core Indicates the relative radial velocity of the core point relative to the millimeter wave radar, x border ,y border , z border Indicates the three-dimensional distance of the nearby point relative to the millimeter-wave radar, vr core Indicates the relative radial velocity of the nearby point relative to the millimeter-wave radar.

[0071] Select the maximum and minimum values ​​in the x direction in the cluster, that is, x max ,x min, and the maximum and minimum values ​​in the y direction, that is, y max ,y min , use these four points to get the cluster bounding box. The center coordinates of the bounding box are x cneter =(x max +x min ) / 2,y cneter =(y max +y min ) / 2, the length of the bounding box = x max -x min , width = y max -y min , find the maximum and minimum values ​​in the z direction in the cluster box, that is, z max ,z min , height = z max -z min , add the relative radial velocities of all radar points in the cluster frame to get vr total , according to the number of radar points in the cluster box, the average radial velocity vr is obtained mean =vr total / n.

[0072] As a preferred embodiment of the present invention, step 4 is specifically as follows:

[0073] Perform global matching on clustering boxes and tracks, calculate the association score between clustering boxes and tracks, which is composed of weighted distance score, area score and speed score. Select a group of clustering boxes and tracks with the largest association score for association; for clustering boxes without corresponding tracks, create a new track.

[0074] The distance score is calculated according to the following formula:

[0075]

[0076] Among them, x c is the distance of the clustering box in the x direction, x t is the distance of the track in the x direction, y c is the distance of the clustering box in the y direction, y t is the distance of the track in the y direction, dist cri is the preset distance threshold.

[0077] The area score is calculated according to the following formula:

[0078]

[0079] Among them, area c is the area of ​​the clustering box, area t is the area of ​​the track, min represents the minimum value, and max represents the maximum value.

[0080] The speed score is calculated according to the following formula:

[0081]

[0082] Among them, VR c is the average radial velocity of the cluster box, vr t is the average radial velocity of the track, vr cri is the preset speed threshold.

[0083] The relevance score is calculated according to the following formula:

[0084] score total =0.4×score distance +0.2×score area +0.4×score velocity ;

[0085] As a preferred embodiment of the present invention, step 5 is specifically:

[0086] Determine whether the generated track enters the queue area. If the center point coordinates of the current frame track are less than the distance of the preset queue area, that is, x t <x q , where x t is the distance of the track in the x direction, x q To preset the distance of the queuing area, perform queuing area track management and jump to step 6. If you have not entered the queuing area, jump to step 7.

[0087] As a preferred embodiment of the present invention, step 6 is specifically:

[0088] Step 6.1: When the track enters the queuing area, a lane track index is established to store the lane track index number of the current frame to achieve mapping from track to lane.

[0089] As a preferred embodiment of the present invention, step 6.1 is specifically as follows:

[0090] When the target track enters the queuing area, that is, the coordinate x of the target track meets the preset range gate, then x track –x cross <d cri , where x track is the distance of the track in the x direction of the kth frame, x cross is the distance of the intersection in the x direction, d cri is the queue area threshold. The target has formed a stable track, a new lane track index is created, and the index number of the target track and the corresponding lane number are stored in it. Each lane is stored in the order of the smallest track coordinate x distance from the intersection.

[0091] Step 6.2: Search the lane track index of the previous frame, compare it with the lane track index of the current frame, and perform lost track query;

[0092] As a preferred embodiment of the present invention, the step 6.2 is specifically as follows:

[0093] According to the lane track index of the kth frame, starting from the first target of the i-th lane, search for the lane track index of the k+1th frame in the track of the lane track index. If the track target is not found, search for the track target in the lanes i–1 and i+1. If the target is not found, it is marked as a lost track, where i is the lane number of the road calibration information;

[0094] Step 6.3: Check the lost track target. If the track is valid, recall the lost target track and repeat step 6.1.

[0095] As a preferred embodiment of the present invention, the step 6.3 is specifically as follows:

[0096] Check the lost target, set a threshold for the number of detection frames and speed of the lost track, and judge it as a false target if it is less than the threshold, reduce the false tracks formed by ghost points of the millimeter-wave radar point cloud, check the distance between the lost target and the stop line, determine whether the first car in the team has left, and if the first car in the team has left, check whether there is target movement in the current frame. If there is target movement, do not modify it, otherwise keep the target to prevent the first car in the team from being lost; recall the lost track and add the attribute value of the track back to the track management;

[0097] Step 6.4: Search the lane track index of the current frame and compare it with the lane track index of the previous frame to find the newly added track.

