Radar tracking method, noise removal method, device and equipment

Abstract

To provide a radar tracking method, noise removal method, device and instrument.SOLUTION: A radar tracking method is configured to: perform clustering with respect to a point cloud acquired by sensing of a radar in a range-Doppler plane, and acquire a range-Doppler point cloud cluster; perform secondary clustering with respect to the range-Doppler point cloud cluster in a spatial dimension or angular dimension, and acquire a secondary clustered point cloud cluster; and determine a tracking object on the basis of the range-Doppler point cloud cluster and the secondary clustered point cloud cluster corresponding to the range-Doppler point cloud cluster.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to the field of information technology, and in particular to radar tracking methods, noise removal methods, devices and equipment. [Background technology]

[0002] Radar detects information such as distance, speed, and azimuth of moving objects through radio signals and can form a point cloud. Conventional radar tracking algorithms can track objects by performing operations such as clustering and filtering based on the spatial information of the point cloud. However, at long distances (when the distance between the moving object and the radar is large), the accuracy of the radar's spatial measurement deteriorates, making the point cloud prone to dispersion and making clustering impossible. Summary of the Invention [Problem to be solved by the invention]

[0003] To solve the above problems, embodiments of the present invention aim to provide a radar tracking method, a noise removal method, a device and an apparatus. [Means for solving the problem]

[0004] According to a first aspect of an embodiment of the present invention, there is provided a radar tracking method, the method comprising: Perform clustering on the point cloud acquired by radar detection in the range-Doppler plane to obtain a range-Doppler point cloud cluster; A secondary clustering is performed on the distance-Doppler point cloud clusters in a spatial dimension or an angular dimension to obtain secondary clustered point cloud clusters. Obtain a clustered point cloud cluster; and determining a tracked object based on the range-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster;

[0005] According to a second aspect of an embodiment of the present invention, there is provided a method for denoising, the method comprising: Statistics are performed on point cloud noise information in the distance-Doppler plane, and the point cloud noise information is calculated by the noise statistics total number n n , and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Includes; Analyzing the point cloud clusters in the range-Doppler plane based on the point cloud noise information to determine whether the point cloud clusters are noise-induced point cloud clusters; and If the point cloud cluster is a noisy point cloud cluster, removing the noisy point cloud cluster in the range-Doppler plane.

[0006] According to a third aspect of an embodiment of the present invention, there is provided a radar tracking apparatus, the apparatus comprising: a first clustering unit that performs clustering on the point cloud acquired by radar sensing in the range-Doppler plane to obtain range-Doppler point cloud clusters; a second clustering unit for performing secondary clustering on the range-Doppler point cloud clusters in a spatial dimension or an angular dimension to obtain secondary clustered point cloud clusters; and A determination unit is included for determining a tracked object based on the range-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster.

[0007] According to a fourth aspect of an embodiment of the present invention, there is provided a noise removal apparatus, the apparatus comprising: A statistical unit for performing statistics on point cloud noise information in a distance-Doppler plane, the point cloud noise information being processed by a noise statistical total number nn , and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Statistical units, including; an analysis unit that analyzes the point cloud clusters in the distance-Doppler plane based on the point cloud noise information and determines whether the point cloud clusters are noise-induced point cloud clusters; and and a processing unit for removing the noisy point cloud clusters in the range-Doppler plane when the point cloud clusters are noisy point cloud clusters.

[0008] According to another aspect of an embodiment of the present invention, there is provided a computing device, the computing device including a processor and a memory, the memory storing a computer program, the processor configured to execute the computer program to implement a method according to the first or second aspect. [Effects of the Invention]

[0009] The advantageous effects of the present invention are as follows: on the one hand, the double clustering strategy improves the tracking accuracy and extends the effective tracking range, thereby solving the problem that the accuracy of radar spatial measurement is poor at long distances, the point cloud is easily dispersed, and clustering cannot be performed; on the other hand, the accuracy of spatial measurement can be further improved by removing point cloud clusters caused by noise in the distance-Doppler plane. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 2 illustrates an example of a radar tracking method according to an embodiment of the present invention. [Figure 2] One indication of the distance-Doppler plane; [Figure 3] FIG. 10 is a diagram illustrating an example of removing noise point cloud clusters in a range-Doppler plane. [Figure 4]FIG. 10 is a diagram illustrating an example of updating point cloud noise information on a range-Doppler plane. [Figure 5] FIG. 1 shows a radar point cloud in the XY plane. [Figure 6] FIG. 1 illustrates a radar point cloud in the range-Doppler plane. [Figure 7] FIG. 10 illustrates an example of performing secondary clustering on range-Doppler point cloud clusters in the spatial dimension. [Figure 8] FIG. 10 is a diagram illustrating an example of correcting a spatial position. [Figure 9] FIG. 10 illustrates an example of performing secondary clustering on range-Doppler point cloud clusters in the angle dimension. [Figure 10] FIG. 10 illustrates an example of determining a tracking object. [Figure 11] FIG. 10 is a diagram illustrating an example of a noise removal method according to an embodiment of the present invention. [Figure 12] 1 is a diagram illustrating an example of a radar tracking device according to an embodiment of the present invention. [Figure 13] FIG. 1 is a diagram illustrating an example of a noise removal device according to an embodiment of the present invention. [Figure 14] FIG. 1 illustrates a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings. However, these embodiments are merely illustrative and are not intended to limit the scope of the present invention.

[0012] <Example of the first aspect> An embodiment of the present invention provides a radar tracking method. Figure 1 shows an example of the radar tracking method in an embodiment of the present invention. As shown in Figure 1, the method includes the following steps:

[0013] 101: Performing clustering on the point cloud acquired by radar sensing in the range-Doppler plane to obtain a range-Doppler point cloud cluster; 102: Performing secondary clustering on the range-Doppler point cloud cluster in a spatial dimension or an angular dimension to obtain a secondary clustered point cloud cluster; 103: Determine a tracking object based on the range-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster.

[0014] According to the method of the embodiment of the present invention, the tracking accuracy is improved and the effective range of tracking is expanded by using a two-step clustering strategy, which solves the problem that the accuracy of radar spatial measurement is poor at long distances, the point cloud is easily dispersed, and clustering cannot be performed.

[0015] In an embodiment of the present invention, a radar periodically transmits a radio signal into space, receives a signal reflected by an object in space (referred to as a reflected signal), and analyzes the reflected signal to output a point cloud, which includes the spatial position and velocity information of the object within the radar's coverage. The point cloud output by the radar (referred to as a radar point cloud) is {o i ,1≦i≦n o}, of which o i is the i-th point, and n o is the number of points in the point cloud.

[0016] Among them, point o in the radar point cloud i Hao i =(r i ,v i ,x i ,y i ,z i ,α i ,β i ) may be expressed as r i is point o i is the distance frequency point of v i is point o i is the Doppler velocity frequency point of (x i ,y i,z i ) is point o i are the spatial coordinates of α i and β i are the points o i The horizontal and vertical angular frequency points are the distance frequency points r i is point o i is used to calculate the distance to the radar, and the radar range resolution is Δ r When , point o i The distance from the radar is r i Δ r Among them, the Doppler velocity frequency point v i is point o i is used to calculate the velocity relative to the radar, and the radar velocity resolution is Δ v When , point o i The Doppler velocity for the radar is v i Δ v The maximum number of distance frequency points and the maximum number of Doppler velocity frequency points of the radar are n r and n v Among them, the horizontal angular frequency point α i is point o i Horizontal angle A=w to the radar a α i / n a are used to calculate, among which, n a is the total number of frequency points in the horizontal angle FFT, and w a is a parameter related to the radar's multi-antenna arrangement (setting). Also, the horizontal angular frequency point α i Similarly, the vertical angular frequency point β i By point o i The vertical angle to the radar can be calculated.

