A dynamic vehicle real-time detection method and device based on a roadside laser radar

Abstract

The application discloses a kind of dynamic vehicle real-time detection method and device based on roadside laser radar, specific method includes static point filtering and adaptive threshold outlier filtering in the matrix with spherical coordinate attribute in combination with different space-time point cloud data, cluster segmentation target point cloud data in space rectangular coordinate system, and vehicle target is identified according to point cloud quantity characteristics and range characteristics.Dimensional reduction is in plane, according to the characteristics of vehicle L shape, I shape determines corner point and initial main direction, in combination with initial main direction, to area criterion and the distance criterion of contour point mathematical model of design bounding box is constructed, and the optimal bounding box is iteratively found.Finally, line buffer area of plane bounding box is created, whether mixed noise is verified to contain.This application effectively reduces noise interference, relieves the influence of appearance change on vehicle identification, by calculating adaptive filtering threshold and optimal solution model, make algorithm more flexible and general, improve the accuracy of real-time detection vehicle.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and in particular to a method and device for real-time detection of dynamic vehicles based on roadside laser radar. Background Art

[0002] Real-time detection of road vehicles has significant application value in intelligent traffic management, helping to measure traffic flow, ensure road construction safety, monitor traffic violations, and support autonomous vehicle testing. At the same time, complex road environments and massive amounts of data place higher demands on technical solutions, requiring operational flexibility, high detection accuracy, real-time dynamic detection capabilities, and efficient data transmission. Among existing technologies, lidar has been widely used in the intelligent transportation sector due to its ability to acquire high-precision three-dimensional spatial information, excellent depth perception, and strong anti-interference properties.

[0003] LiDAR-based target detection methods include OBB bounding box method, convex hull fitting, deep learning, etc. However, these methods still have some challenges, such as high computational complexity, severe information loss, and noise sensitivity. Currently, in the scenario of real-time roadside detection of dynamic vehicles, there is still a lack of a technical solution that can efficiently obtain target geometric features, provide timely feedback on abnormal information, and is suitable for real-time detection. Summary of the Invention

[0004] The purpose of the present invention is to overcome the shortcomings of the existing technology. In response to the shortcomings of the existing technology, a method and device for real-time detection of dynamic vehicles based on roadside laser radar are provided.

[0005] In order to achieve the above objectives, the technical solution of the present invention is as follows: In the first aspect, a method for real-time detection of dynamic vehicles based on roadside laser radar is provided, the method comprising the following steps:

[0006] Step 1: Obtain 3D point cloud data of the real-time road conditions;

[0007] Step 2: Perform stationary point filtering and outlier filtering on the 3D point cloud data;

[0008] Step 3: Cluster the filtered 3D point cloud data to obtain single target point cloud data, and determine whether it is a dynamic vehicle, and finally obtain vehicle point cloud data;

[0009] Step 4: Calculate the corner points of the vehicle point cloud data, segment the clusters of the vehicle head based on the corner points, and then fit the initial width main direction of the vehicle;

[0010] Step 5: Calculate the vehicle boundary contour points. Combined with the initial width main direction of the vehicle, minimize the sum of the area weight and distance weight of the bounding box as the objective function. Build a mathematical model of the bounding box. Use the initial width main direction slope of the vehicle as the design variable. Iterate to find the optimal bounding box and filter out mixed noise points.

[0011] Step 6: Based on the optimal bounding box obtained in step 5, calculate the geometric features of the vehicle and output the detection results.

[0012] Furthermore, in step one, three-dimensional point cloud data of the real-time road conditions is obtained by using a laser radar. The laser radar system equipment is arranged outside the motor vehicle road at a distance of L m, wherein the direction of the laser radar is opposite to the direction of vehicle travel, and the center line of the laser radar is parallel to the lane line or facing the lane.

[0013] Furthermore, in step 2, the static point filtering method is to subtract the currently acquired point cloud data S from the point cloud data S1 of the fixed frame interval. 11 The outlier filtering adopts radius filtering based on continuous search, and the threshold of radius filtering has adaptive characteristics, and its calculation formula is:

[0014] T i,j =R i,j ·f·E;

[0015] Where, T i,j ,R i,j are the radius threshold and radial distance of the point in the i-th row and j-th column of the matrix, f is the minimum resolution of the distance analysis expression; E is the correction coefficient for the change in point cloud sparsity, which is experimentally tested using the relative volume fraction indicator based on the radial distance of the vehicle and is set according to the expected value.