[0098] As a preferred embodiment of the present invention, the step 6.4 is specifically as follows:

[0099] According to the lane track index of the k+1th frame, starting from the first target of the i-th lane, search for the lane track index of the k-th frame in the track of the lane track index of the k-th frame to see if there is a lane track index of the k+1th frame. If not found, it is determined that a new track appears in the i lane of the k+1th frame, and then the i-1 and i+1 lanes of the k-th frame are checked to see if there is such a track. If not, it is determined that the track is a new track, where i is the lane number of the road calibration information;

[0100] Step 6.5: Check the newly added track. If the track is invalid, delete the false track and repeat step 6.1. As a preferred embodiment of the present invention, step 6.5 is specifically as follows:

[0101] Check the newly added tracks, set thresholds for the detection frames and speeds of the newly added tracks, and judge them as false tracks if they are less than the thresholds, thereby reducing the false tracks formed by ghost points in the millimeter-wave radar point cloud; delete the newly added tracks and remove them from track management.

[0102] Step 6.6: Perform K-Means clustering on the queuing area point cloud;

[0103] As a preferred embodiment of the present invention, Figure 3 As shown, the queue area clustering in step 6.6 is as follows:

[0104] The number of lane tracks is obtained from the lane track index of the current frame, the 4D millimeter-wave radar point cloud of the queuing area is clustered by lane, and the millimeter-wave radar point cloud of the current lane is clustered by K-Means. The number of clusters is set to the number of current lane tracks k. K points are selected from the current lane point cloud as cluster centers, and the Euclidean distances from all points to these k points are calculated, that is, Among them, x c is the distance of the cluster center in the x direction, x i is the distance of the i-th radar point in the x direction, y c is the distance of the cluster center in the y direction, y i is the distance of the i-th radar point in the y direction, and the point with the minimum Euclidean distance from the cluster center is assigned to the cluster center. After all points are assigned, k clusters are formed; the mean of each cluster is calculated, and the k cluster centers are updated, that is, Among them, x c is the distance of the cluster center in the x direction, x j is the distance of the jth radar point in the cluster in the x direction, y c is the distance of the cluster center in the x direction, y is the distance of the jth radar point in the cluster in the y direction, and then calculate the difference between the new cluster center and the previous cluster center. When the difference is less than 0.0001 or the number of iterations reaches 9, the iteration ends and the point cloud clustering of the current lane is completed; repeat this step until the point clouds of all lanes are clustered.

[0105] Select the maximum and minimum values ​​in the x direction in the cluster, that is, x max ,x min , and the maximum and minimum values ​​in the y direction, that is, y max ,y min , use these four points to get the cluster bounding box. The center coordinates of the bounding box are x cneter =(x max +x min ) / 2,y cneter =(y max +y min) / 2, the length of the bounding box = x max -x min , width = y max -y min , find the maximum and minimum values ​​in the z direction in the cluster box, that is, z max ,z min , height = z max -z min , add the relative radial velocities of all radar points in the cluster frame to get vr total , according to the number of radar points in the cluster box, the average radial velocity vr is obtained mean =vr total / n.

[0106] Step 6.7: Associate the queuing area tracks with the clusters.

[0107] As a preferred embodiment of the present invention, the step 6.7 is specifically as follows:

[0108] Match the clustering frames and tracks of the first lane by lane, and calculate the association score of the clustering frames and tracks of the lane. The association score is composed of the sum of the distance score, area score and speed score. The specific calculation method is the same as step 4. Select a group of clustering frames and tracks with the largest association score for association until the clustering frames and tracks of all lanes are associated.

[0109] Among them, the lane track management of steps 6.1 to 6.5 is as follows: Figure 2 shown.