[0017] In some implementations of the present invention, clustering the point cloud in the distance-Doppler plane includes mapping the point cloud onto the distance-Doppler plane, dividing the point cloud into a plurality of point cloud clusters (referred to as distance-Doppler point cloud clusters) and non-clustered point clouds (points that cannot form a point cloud cluster are referred to as "non-clustered point clouds") based on the distances of the point clouds in the distance-Doppler plane, and determining the number of points in each point cloud cluster to be less than a first threshold T n1 and the distance from each point in each point cloud cluster to the point cloud cluster is greater than a second threshold T d1 is smaller than.

[0018] In the above embodiment, the range-Doppler plane is a two-dimensional plane, the horizontal axis of which is the range frequency points and the vertical axis of which is the Doppler velocity frequency points, and the radar point cloud can be mapped onto the range-Doppler plane based on the range frequency points and Doppler velocity frequency points of each point in the radar point cloud.

[0019] Figure 2 shows an example of a radar point cloud mapped onto a range-Doppler plane. In the point cloud in area A, the number of points is large and the distribution is concentrated, which may be due to moving objects. In area B, the number of points is small and the distribution is dispersed, which may be due to noise.

[0020] In the above embodiment, the clustering operation is performed in the distance-Doppler plane, and the point cloud is divided into several clusters (referred to as distance-Doppler point cloud clusters) based on the distance of the point cloud in the distance-Doppler plane. After the distance-Doppler clustering is performed, all points in the point cloud can be divided into several distance-Doppler point cloud clusters and non-cluster points. Among them, the points in the non-cluster point cloud may be due to noise.

[0021] In the above embodiment, a range-Doppler point cloud cluster is composed of multiple points that are close to each other on the range-Doppler plane, and the number of points is determined based on a threshold T n1 (called the first threshold), and the distance from each point to the point cloud cluster is greater than the threshold T d1 (called the second threshold).

[0022] For example, C={o k ,1≦k≦nc} represents the distance-Doppler point cloud cluster, among which, n c is the number of points in the point cloud cluster, and o k is the k-th point belonging to the point cloud cluster, and in this case n c >T n1 and point o k Distance d(o k ,C) is the threshold T d1 is smaller than d(o k ,C) <T d1 is.

[0023] In some embodiments, the distance from each point in each point cloud cluster to the point cloud cluster refers to the minimum distance from the point to all other points in the point cloud cluster.

[0024] For example, point o k Distance d(o k ,C) is the point o k is the minimum distance between a point and any other point in the point cloud cluster C,

number

[0025] In some embodiments, the distance between two points in a point cloud cluster is a weighted sum of the absolute value of the difference in distance frequency points of the two points and the absolute value of the difference in Doppler velocity frequency points of the two points.

[0026] For example, point o in point cloud cluster C j and k distance between - distance d(o j ,o k ) is the point o j and k is a weighted sum of the absolute value of the distance frequency point difference and the absolute value of the Doppler velocity frequency point difference, i.e., d(o j ,o k )=a|r j -r k |+(1-a)|v j -v k | (1) is.

[0027] Among them, r j and r k are the point groups o j and o k is the distance frequency point of v j and v k are the point groups o j and o k is the Doppler velocity frequency point, and a is a predetermined weight value (weight) in the range of 0 to 1.

[0028] Note that the above formula (1) for calculating the distance between points in a point cloud cluster is merely an example, and the present invention is not limited thereto. The distance between points in a point cloud cluster may be calculated by other conventional distance calculation methods, such as the Euclidean distance calculation algorithm.

[0029] In the embodiment of the present invention, the specific algorithm for performing clustering on the distance-Doppler plane is not limited, and for example, DBSCAN (Density-Based Spatial Clustering of Conventional clustering methods such as (Applications with Noise) and (OPTICS) ordering points to identify the clustering structure may be employed.

[0030] In some embodiments, as shown in FIG. 1, the method may further include the following steps:

[0031] 104: Remove point cloud clusters due to noise in the range-Doppler point cloud clusters.

[0032] In some embodiments, as shown in Figure 1, 104 is performed after 101, i.e., after obtaining the range-Doppler point cloud clusters by 101, the noisy point cloud clusters in the range-Doppler point cloud clusters can be removed. Removing the noisy point cloud clusters can further improve the accuracy of the spatial measurement of radar tracking.

[0033] In some embodiments, after 102, an operation of removing noise-caused point cloud clusters in the secondary clustered point cloud clusters may be added, and the specific operation flow is similar to that of 104. Therefore, hereinafter, only 104 will be taken as an example to describe the method of removing noise-caused point cloud clusters in the secondary clustered point cloud clusters.

[0034] FIG. 3 is a diagram illustrating an example of removing point cloud clusters due to noise in range-Doppler point cloud clusters. As shown in FIG. 3, the method includes the following steps:

[0035] 301: Performing statistics on point cloud noise information on the distance-Doppler plane, the point cloud noise information is processed for a total number of noise statistics n n , and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Includes; 302: Analyzing the range-Doppler point cloud cluster based on the point cloud noise information to determine whether the point cloud cluster is a point cloud cluster caused by noise; 303: If the point cloud cluster is a noisy point cloud cluster, remove the noisy point cloud cluster in the range-Doppler plane.

[0036] In some embodiments, the point cloud noise information on the range-Doppler plane includes the total number of noise statistics and the number of times that noise points appear at each position on the plane. In some implementations, determining whether a range-Doppler point cloud cluster (e.g., point cloud cluster C) is a noise point cloud cluster (referred to as a noise point cloud cluster) can be performed as follows: based on the above point cloud noise information, calculate the probability (represented as P(C)) that the point cloud cluster C is noise, and if the probability P(C) that the point cloud cluster C is noise is greater than or equal to a threshold T n If it is greater than the third threshold, it is determined that the point cloud cluster C is a noise point cloud cluster; otherwise, it is determined that the point cloud cluster C is a moving object.

[0037] In some embodiments, the probability that a range-Doppler point cloud cluster is a noise point cloud cluster is the average probability that all points belonging to the point cloud cluster are noise. For example, still taking point cloud cluster C as an example, the probability P(C) that point cloud cluster C is noise is the average probability that each point in point cloud cluster C is noise:

number

[0038] Among them, C is the distance-Doppler point cloud cluster, and o k are points in the point cloud cluster C, and n C is the number of points in the point cloud cluster C; P(C) is the probability that the range-Doppler point cloud cluster C is a noise point cloud cluster; P(o k) is point o k is the probability that it is noise.

[0039] In some embodiments, the probability that each point in the point cloud cluster C is noise is the ratio of the number of times the noise point appears at each location in the range-Doppler plane to the total number of times the noise statistic appears.

[0040] For example, if the total number of noise statistics is n n The number of times that a noise point appears at each position (the position of the distance frequency point r and the Doppler frequency point v) on the distance-Doppler plane is n r,v and the probability that a noise point appears at that position is represented by P(r,v), P(r,v)=n r,v / n n (3) is.