[0016] Furthermore, in step 3, the method for determining a dynamic vehicle is to reduce the dimension of the clustered target point cloud data to a two-dimensional plane belonging to the ground, and then calculate the quantity characteristics and range characteristics of the point cloud. If the following formula is satisfied, the target point cloud data is dynamic vehicle data;

[0017]

[0018] Where Q is the number of point clouds, r is the horizontal viewing angle resolution of the lidar, and E is the correction coefficient for the sparsity change of the point cloud. MaxY is the maximum value of the Y coordinate, and MinY is the minimum value of the Y coordinate. The Y coordinate value reflects the lane width, and MaxY MinY reflects the vehicle width range.

[0019] Furthermore, in step 4, the corner point is determined by the minimum radial distance of the point cloud; then, a straight line L is drawn through the origin and the corner point. The straight line L divides the vehicle point cloud data into cluster A and cluster B. Cluster B is the cluster of the front part of the vehicle. The straight line L2 of cluster B after RANSAC fitting represents the initial width main direction of the vehicle, and cluster A is the point cloud of the side of the vehicle.

[0020] Furthermore, in step 5, the mathematical model of the optimal bounding box design is to use the slope of the straight line L2 as the design variable, the sum of the area weight and the distance weight of the bounding box as the objective function, and find the value of the optimal function within a suitable range, which is specifically expressed as follows:

[0021] Min W=w1Area+w2Distance

[0022] Area=a·b

[0023]

[0024]

[0025] Where W is the objective function; Area is the area of ​​the bounding box, which is normalized; a is the width of the bounding box, b is the length of the bounding box; Distance is the sum of the shortest distances from all contour points to the four straight lines of the bounding box, which is normalized; J is the number of contour points; d i is the minimum value of the distance from contour point i to the four straight lines; w1 and w2 are weights respectively; k2 is the initial slope of L2, and k is the search step size.

[0026] Furthermore, in step five, the mixed noise is filtered by creating a line buffer, gradually moving the four straight lines constituting the optimal bounding box closer to the inside of the bounding box, and determining whether mixed noise is contained in the continuously changing line buffer.

[0027] Furthermore, in step six, the geometric features refer to the length, width, height, and skew angle arctan(k2) of the vehicle, and the output result refers to uploading the geometric features of the vehicle to the cloud platform and storing and displaying them.

[0028] In the second aspect, the present invention also provides a dynamic vehicle real-time detection device based on roadside lidar, including a lidar, a memory, a processor, a PC, and a network interface. The memory stores executable code, and is characterized in that when the processor executes the executable code, it implements the dynamic vehicle real-time detection method based on lidar.

[0029] In a third aspect, the invention also provides a computer-readable storage medium on which a program is stored, characterized in that when the program is executed by a processor, the method of real-time detection of dynamic vehicles based on roadside lidar is implemented.

[0030] Beneficial effects of the present invention:

[0031] This method effectively reduces noise interference through stationary point filtering, outlier filtering, and a hybrid point filtering method based on buffer path search. Leveraging the L- and I-shaped nature of vehicle point clouds, the front of the vehicle is used as the initial principal direction for fitting, effectively mitigating the impact of appearance changes on vehicle recognition and improving the algorithm's efficiency and robustness. By calculating adaptive filtering thresholds and optimal solution models, the algorithm becomes more flexible and versatile, enhancing the accuracy of real-time vehicle detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] To more clearly illustrate the technical solutions in the embodiments of this application, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0033] Figure 1 This is a schematic block diagram of the process structure of an embodiment of the present invention.

[0034] Figure 2 This is a schematic diagram of the layout of the laser radar detection system according to an embodiment of the present invention.

[0035] Figure 3 Schematic diagram of the initial main direction of a vehicle according to an embodiment of the present invention.

[0036] Figure 4 Schematic diagram of a line buffer according to an embodiment of the present invention

[0037] Figure 5 This is a diagram showing the vehicle detection effect of an embodiment of the present invention.