[0110] In actual application, the method for stabilizing the track of vehicles queuing at intersections based on 4D millimeter-wave radar has the following main processes:

[0111] (1) Input: 4D millimeter wave radar point cloud, road calibration information;

[0112] (2) Frame k: The target that has not entered the queuing area forms a stable track through multi-frame association. When the track enters the queuing area, due to the decrease in target speed, the corresponding point cloud of the target cannot be clustered into the corresponding point cloud cluster using DBSCAN. The point clouds of the targets in the same lane and the front and rear are clustered into one cluster, or the point clouds of the targets in adjacent lanes are clustered into one cluster, resulting in track jumps or false tracks in the queuing area. Therefore, when the track enters the queuing area, the lane track index is used to record the lane index number entering the queuing area as the comparison group for the lane track management of the k+1th frame. When the target track enters the queuing area, that is, the coordinate x of the target track meets the preset distance gate, then x track –x cross <d cri , where x trackis the distance of the track in the x direction of the kth frame, x cross is the distance of the intersection in the x direction, d cri is the queue area threshold. The target has formed a stable track. A new array is created to store the index number of the target track and the corresponding lane number. Each lane is stored in the order of the smallest track coordinate x distance from the intersection.

[0113] (3) Frame k+1: First, record the lane track index of the k+1 frame entering the queue area and compare it with the lane track index of the previous frame; based on the lane track index of the kth frame, start searching in the track of the lane track index of the k+1th frame from the first target in the i-th lane. If the track target is not found, search for the track target in the lanes i–1 and i+1. If the target is not found, mark it as a lost track, where i is the lane number of the road calibration information; check the lost target, set a threshold for the number of detection frames and speed of the lost track, and judge it as a false target if it is less than the threshold, so as to reduce the false tracks formed by the ghost points of the millimeter-wave radar, check the distance of the lost target from the stop line, and determine whether it is the first vehicle in the queue to leave. If the first vehicle in the queue leaves, check whether there is a target in the current frame. If there is target movement, do not modify it, otherwise keep the target to prevent the loss of the team leader; recall the lost track and add the attribute value of the track back to the track management; according to the lane track index of the k+1th frame, compare the lane track index of the k+1th frame of the i-th lane with the lane track index of the k-th frame. If a new track is found in the i lane of the k+1th frame, check whether the i-1 and i+1 lanes of the k-th frame have the track. If not, the track is judged to be a new track, where i is the lane number of the road calibration information; check the new track, set a threshold for the number of detection frames and speed of the new track, and judge it as a false track if it is less than the threshold, so as to reduce the false tracks formed by the ghost points of the millimeter-wave radar; delete the new track and remove it from the track management. Finally, update the lane track index of the k+1th frame.

[0114] (4) Frame k+1: According to the lane track index of frame k+1, obtain the number of tracks k of lane i, and use K-Means clustering for the 4D millimeter-wave radar point cloud of the lane. The number of clusters is set to the number of tracks in the current lane, and the clustering parameter uses the Euclidean distance, that is, until all lanes are clustered. Next, associate the lane tracks with the clusters in the queuing area.

[0115] The method for stabilizing the tracks of vehicles queuing at intersections based on 4D millimeter-wave radar of the present invention solves the problem of unstable tracks of queuing vehicles at intersections by 4D millimeter-wave radar target tracking in traffic scenarios. A stable track is formed before entering the queuing area, and after entering the queuing area, the track is recalled or deleted according to the mutual comparison of the previous and next frames, thereby realizing track management of the queuing area at the intersection; through the managed track, K-Means clustering is performed on the radar point cloud of the queuing area, and then the queuing area is associated, so that the track of the queuing area can be associated with the corresponding point cloud, the observation of the track of the queuing area is reconstructed, and the stability of the track of the queuing area is realized.

[0116] The present invention significantly improves the accuracy of traffic monitoring, enhances the safety of vehicle driving, and optimizes traffic flow management, thereby contributing to the development of intelligent transportation systems.

[0117] The above-mentioned embodiments only express the preferred implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention.

Claims

1. A method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar, characterized in that: include: Step 1: Obtain 4D millimeter wave radar point cloud data and road calibration information; Step 2: Preprocess the millimeter wave radar point cloud data according to the road calibration information; Step 3: Perform DBSCAN clustering on the preprocessed 4D millimeter wave point cloud to obtain a clustering box containing the center coordinate position, length, width, height and average radial velocity; Step 4: Associate the generated tracks with the clustering boxes, and generate new tracks for the unassociated clustering boxes; Step 5: Determine whether the generated track enters the queue area. If it enters the queue area, perform queue area track management, that is, jump to step 6. If it does not enter the queue area, jump to step 7. Step 6: After the track enters the queue area, the track management of the queue area is realized according to the track index of the lanes of the previous and next two frames. Then, according to the track index of the lanes of the current frame, the point cloud of the queue area is clustered by K-Means. After clustering, the track of the queue area is associated with the cluster. Step 7: Output stable track information.

2. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 1 is characterized in that: Step 2: The specific method for preprocessing the millimeter wave radar point cloud data according to the road calibration information is as follows: The region of interest is obtained from road calibration, and the region of interest includes the specific location coordinates of motor vehicle lanes, non-motor vehicle lanes and intersections. The specific location coordinates of the intersection use the left-hand coordinate system, and the 4D millimeter-wave radar is used as the coordinate origin. The point cloud of the 4D millimeter-wave radar is filtered, and the point cloud preprocessing is achieved by setting thresholds for the height and speed attributes of the non-ROI area.

3. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 1 is characterized in that: Step 3 performs DBSCAN clustering on the preprocessed 4D millimeter wave point cloud, and the specific method of outputting the bounding box containing the center coordinate position, length, width, height and average radial velocity is as follows: DBSCAN clustering is performed based on the three-dimensional coordinate position and relative radial velocity in the preprocessed millimeter-wave radar point cloud information. A radar point cloud is selected as the core point. The difference between the three-dimensional coordinate position and the relative radial velocity between the point and the adjacent radar point cloud is calculated to see whether it meets the clustering parameters. If the clustering parameters are met, the adjacent radar points are judged as qualified adjacent points, and the number of adjacent points is calculated. After finding the adjacent points of the radar point cloud, the adjacent points are used as core points to continue to find adjacent points. The steps of finding adjacent points are repeated until all adjacent points are found, and a cluster containing n points is obtained. According to the characteristics of millimeter wave radar point cloud, two groups of clustering parameters are set with 80m of road as the boundary. The specific parameters within 80m are: 80m away: Among them, x core ,y core , z core Indicates the three-dimensional distance of the core point relative to the millimeter-wave radar, vr core Indicates the relative radial velocity of the core point relative to the millimeter wave radar, x border ,y border , z border Indicates the three-dimensional distance of the nearby point relative to the millimeter-wave radar, vr core Indicates the relative radial velocity of the nearby point relative to the millimeter-wave radar; Select the maximum and minimum values ​​in the x direction in the cluster, that is, x max ,x min , and the maximum and minimum values ​​in the y direction, that is, y max ,y min , use these four points to get the cluster bounding box; The center coordinate x of the bounding box cneter =(x max +x min ) / 2,y cneter =(y max +y min ) / 2, the length of the bounding box is length = x max -x min , width = y max -y min , find the maximum and minimum values ​​in the z direction in the cluster box, that is, z max ,z min , height = z max -z min , add the relative radial velocities of all radar points in the cluster frame to get vr total , the average radial velocity vr is obtained according to the number of radar points in the cluster box mean =vr total / n.

4. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 1, characterized in that: Step 4 associates the generated track with the clustered point cloud clusters. The specific method for generating new tracks from unassociated clusters is as follows: Perform global matching on clusters and tracks, calculate the association scores between clusters and tracks, select a group of clusters and tracks with the largest association scores for association; for clusters without corresponding tracks, create a new track.

5. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 4, characterized in that: The association score between clusters and tracks is composed of the weighted distance score, area score and speed score. The calculation process is: The distance score is calculated according to the following formula: Among them, x c is the distance of the clustering box in the x direction, x t is the distance of the track in the x direction, y c is the distance of the clustering box in the y direction, y t is the distance of the track in the y direction, dist cri is the preset distance threshold; The area score is calculated according to the following formula: Among them, area c is the area of ​​the clustering box, area t is the area of ​​the track, min represents the minimum value, and max represents the maximum value; The speed score is calculated according to the following formula: Among them, VR c is the average radial velocity of the cluster box, vr t is the average radial velocity of the track, vr cri is the preset speed threshold; The association score is calculated according to the following formula: score total =0.4×score distance +0.2×score area +0.4×score velocity 。 6. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 1, characterized in that: Step 6: After the track enters the queue area, the track management of the queue area is realized according to the track index of the lanes of the previous and next two frames. Then, the point cloud of the queue area is clustered by K-Means according to the track index of the lane of the current frame. After clustering, the specific method of associating the track of the queue area with the cluster is as follows: Step 6.1: When the track enters the queuing area, a lane track index is established to store the lane track index number of the current frame, thus realizing the mapping from track to lane; Step 6.2: Search the lane track index of the previous frame, compare it with the lane track index of the current frame, and perform lost track query; Step 6.3: Check the lost track target. If the track is valid, recall the lost target track and repeat step 6.1; Step 6.4: Search the lane track index of the current frame, compare it with the lane track index of the previous frame, and find the newly added track; Step 6.5: Check the newly added track. If the track is invalid, delete the false track and repeat step 6.1; Step 6.6: Perform K-Mean on the queue area point cloud s Clustering; Step 6.7: Associate the queuing area tracks with the clusters.

7. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 5, characterized in that: Step 6.1: When the track enters the queuing area, a lane track index is established to store the lane track index number of the current frame. The specific method for mapping the track to the lane is as follows: When the target track enters the queuing area, that is, the coordinate x of the target track meets the preset range gate, then x track –x cross <d cri , where x track is the distance of the track in the x direction of the kth frame, x cross is the distance of the intersection in the x direction, d cri For the queue area threshold, the target has formed a stable track, a new lane track index is created, and the index number of the target track and the corresponding lane number are stored in it. Each lane is stored in the order of the smallest track coordinate x distance from the intersection.

8. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 5, characterized in that: Step 6.2 Search the lane track index of the previous frame and compare it with the lane track index of the current frame. The specific method for querying the lost track is as follows: According to the lane track index of the kth frame, start searching in the track of the lane track index of the k+1th frame from the first target in the i-th lane. If the track target is not found, search for the track target in the lanes i–1 and i+1. If the target is not found, it is marked as a lost track, where i is the lane number of the road calibration information.

9. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 5, characterized in that: Step 6.3 is as follows: Check the lost target, set a threshold for the number of detection frames and speed of the lost track, and judge it as a false target if it is less than the threshold, reduce the false tracks formed by ghost points of the millimeter-wave radar point cloud, check the distance between the lost target and the stop line, and determine whether the first car in the team has left. If the first car in the team has left, check whether there is target movement in the current frame. If there is target movement, do not modify it, otherwise keep the target to prevent the first car in the team from being lost; Recall the lost track and add the track attribute value back to the track management.

10. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 5, characterized in that: The step 6.4 is specifically as follows: According to the lane track index of the k+1th frame, start searching in the track of the lane track index of the kth frame from the first target in the i-th lane. If a new track is found in the i-th lane of the k+1th frame, check whether the i-1 and i+1 lanes of the k-th frame have the track. If not, the track is determined to be a new track, where i is the lane number of the road calibration information.

11. The method for achieving track stabilization of vehicles queuing at intersections based on 4D millimeter wave radar according to claim 5, characterized in that: Step 6.6 The specific method of K-Means clustering on the queuing area point cloud is: The number of lane tracks is obtained from the lane track index of the current frame, the 4D millimeter-wave radar point cloud of the queuing area is clustered by lane, and the millimeter-wave radar point cloud of the current lane is clustered by K-Means. The number of clusters is set to the number of current lane tracks k. K points are selected from the current lane point cloud as cluster centers, and the Euclidean distances from all points to these k points are calculated, that is, Among them, x c is the distance of the cluster center in the x direction, x i is the distance of the i-th radar point in the x direction, y c is the distance of the cluster center in the y direction, y i is the distance of the i-th radar point in the y direction; Assign the point with the minimum Euclidean distance from the cluster center to the cluster center. After all points are assigned, k clusters are formed. Calculate the mean of each cluster and update the k cluster centers, that is, Among them, x c is the distance of the cluster center in the x direction, x j is the distance of the jth radar point in the cluster in the x direction, y c is the distance of the cluster center in the x direction, and y is the distance of the jth radar point in the cluster in the y direction; Calculate the difference between the new cluster center point and the previous cluster center point. When the difference is less than 0.0001 or the number of iterations reaches the set number, end the iteration and complete the point cloud clustering of the current lane. Repeat this step until the point clouds of all lanes are clustered. Select the maximum and minimum values ​​in the x direction in the cluster, that is, x max ,x min , and the maximum and minimum values ​​in the y direction, that is, y max ,y min , use these four points to get the cluster bounding box; the center coordinate of the bounding box is x cneter =(x max +x min ) / 2,y cneter =(y max +y min ) / 2, the length of the bounding box is length = x max -x min , width = y max -y min , find the maximum and minimum values ​​in the z direction in the cluster box, that is, z max ,z min , height = z max -z min , add the relative radial velocities of all radar points in the cluster box to get vr total , the average radial velocity vr is obtained according to the number of radar points in the cluster box mean =vr total / n.

Images