[0041] In equation (2), P(o k )=P(r k ,v k ), among which, r k and v k are the points o k are the distance frequency points and the Doppler velocity frequency points.

[0042] In some embodiments of the present invention, as shown in FIG. 3, the method further includes the following steps:

[0043] 304: Update point cloud noise information in the range-Doppler plane, which includes adding 1 to the noise statistics total count and adding 1 to the count of noise occurrences at positions in the range-Doppler plane corresponding to all points belonging to the range-Doppler noise point cloud cluster and all points in the non-cluster point cloud.

[0044] 4 is a diagram showing an example of updating point cloud noise information in the range-Doppler plane. As shown in FIG. 4, the method includes the following steps:

[0045] 401: Update the total number of noise statistics and add 1 to the total number of noise statistics; 402-405: Update the number of times noise appears at each position point on the range-Doppler plane.

[0046] In the example of Figure 4, (r, v) represents a point at one position on the range-Doppler plane, where r is the range frequency point and v is the Doppler velocity frequency point. In 403, it is determined whether a point exists in the range-Doppler noise point cloud cluster or non-cluster point cloud where the range frequency point is r and the Doppler velocity frequency point is v. If so, perform the operation of 404; otherwise, do not perform any processing. In 404, the number of times noise appears at the position (r, v) is updated, and the number of times noise appears at that position is added by 1.

[0047] Although the above description has been given using only the example of removing point cloud clusters due to noise from the range-Doppler point cloud cluster obtained in 101, a similar method can also be applied to removing point cloud clusters due to noise from the secondary clustered point cloud cluster obtained in 102. A detailed description thereof will be omitted here.

[0048] In addition, although only one method for removing point cloud clusters caused by noise has been described above, the present invention is not limited thereto. In the embodiments of the present invention, other feasible methods can also be used to remove point cloud clusters caused by noise, and detailed descriptions thereof will be omitted here.

[0049] In an embodiment of the present invention, in 102, a secondary clustered point cloud cluster can be obtained by performing secondary clustering on the above-mentioned range-Doppler point cloud cluster in the spatial dimension or by performing secondary clustering on the above-mentioned range-Doppler point cloud cluster in the angular dimension.

[0050] In an embodiment of the present invention, if two moving objects have the same distance and velocity from the radar, the distance-Doppler clustering operation cannot distinguish between the two objects after their point clouds are mapped to the range-Doppler plane. As shown in FIG. 5, a radar captures point clouds of two moving objects, and moving objects A and B have the same distance from the radar and the same velocity relative to the radar. As shown in FIG. 6, after mapping to the range-Doppler plane, the radar point clouds are mixed and become only one range-Doppler point cloud cluster, making it impossible to distinguish between objects A and B. In contrast, in an embodiment of the present invention, secondary clustering is performed on the range-Doppler point cloud cluster determined to be a moving object by the above-mentioned 102, and point clouds belonging to different moving objects in the range-Doppler point cloud cluster can be distinguished using spatial position information (spatial dimension) or angle information (angular dimension).

[0051] FIG. 7 is a diagram showing an example of performing secondary clustering on the range-Doppler point cloud clusters in the spatial dimension (abbreviated as spatial position clustering). As shown in FIG. 7, the method includes the following steps:

[0052] 701: In each distance-Doppler point cloud cluster, distance frequency points exceed a fourth threshold T r Perform spatial position correction for all points greater than ; 702: Based on the corrected spatial positions, perform spatial position clustering on all points in each range-Doppler point cloud cluster, and obtain a spatial point cloud cluster and / or an unclustered point cloud corresponding to each range-Doppler point cloud cluster as the secondary clustered point cloud cluster.

[0053] In an embodiment of the present invention, based on the spatial distance of points, spatial location clustering can divide points belonging to the same distance-Doppler point cloud cluster into several sub-point cloud clusters and one non-cluster point cloud. In an embodiment of the present invention, the sub-point cloud clusters obtained by spatial location clustering are called spatial point cloud clusters.

[0054] In an embodiment of the present invention, the spatial position clustering includes two steps: first, the spatial positions (i.e., X, Y, Z) of the points that need spatial position correction are corrected (701) to solve the problem of the uncertainty of the radar measurement at long distances, and then the clustering operation is performed using the corrected spatial positions of the points. The present invention is not limited to a clustering method, and conventional clustering methods such as DBSCAN and OPTICS may be adopted.

[0055] 8 is a diagram showing an example of spatial position correction. As shown in FIG. 8, the method includes the following steps.

[0056] 801: point o i =(r i ,v i ,x i ,y i ,z i ,α i ,β i ), and then type r i is point o i is the distance frequency point of v i is point o i is the Doppler velocity frequency point of (x i ,y i ,z i ) is point o i are the spatial coordinates of α i and β i are the points o i are the horizontal and vertical angular frequency points; 802: Point o i Distance frequency point r i is the threshold T rDetermine whether it is greater than , if yes, perform the subsequent operation, if not, do not perform spatial position correction; 803: Performing spatial position correction for points that require spatial position correction; 804: no correction of the spatial position of the point is required; 805: (x', y', z') are the spatial coordinates of the corrected point.

[0057] In the embodiment of the present invention, as shown in 803 of FIG. 8, two types of spatial position correction methods are shown.

[0058] For example, if the distance frequency point is greater than the fourth threshold T r for each point greater than , keeping the value of its spatial coordinate x unchanged, setting the value of its spatial coordinate z to a predetermined value, and recalculating the value of its spatial coordinate y;

number

[0059] Among them, (x i ,y i ,z i ) are the original spatial coordinates of the point, and (x i ',y i ',z i ') is the updated spatial coordinate of the point, and z p is the predetermined value, which is the average height of the moving object relative to the radar.

[0060] Also, for example, when the distance frequency point is equal to or exceeds the fourth threshold T r For each point greater than , the y-value and z-value of that spatial coordinate are set to predetermined values, and the x-value of that spatial coordinate is recalculated;

number

[0061] Among them, (x i ,y i ,z i ) are the original spatial coordinates of the point, and (x i',y i ',z i ') is the updated spatial coordinate of the point, and y p and z p is a predetermined value, and y p is the average value of the Y axis relative to the radar centerline in the surveillance scene, and z p is the average height of the moving object relative to the radar.

[0062] The above-mentioned two types of spatial position correction methods are merely examples, and the present invention is not limited to these.

[0063] In equations (4) and (5), the value of the spatial coordinate Z is set to a predetermined value z p The predetermined value is the average height of the moving object relative to the radar. In equation (4), the value of the spatial coordinate X is kept unchanged, and then the value of Y is calculated again. In equation (5), the value of the spatial coordinate Y is set to a predetermined value y p Then, the value of X is calculated again. This correction method is suitable for long and narrow object tracking scenes (e.g., corridors), where the Y axis is oriented along the length of the long and narrow scene, and the value of y is set to a predetermined value. p may be set to the average value of the Y axis relative to the radar of the center line of the surveillance scene, and a predetermined value z p is the average height of the moving object relative to the radar.

[0064] In an embodiment of the present invention, after spatial position correction is performed on the points in the distance-Doppler point cloud cluster, clustering is performed based on the spatial distance of the corrected points to obtain multiple spatial point cloud clusters and unclustered point clouds. A spatial point cloud cluster consists of multiple points that are close to each other in space, and the number of points is limited to a threshold T n2 (called the fifth threshold), and the distance from each point to the point cloud cluster is greater than the threshold T d2 (referred to as the sixth threshold).

[0065] In some embodiments, the distance from each point in each spatial point cloud cluster to the spatial point cloud cluster is the minimum of the distances from the point to all other points in the spatial point cloud cluster.

[0066] For example, D={o l ,1≦l≦n D} represents the spatial point cloud cluster, among which, n D is the number of points in the spatial point cloud cluster, and n D >T n2 and o l is the l-th point belonging to the spatial point group cluster, and its distance to the spatial point group cluster is the point o l is the minimum value of the distance between a point and any other point in the spatial point cloud cluster,

number

[0067] In some embodiments, the distance between two points in a spatial point cloud cluster is the Euclidean distance of the spatial coordinates of the two points.

[0068] For example, point o j and o l The distance between is the Euclidean distance between the spatial coordinates of these two points, i.e.,

number

[0069] It should be noted that the above-mentioned method for calculating the distance between two points in a spatial point cloud cluster is merely an example, and the present invention is not limited thereto. In the present invention, other feasible methods may also be used to calculate the distance between two points in a spatial point cloud cluster.

[0070] FIG. 9 is a diagram showing an example of performing secondary clustering on the range-Doppler point cloud clusters in the angle dimension (called azimuth clustering). As shown in FIG. 9, the method includes the following steps:

[0071] 901: For all points in each range-Doppler point cloud cluster, perform azimuth angle clustering based on the azimuth angle information of all the points, and obtain an azimuth point cloud cluster and / or an unclustered point cloud corresponding to each range-Doppler point cloud cluster as the secondary clustered point cloud cluster.

[0072] In an embodiment of the present invention, based on the angular frequency point distance of the points, azimuth clustering can divide the points belonging to the same distance-Doppler point cloud cluster into several sub-point cloud clusters and one non-cluster point cloud. In an embodiment of the present invention, the sub-point cloud cluster obtained by azimuth clustering is called an azimuth point cloud cluster.

[0073] In an embodiment of the present invention, one orientation point cloud cluster is composed of a plurality of points whose angular frequency points are close to each other, and the number of points is less than a threshold T n3 (called the seventh threshold), and the distance from each point to the oriented point cloud cluster is greater than the threshold T d3 (8th threshold) is smaller.

[0074] In some embodiments, the distance from each point in each oriented point cloud cluster to the oriented point cloud cluster is the minimum of the distances from the point to all other points in the oriented point cloud cluster.

[0075] For example, E={o m ,1≦m≦n E} represents the oriented point cloud cluster, of which n E is the number of points in the oriented point cloud cluster, and n E <T n3 and o m is the m-th point belonging to the oriented point cloud cluster, and its distance to the oriented point cloud cluster is point o m is the minimum distance between a point and any other point in the oriented point cloud cluster,

number

[0076] In some embodiments, the distance between two points in an orientation point cloud cluster is a weighted sum of the absolute value of the difference in horizontal angular frequency points of the two points and the absolute value of the difference in vertical angular frequency points of the two points.

[0077] For example, point o j and m The angular frequency point distance is the weighted sum of the absolute value of the horizontal angular frequency point difference and the absolute value of the vertical angular frequency point difference between these two points, i.e., d(o j ,o m )=b|α j -α m |+(1-b)|β j -β m | (7) is.

[0078] Among them, α j and β j is point o j are the horizontal and vertical angular frequency points of α m and β m is point om are the horizontal and vertical angular frequency points, and b is a predetermined weight value between 0 and 1.

[0079] The present invention is not limited to a method of clustering range-Doppler point cloud clusters in the angle dimension, and conventional clustering methods such as DBSCAN and OPTICS may also be employed.

[0080] In an embodiment of the present invention, 103 can determine the tracking object based on two clustering results (distance-Doppler point cloud clusters obtained by performing distance-Doppler clustering processing on radar point clouds, and secondary clustered point cloud clusters obtained by performing secondary clustering on each distance-Doppler point cloud cluster), where, according to different secondary clustering methods, the secondary clustered point cloud clusters are either spatial point cloud clusters or azimuth point cloud clusters.

[0081] In some embodiments, if the number of secondary clustered point cloud clusters corresponding to the distance-Doppler point cloud cluster is greater than 1, the distance-Doppler point cloud cluster is the tracking object; if the number of secondary clustered point cloud clusters corresponding to the distance-Doppler point cloud cluster is not greater than 1, the distance-Doppler point cloud cluster is the tracking object.

[0082] FIG. 10 is a diagram illustrating an example of determining a tracking object. As shown in FIG. 10, the method includes the following steps:

[0083] 1001: Input a distance-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster, where C represents one distance-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster is {S i ,0≦i≦n s}; 1002: Number of secondary clustering point cloud clusters n sDetermine if is greater than 1, if yes, execute 1004, if not, execute 1003; 1003: Determine that the distance-Doppler point cloud cluster C is the tracked object; 1004: Determine the secondary clustered point cloud cluster as the tracked object.

[0084] Although only the operations or processes related to the present invention have been described above, the present invention is not limited thereto, and the method may further include other operations or processes, and reference can be made to the related art for the specific content of these operations or processes.

[0085] According to the method of the embodiment of the present invention, the tracking accuracy is improved and the effective range of tracking is expanded by using a two-step clustering strategy, which solves the problem that the accuracy of radar spatial measurement is poor at long distances, the point cloud is easily dispersed, and clustering cannot be performed.

[0086] <Example of the second aspect> In the embodiment of the present invention, a noise removal method is provided, which is similar to the noise removal method of the embodiment of the first aspect of the present invention shown in Fig. 3, and therefore a redundant description of the same content will be omitted.

[0087] FIG. 11 is a diagram illustrating an example of a noise removal method in an embodiment of the present invention. As shown in FIG. 11, the method includes the following steps:

[0088] 1101: Performing statistics on point cloud noise information on the distance-Doppler plane, the point cloud noise information is noise statistics total number n n , and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Includes; 1102: Analyzing the point cloud clusters on the distance-Doppler plane based on the point cloud noise information to determine whether the point cloud clusters are point cloud clusters caused by noise; 1103: If the point cloud cluster is a noisy point cloud cluster, remove the noisy point cloud cluster in the range-Doppler plane.

[0089] In some embodiments, in 1102, a probability P(C) of each range-Doppler point cloud cluster C being noise is obtained based on the point cloud noise information, and the probability P(C) of each point cloud cluster C being noise is greater than a third threshold T n If it is greater than , the point cloud cluster C is considered to be a noise point cloud cluster.

[0090] In the above embodiment, the probability P(C) of each point cloud cluster C being noise is the average probability of each point in the point cloud cluster C being noise, and the probability of each point in the point cloud cluster C being noise is the number n of times a noise point appears at each position on the range-Doppler plane. r,v and the total number of noise statistics n n It is a ratio of.

[0091] In an embodiment of the present invention, as shown in FIG. 11, the method further includes the following steps:

[0092] 1104: Update point cloud noise information in the range-Doppler plane, which includes adding 1 to the noise statistics total count and adding 1 to the count of noise occurrences at positions in the range-Doppler plane corresponding to all points belonging to the range-Doppler noise point cloud cluster and all points in the non-cluster point cloud.

[0093] For a specific update method, please refer to the description of FIG. 4 in the embodiment of the first aspect.

[0094] Although only the operations or processes related to the present invention have been described above, the present invention is not limited thereto, and the method may further include other operations or processes, and reference can be made to the related art for the specific content of these operations or processes.

[0095] According to the method of the embodiment of the present invention, based on the point cloud noise information on the range-Doppler plane, it is determined whether the point cloud clusters on the range-Doppler plane are point cloud clusters caused by noise, and the point cloud clusters caused by noise are removed, thereby further improving the tracking accuracy.

[0096] <Example of the third aspect> In the embodiment of the present invention, a radar tracking device is provided, and the radar tracking device corresponds to the radar tracking method of the first aspect of the embodiment, so that the overlapping description of the same content will be omitted.

[0097] 12 is a diagram showing an example of a radar tracking device according to an embodiment of the present invention. As shown in FIG. 12, a radar tracking device 1200 according to an embodiment of the present invention includes:

[0098] A first clustering unit 1201: performs clustering on the point cloud acquired by radar detection in the range-Doppler plane to obtain a range-Doppler point cloud cluster; A second clustering unit 1202: performs secondary clustering on the range-Doppler point cloud cluster in a spatial dimension or an angular dimension to obtain a secondary clustered point cloud cluster; A determining unit 1203: determines a tracking object based on the range-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster.

[0099] In some embodiments, the first clustering unit 1201 maps the point cloud onto a distance-Doppler plane, and divides the point cloud into a plurality of point cloud clusters and non-clustered point clouds based on the distance of the point clouds in the distance-Doppler plane, and the number of points in each point cloud cluster is equal to or exceeds a first threshold T n1 and the distance from each point in each point cloud cluster to the point cloud cluster is greater than a second threshold T d1 Specific clustering methods include, but are not limited to, DBSCAN, OPTICS, etc.

[0100] In the above embodiment, the distance from each point in each point cloud cluster to that point cloud cluster is the minimum of the distances from that point to all other points in that point cloud cluster.

[0101] In the above embodiment, the distance between two points in a point cloud cluster is a weighted sum of the absolute value of the difference in distance frequency points of the two points and the absolute value of the difference in Doppler velocity frequency points of the two points.

[0102] For example, the distance between points in a point cloud cluster can be calculated using the following formula:

[0103] d(o j ,o k )=a|r j -r k |+(1-a)|v j -v k | Among them, r j and r k are the points o in the point cloud cluster C, respectively. j and point o k is the distance frequency point of v j and v k are the points o in the point cloud cluster C, respectively. j and point o k is the Doppler velocity frequency point, and a is a predetermined weight value between 0 and 1.

[0104] In an embodiment of the present invention, optionally, as shown in FIG. 12, the apparatus 1200 further includes:

[0105] Noise removal unit 1204: removes point cloud clusters due to noise in the range-Doppler point cloud clusters.

[0106] In some embodiments, the noise removal unit 1204 performs statistics on the point cloud noise information in the range-Doppler plane, and the point cloud noise information is a noise statistic total number n n, and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Analyzing the distance-Doppler point cloud cluster based on the point cloud noise information, determining whether the distance-Doppler point cloud cluster is a point cloud cluster caused by noise, and if the distance-Doppler point cloud cluster is a point cloud cluster caused by noise, removing the point cloud cluster caused by noise in the distance-Doppler plane.

[0107] In some embodiments, the noise removal unit 1204 obtains a probability P(C) that each range-Doppler point cloud cluster C is noise based on the point cloud noise information, and the probability P(C) that each range-Doppler point cloud cluster C is noise is greater than or equal to a third threshold T n If it is greater than , the distance-Doppler point cloud cluster C is considered to be a noise point cloud cluster.

[0108] In some embodiments, the probability P(C) of each of the range-Doppler point cloud clusters C being noise is the average probability of each point in the range-Doppler point cloud cluster C being noise, and the probability of each point in the range-Doppler point cloud cluster C being noise is the number n of times a noise point appears at each position in the range-Doppler plane. r,v and the total number of noise statistics n n It is a ratio of.

[0109] In some embodiments, the noise removal unit 1204 may further update the point cloud noise information in the range-Doppler plane, by adding 1 to the noise statistics total count and adding 1 to the counts of noise occurrence at range-Doppler plane positions corresponding to all points belonging to the range-Doppler noise point cloud cluster and all points in the non-cluster point cloud.

[0110] In some embodiments, the second clustering unit 1202 performs secondary clustering on the range-Doppler point cloud clusters in the spatial dimension by determining whether the range frequency points in each range-Doppler point cloud cluster meet a fourth threshold T rThen, spatial position correction is performed for all points larger than , and spatial position clustering is performed for all points in each range-Doppler point cloud cluster based on the corrected spatial positions, to obtain spatial point cloud clusters and / or unclustered point clouds as the secondary clustered point cloud clusters corresponding to each range-Doppler point cloud cluster. Specific clustering methods include, but are not limited to, DBSCAN, OPTICS, etc.

[0111] In the above embodiment, the spatial location correction is performed when the distance frequency point exceeds a fourth threshold T r for each point greater than , keeping the value of its spatial coordinate x unchanged, setting the value of its spatial coordinate z to a predetermined value, and recalculating the value of its spatial coordinate y;

number

[0112] Among them, (x i ,y i ,z i ) are the original spatial coordinates of the point, and (x i ',y i ',z i ') is the updated spatial coordinate of the point, and z p is the predetermined value, which is the average height of the moving object relative to the radar.

[0113] In some embodiments, the spatial location correction is performed when the distance frequency points exceed a fourth threshold T r For each point greater than , the y-value and z-value of that spatial coordinate are set to predetermined values, and the x-value of that spatial coordinate is recalculated;

number

[0114] Among them, (x i ,y i ,z i ) are the original spatial coordinates of the point, and (x i ',yi ',z i ') is the updated spatial coordinate of the point, and y p and z p is a predetermined value, and y p is the average value of the Y axis relative to the radar centerline in the surveillance scene, and z p is the average height of the moving object relative to the radar.

[0115] In some embodiments, the number of points in each spatial point cloud cluster exceeds a fifth threshold T n2 and the distance from each point in each spatial point cloud cluster to the spatial point cloud cluster is greater than a sixth threshold T d2 is smaller than.

[0116] In some embodiments, the distance from each point in each spatial point cloud cluster to the spatial point cloud cluster is the minimum of the distances from the point to all other points in the spatial point cloud cluster.

[0117] In the above embodiment, the distance between two points in a spatial point cloud cluster is the Euclidean distance of the spatial coordinates of the two points.

[0118] In some embodiments, the second clustering unit 1202 performs secondary clustering on the range-Doppler point cloud clusters in the angle dimension by performing azimuth clustering on all points in each range-Doppler point cloud cluster based on the azimuth angle information of all points, and obtains an azimuth point cloud cluster and / or an unclustered point cloud as the secondary clustered point cloud cluster for each range-Doppler point cloud cluster. Specific clustering methods include, but are not limited to, DBSCAN, OPTICS, etc.

[0119] In some embodiments, the number of points in each oriented point cloud cluster exceeds a seventh threshold T n3 and the distance from each point in each oriented point cloud cluster to the oriented point cloud cluster is greater than an eighth threshold T d3 is smaller than.

[0120] In some embodiments, the distance from each point in each oriented point cloud cluster to that point cloud cluster is the minimum of the distances from that point to all other points in that oriented point cloud cluster.

[0121] In the above embodiment, the distance between two points in an orientation point cloud cluster is a weighted sum of the absolute value of the difference between the horizontal angular frequency points of the two points and the absolute value of the difference between the vertical angular frequency points of the two points.

[0122] For example, the distance between points in an oriented point cloud cluster can be calculated using the following formula:

[0123] d(o j ,o m )=b|α j -α m |+(1-b)|β j -β m | Among them, α j and β j is a point in the oriented point cloud cluster j are the horizontal and vertical angular frequency points of α m and β m is a point in the oriented point cloud cluster m are the horizontal and vertical angular frequency points, and b is a predetermined weight value between 0 and 1.

[0124] In some embodiments, if the number of secondary clustered point cloud clusters corresponding to the distance-Doppler point cloud cluster is greater than 1, the determining unit 1203 determines the secondary clustered point cloud cluster as a tracking object; if the number of secondary clustered point cloud clusters corresponding to the distance-Doppler point cloud cluster is not greater than 1, the determining unit 1203 determines the distance-Doppler point cloud cluster as a tracking object.

[0125] Although only the components or modules related to the present invention have been described, the present invention is not limited thereto, and the radar tracking device 1200 may further include other components or modules, and the specific contents of these components or modules can be found in the related art.

[0126] According to an embodiment of the present invention, the tracking accuracy is improved and the effective range of tracking is extended by using a two-step clustering strategy, thereby solving the problem that the accuracy of radar spatial measurement is poor at long distances, the point cloud is easily dispersed, and clustering cannot be performed.

[0127] <Example of the fourth aspect> An embodiment of the present invention provides a noise removal device, which corresponds to the noise removal method of the second aspect of the embodiment, and redundant description of the same content will be omitted.

[0128] 13 is a diagram showing an example of a noise removal device according to an embodiment of the present invention. As shown in FIG. 13, a noise removal device 1300 according to an embodiment of the present invention includes:

[0129] A statistical unit 1301 performs statistics on point cloud noise information in the distance-Doppler plane, and the point cloud noise information is calculated by dividing the total number of noise statistics n n , and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Includes; An analysis unit 1302: analyzes the point cloud clusters in the range-Doppler plane according to the point cloud noise information, and determines whether the range-Doppler point cloud clusters are point cloud clusters caused by noise; Processing unit 1303: If the range-Doppler point cloud cluster is a noisy point cloud cluster, processing unit 1303 removes the noisy point cloud cluster in the range-Doppler plane.

[0130] In some embodiments, the analysis unit 1302 obtains a probability P(C) that each range-Doppler point cloud cluster C is noise based on the point cloud noise information, and the probability P(C) that each range-Doppler point cloud cluster C is noise exceeds a third threshold T n If it is greater than , the distance-Doppler point cloud cluster C is considered to be a noise point cloud cluster.

[0131] In some embodiments, the probability P(C) of each of the range-Doppler point cloud clusters C being noise is the average probability of each point in the range-Doppler point cloud cluster C being noise, and the probability of each point in the range-Doppler point cloud cluster C being noise is the number n of times a noise point appears at each position in the range-Doppler plane. r,v and the total number of noise statistics n n It is a ratio of.

[0132] In some embodiments, as shown in FIG. 13, the device 1300 further includes:

[0133] An update unit 1304: updates the point cloud noise information in the distance-Doppler plane, which adds 1 to the noise statistics total number of times, and adds 1 to the number of times noise appears at positions in the distance-Doppler plane corresponding to all points belonging to the distance-Doppler noise point cloud cluster and all points in the non-cluster point cloud.

[0134] Although only the components or modules related to the present invention have been described above, the present invention is not limited thereto. The noise removal device 1300 may further include other components or modules, and reference can be made to the related art for specific details of these components or modules.

[0135] According to an embodiment of the present invention, based on the point cloud noise information on the distance-Doppler plane, it is determined whether the point cloud clusters on the distance-Doppler plane are point cloud clusters caused by noise, and the point cloud clusters caused by noise are removed, thereby further improving the tracking accuracy.

[0136] <Example of the fifth aspect> In an embodiment of the present invention, a computing device is provided, and the computing device may be, for example, a computer, a server, a workstation, a desktop computer, a smartphone, etc., but the embodiment of the present invention is not limited thereto.

[0137] 14 is a diagram showing a computer device according to an embodiment of the present invention. As shown in FIG. 14, the computer device 1400 includes at least one interface (not shown), a processor (e.g., a central processing unit (CPU)) 1401, and a memory 1402, the memory 1402 being connected to the processor 1401. The memory 1402 can store various data, and can also store a program 1403, and execute the program 1403 under the control of the processor 1401 to store various data, such as predetermined thresholds, predetermined conditions, etc.

[0138] In some embodiments, the functionality of the radar tracking device 1200 described in the embodiments of the third aspect may be integrated into a processor 1401 to implement the radar tracking method described in the embodiments of the first aspect. For example, the processor 1401 may be configured to perform the following processes: Perform clustering on the point cloud obtained by radar detection in the range-Doppler plane to obtain range-Doppler point cloud clusters; performing secondary clustering on the range-Doppler point cloud clusters in a spatial dimension or an angular dimension to obtain secondary clustered point cloud clusters; A tracked object is determined based on the range-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster.

[0139] In some embodiments, the functionality of the denoising device 1300 of the embodiments of the fourth aspect can be integrated into a processor 1401 to implement the denoising method described in the embodiments of the second aspect. For example, the processor 1401 may be configured to perform the following processes: Statistics are performed on point cloud noise information in the distance-Doppler plane, and the point cloud noise information is the noise statistics total number n n , and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Includes; Analyzing the point cloud clusters on the range-Doppler plane based on the point cloud noise information to determine whether the range-Doppler point cloud clusters are point cloud clusters caused by noise; If the range-Doppler point cloud cluster is a point cloud cluster due to noise, the point cloud cluster due to noise in the range-Doppler plane is removed.

[0140] In some embodiments, the radar tracking device 1200 described in the embodiments of the third aspect or the noise reduction device 1300 described in the embodiments of the fourth aspect may be arranged separately from the processor 1401, for example, the radar tracking device 1200 or the noise reduction device 1300 may be configured as a chip connected to the processor 1401, and the functions of the radar tracking device 1200 or the noise reduction device 1300 may be realized under the control of the processor 1401.

[0141] It should be noted that the computer device 1400 may further include a display 1405 and an I / O device 1404, or may not necessarily include all of the components in FIG. 14, for example, it may further include a camera head and / or radar (not shown) for obtaining images or radar point clouds, or the computer device 1400 may further include components not shown in FIG. 14, for which reference may be made to the prior art.

[0142] In an embodiment of the present invention, the processor 1401 may be referred to as a controller or operational control and may include a microprocessor or other processing and / or logic device, and the processor 1401 can receive inputs and control the operation of each component of the computing device 1400.

[0143] In an embodiment of the present invention, the storage device 1402 may include one or more of a buffer, flash memory, HDD, removable medium, volatile storage, non-volatile storage, or other suitable devices, and may store various types of information and may further store programs for information processing. The processor 1401 may also execute the programs stored in the storage device 1402 to store, process, and otherwise process information. Since the functions of the other components are similar to those of the conventional components, detailed descriptions thereof will be omitted here. Each component of the computer device 1400 may be implemented by dedicated hardware, firmware, software, or a combination thereof, all of which are within the scope of the present invention.

[0144] An embodiment of the present invention further provides a computer readable program, which, when executed in a computing device, causes the computing device to perform a method according to the first or second aspect of the embodiment.

[0145] An embodiment of the present invention further provides a storage medium storing a computer readable program, wherein the computer readable program executes the method according to the first or second aspect of the embodiment in a computer device.

[0146] The above-described apparatus and method of the present invention may be realized by hardware or a combination of hardware and software. The present invention also relates to a computer-readable program that, when executed by a logic component, causes the logic component to realize the above-described apparatus or component, or to perform the above-described various methods or steps. The present invention also relates to a storage medium capable of storing such a program, such as a hard disk, magnetic disk, optical disk, DVD, flash memory, etc.

[0147] The object of the present invention may also be realized in the following manner: a storage medium storing the above-mentioned executable program code is provided directly or indirectly to a system or device, and a computer or central processing unit (CPU) in the system or device reads and executes the above-mentioned program code. In this case, as long as the system or device has the function of executing a program, the embodiment of the present invention is not limited to a program, and the program may be in any form, such as an object-oriented program, a program executed by an interpreter, or a script program provided to an operating system.

[0148] These machine-readable storage media may include, but are not limited to, various types of memory and storage units, semiconductor devices, optical, magnetic, magnetic disks such as magneto-optical disks, and other media suitable for storing information.

[0149] In addition, a computer can also connect to a corresponding website on the Internet, download and install the computer program code according to the present invention into the computer, and then run the program to realize the technical solution of the present invention.

[0150] The present invention also provides a program product including machine-readable instruction codes, which, when read and executed by a machine, can perform the methods of the above-described embodiments of the present invention. Accordingly, various storage media for carrying such program products, such as magnetic disks (including floppy disks (registered trademark)), optical disks (including CD-ROMs and DVDs), magneto-optical disks (including MDs (registered trademark)), and semiconductor storage devices, are also included in the present invention.

[0151] The storage medium may include, for example, a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory device, etc., but is not limited to these.

[0152] Furthermore, each operation (process) in the above-described method can also be realized in the form of a computer-executable program stored in various machine-readable storage media.

[0153] Furthermore, the above-mentioned embodiments are further disclosed as supplementary notes as follows.

[0154] (Appendix 1) 1. A radar tracking method comprising: S1: Perform clustering on the point cloud acquired by radar detection in the range-Doppler plane to obtain range-Doppler point cloud clusters; S3: Perform secondary clustering on the range-Doppler point cloud cluster in a spatial dimension or an angular dimension to obtain a secondary clustered point cloud cluster; and S4: determining a tracked object based on the range-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster.

[0155] (Appendix 2) 2. The method of claim 1, comprising: S1 is S11: Mapping the point cloud onto a range-Doppler plane; S12: Divide the point cloud into a plurality of point cloud clusters and non-clustered point clouds based on the distance of the point cloud in the distance-Doppler plane, and the number of points in each point cloud cluster is equal to or smaller than a first threshold T n1 and the distance from each point in each point cloud cluster to the point cloud cluster is greater than a second threshold T d1 Way smaller than.

[0156] (Appendix 3) 10. The method of claim 2, A method wherein the distance from each point in each point cloud cluster to the point cloud cluster is the minimum of the distances from that point to all other points in the point cloud cluster.

[0157] (Appendix 4) 4. The method of claim 3, The method, wherein the distance between two points in a point cloud cluster is a weighted sum of the absolute value of the difference in distance frequency points of the two points and the absolute value of the difference in Doppler velocity frequency points of the two points.

[0158] (Appendix 5) 5. The method of claim 4, The distance between points in a point cloud cluster is d(o j ,o k )=a|r j -r k |+(1-a)|v j -v k | is calculated based on Among them, r j and r k are the points o in the point cloud cluster C, respectively. j and point o k is the distance frequency point of v j and v k are the points o in the point cloud cluster C, respectively. j and point o k is the Doppler velocity frequency point, and a is a predetermined weight value between 0 and 1.

[0159] (Appendix 6) The method of claim 1, further comprising: S2: Removing noisy point cloud clusters within the range-Doppler point cloud clusters.

[0160] (Appendix 7) 7. The method of claim 6, S2 is S21: Perform statistics on point cloud noise information on the distance-Doppler plane, and the point cloud noise information is counted by a total number of noise statistics n n , and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Includes; S22: Analyzing the range-Doppler point cloud cluster based on the point cloud noise information, and determining whether the range-Doppler point cloud cluster is a point cloud cluster caused by noise; and S23: If the range-Doppler point cloud cluster is a noisy point cloud cluster, removing the noisy point cloud cluster in the range-Doppler plane.

[0161] (Appendix 8) 8. The method of claim 7, In S22, Based on the point cloud noise information, determine a probability P(C) that each range-Doppler point cloud cluster C is noise; and The probability P(C) that the distance-Doppler point cloud cluster C is noise is set to a third threshold T n If C is greater than C, the distance-Doppler point cloud cluster C is considered to be a noise-induced point cloud cluster.

[0162] (Appendix 9) 9. The method of claim 8, The probability P(C) that each of the range-Doppler point cloud clusters C is noise is the average probability that each point in the range-Doppler point cloud cluster C is noise, The probability that each point in the range-Doppler point cloud cluster C is noise is calculated by the number of times n noise points appear at each position in the range-Doppler plane.r,v and the total number of noise statistics n n A method that is a ratio of

[0163] (Appendix 10) 8. The method of claim 7, S2 further S24: Updating point cloud noise information in the range-Doppler plane Including, S24 is adding 1 to the noise statistics count; and The method includes adding 1 to the number of noise occurrences at distance-Doppler plane locations corresponding to all points in the distance-Doppler noise point cloud cluster and all points in the non-cluster point cloud.

[0164] (Appendix 11) 2. The method of claim 1, comprising: In S3, performing secondary clustering on the range-Doppler point cloud clusters in the spatial dimension is S31: In each distance-Doppler point cloud cluster, the distance frequency points exceed the fourth threshold T r Perform spatial position correction for all points greater than S32: performing spatial position clustering on all points in each range-Doppler point cloud cluster based on the corrected spatial positions, and obtaining a spatial point cloud cluster and / or an unclustered point cloud corresponding to each range-Doppler point cloud cluster as the secondary clustered point cloud cluster.

[0165] (Appendix 12) 12. The method of claim 11, In S31, the distance frequency point is equal to or exceeds the fourth threshold T r for each point greater than , keeping the value of its spatial coordinate x unchanged, setting the value of its spatial coordinate z to a predetermined value, and recalculating the value of its spatial coordinate y;

number

[0166] (Appendix 13) 12. The method of claim 11, In S31, the distance frequency point is equal to or exceeds the fourth threshold T r For each point greater than , the y-value and z-value of that spatial coordinate are set to predetermined values, and the x-value of that spatial coordinate is recalculated;

number

[0167] (Appendix 14) 12. The method of claim 11, In S32, the number of points in each spatial point cloud cluster is determined by a fifth threshold T n2 and the distance from each point in each spatial point cloud cluster to the spatial point cloud cluster is greater than a sixth threshold T d2 Way smaller than.

[0168] (Appendix 15) 15. The method of claim 14, A method wherein the distance from each point in each spatial point cloud cluster to the spatial point cloud cluster is the minimum of the distances from the point to all other points in the spatial point cloud cluster.

[0169] (Appendix 16) 16. The method of claim 15, The method, wherein the distance between two points in a spatial point cloud cluster is the Euclidean distance of the spatial coordinates of the two points.

[0170] (Appendix 17) 2. The method of claim 1, comprising: In S3, performing secondary clustering on the range-Doppler point cloud clusters in the angle dimension is S31': For all points in each range-Doppler point cloud cluster, perform azimuth clustering based on azimuth angle information of all the points, and obtain an azimuth point cloud cluster and / or an unclustered point cloud corresponding to each range-Doppler point cloud cluster as the secondary clustered point cloud cluster.

[0171] (Appendix 18) 18. The method of claim 17, The number of points in each oriented point cloud cluster is determined by the seventh threshold T n3 and the distance from each point in each oriented point cloud cluster to the oriented point cloud cluster is greater than an eighth threshold T d3 Way smaller than.

[0172] (Appendix 19) 19. The method of claim 18, A method wherein the distance from each point in each oriented point cloud cluster to that point cloud cluster is the minimum of the distances from that point to all other points in that oriented point cloud cluster.

[0173] (Appendix 20) 19. The method of claim 18, The method, wherein the distance between two points in an orientation point cloud cluster is a weighted sum of the absolute value of the difference in horizontal angular frequency points of the two points and the absolute value of the difference in vertical angular frequency points of the two points.

[0174] (Appendix 21) 21. The method of claim 20, The distance between points in an oriented point cloud cluster is d(o j ,o m )=b|α j -α m |+(1-b)|β j -β m | is calculated based on Among them, α j and β j is a point in the oriented point cloud cluster j are the horizontal and vertical angular frequency points of α m and β m is a point in the oriented point cloud cluster m are the horizontal angular frequency points and the vertical angular frequency points, and b is a predetermined weight value between 0 and 1.

[0175] (Appendix 22) 2. The method of claim 1, comprising: S4 is If the number of secondary clustered point cloud clusters corresponding to the range-Doppler point cloud cluster is greater than 1, the secondary clustered point cloud cluster is set as a tracking object; and If the number of secondary clustered point cloud clusters corresponding to the range-Doppler point cloud cluster is not greater than 1, the range-Doppler point cloud cluster is selected as the tracking object.

[0176] (Appendix 23) A noise removal method, comprising: S21: Perform statistics on point cloud noise information on the distance-Doppler plane, and the point cloud noise information is counted by a total number of noise statistics n n, and the number of times the noise point appears at each position in the range-Doppler plane, n r,v Includes; S22: Analyzing the point cloud clusters on the range-Doppler plane based on the point cloud noise information to determine whether the range-Doppler point cloud clusters are noise-induced point cloud clusters; and S23: If the range-Doppler point cloud cluster is a noisy point cloud cluster, removing the noisy point cloud cluster in the range-Doppler plane.

[0177] (Appendix 24) 24. The method of claim 23, In S22, According to the point cloud noise information, obtain a probability P(C) that each range-Doppler point cloud cluster C is noise; The probability P(C) that the distance-Doppler point cloud cluster C is noise is set to a third threshold T n If C is greater than C, the distance-Doppler point cloud cluster C is considered to be a noise-induced point cloud cluster.

[0178] (Appendix 25) 25. The method of claim 24, The probability P(C) that each of the range-Doppler point cloud clusters C is noise is the average probability that each point in the range-Doppler point cloud cluster C is noise; The probability that each point in the range-Doppler point cloud cluster C is noise is calculated by the number of times n noise points appear at each position in the range-Doppler plane. r,v and the total number of noise statistics n n A method that is a ratio of

[0179] (Appendix 26) 24. The method of claim 23, further comprising: S24: Updating point cloud noise information in the range-Doppler plane Including, S24 is adding 1 to the noise statistics count; and The method includes adding 1 to the noise application count at distance-Doppler plane locations corresponding to all points in the distance-Doppler noise point cloud cluster and all points in the non-cluster point cloud.

[0180] (Appendix 27) A computing device including a memory and a processor, 27. A computing device, the storage device storing a computer program, the processor configured to execute the computer program to perform the method of any one of claims 1 to 26.

[0181] (Appendix 28) A storage medium storing a computer-readable program, A storage medium, the computer readable program causing a computer to execute the method according to any one of appendices 1 to 26 in a computing device.

[0182] Although the preferred embodiment of the present invention has been described above, the present invention is not limited to this embodiment, and any modification to the present invention falls within the technical scope of the present invention as long as it does not depart from the spirit of the present invention.

Claims

1. 1. A radar tracking device, comprising: a first clustering unit that performs clustering on the point cloud obtained by radar detection in the range-Doppler plane to obtain range-Doppler point cloud clusters; a second clustering unit for performing secondary clustering on the range-Doppler point cloud clusters in a spatial dimension to obtain secondary clustered point cloud clusters; and a determining unit for determining a tracking object based on the range-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster; The second clustering unit performs secondary clustering on the range-Doppler point cloud clusters in the spatial dimension, Performing spatial location correction for all points in each range-Doppler point cloud cluster whose range-frequency points are greater than a fourth threshold; and performing spatial location clustering on all points in each range-Doppler point cloud cluster based on the corrected spatial locations, and obtaining a spatial point cloud cluster and / or an unclustered point cloud corresponding to each range-Doppler point cloud cluster as the secondary clustered point cloud cluster; The unclustered point cloud refers to a point cloud that is not a cluster.

2. 2. The radar tracking device of claim 1, the first clustering unit maps the point cloud onto a range-Doppler plane, and divides the point cloud into a plurality of point cloud clusters and unclustered point clouds based on the distances of the point clouds on the range-Doppler plane, wherein the number of points in each point cloud cluster is greater than a first threshold, and the distance from each point in each point cloud cluster to the point cloud cluster is less than a second threshold.

3. 2. The radar tracking device of claim 1, The radar tracking device further includes a denoising unit for removing point cloud clusters due to noise in the range-Doppler point cloud clusters.

4. 2. The radar tracking device of claim 1, If the number of secondary clustered point cloud clusters corresponding to the distance-Doppler point cloud cluster is greater than 1, the determining unit determines the secondary clustered point cloud cluster as a tracking object; If the number of secondary clustered point cloud clusters corresponding to the range-Doppler point cloud cluster is not greater than 1, the determination unit determines the range-Doppler point cloud cluster as a tracking object.

5. On the computer, Perform clustering on the point cloud obtained by radar detection in the range-Doppler plane to obtain range-Doppler point cloud clusters; performing secondary clustering on the range-Doppler point cloud clusters in a spatial dimension to obtain secondary clustered point cloud clusters; and determining a tracked object based on the range-Doppler point cloud cluster and its corresponding secondary clustered point cloud cluster; A program for executing a radar tracking method including: performing a second-order clustering on the range-Doppler point cloud clusters in the spatial dimension, Performing spatial location correction for all points in each range-Doppler point cloud cluster whose range-frequency points are greater than a fourth threshold; and performing spatial location clustering on all points in each range-Doppler point cloud cluster based on the corrected spatial locations, and obtaining a spatial point cloud cluster and / or an unclustered point cloud corresponding to each range-Doppler point cloud cluster as the secondary clustered point cloud cluster; The unclustered point cloud refers to a point cloud that is not a cluster.

Images