[0038] Figure 6 This is a structural diagram of a dynamic vehicle real-time detection device based on laser radar in the present invention DETAILED DESCRIPTION

[0039] In order to more clearly illustrate the technical problems, technical solutions and beneficial effects to be solved by this application, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0040] The following is a further detailed description through specific implementation methods:

[0041] Example

[0042] This embodiment provides a method and device for real-time detection of dynamic vehicles based on roadside laser radar. Figure 1 As shown, the following steps are included:

[0043] Step 1: Obtain 3D point cloud data of the real-time road conditions. The LiDAR system equipment is placed outside the motor vehicle road, 1m away, with the LiDAR facing in the opposite direction of the vehicle, the center line of the LiDAR parallel to the lane line, and the origin of the coordinate system is the LiDAR position, such as Figure 2 As shown; when acquiring data, in addition to recording the point cloud data at the current moment, the data of the previous 10 frames are retained. The total data can be expressed as: P = [S1, S2, S3......S 11 ], where S 11 For the current frame, each frame of point cloud data is stored in a matrix with spherical coordinate attributes. The dimension of the matrix is ​​300×125. The physical meaning of the number of rows 300 represents the horizontal viewing angle range, and the physical meaning of the number of columns 125 represents the vertical viewing angle range. The matrix stores the radial distance of the point cloud.

[0044] Step 2: The currently acquired point cloud data S 11 Perform stationary point filtering and outlier filtering, and then convert from the spherical coordinate system to the spatial rectangular coordinate system. Stationary points include ground points, green belts, fences, etc. Subtract the currently acquired point cloud data S from the point cloud data S1 11 , if the difference is less than 0.3m, it is assigned a value of 0; the outlier filtering adopts a radius filtering method based on continuous search. For example, in the same level (column) of the matrix S[i,1], (i=1,2,3,......m), the radius threshold of point p1 is defined as T1. If the Euclidean distance from the next point p2 to this point is greater than the radius threshold, then p2 is an interval point. Then, with p2 as the center and the radius threshold as T2, the search and judgment are continued. If three interval points appear continuously, p1, p2, and p3 are filtered as noise points. The threshold is calculated as follows:

[0045] T i,j =R i,j ·f·E;

[0046] Where, T i,j ,R i,jare the radius threshold and radial vector distance of the point in the i-th row and j-th column in the matrix, f is the minimum resolution of the lidar distance analytical formula of 0.01m, E is the correction coefficient for the change of point cloud sparsity, and when the radial distance interval is [5,10], [10,20], [20,30], [30,40], [40,50], [50,60], [60,70], [70,80], the values ​​of E are 1, 2, 3, 4, 5, 5, 5, 5 respectively. When it is within 5m, it is not detected.

[0047] The correction coefficient E is determined by using the relative volume fraction indicator for experimental testing. 200 frames of point cloud data are taken in each radial distance segment, and different E are introduced. The relative volume fractions of the point cloud target after clustering segmentation and the actual target are calculated, and the best expected value of the test data results is taken. The larger the recent expectation, the more appropriate E.

[0048] Step 3: In the spatial rectangular coordinate system, use the DBSCAN density clustering algorithm to cluster and segment the three-dimensional point cloud data, obtain single target point cloud data, and determine whether it is a dynamic vehicle. When clustering, set the DBSCAN field radius to 1 and the minimum number of points within the field radius to 5 to obtain single target point cloud data. The number of target point clouds is 1168. Reduce the dimension to the two-dimensional plane belonging to the ground, calculate the minimum and maximum Y coordinates, and if the following requirements are met, the target point cloud data is dynamic vehicle data;

[0049]

[0050] Where Q is the number of point clouds, r is the horizontal viewing angle resolution of the lidar (0.2°), and E is the correction coefficient for point cloud sparsity changes. MaxY is the maximum Y coordinate value of 5.82, and MinY is the minimum Y coordinate value of 3.98. The Y coordinate value reflects the lane width distance.

[0051] Step 4: Calculate the corner points in the vehicle point cloud data, segment the clusters of the vehicle head based on the corner points, and use the RANSAC random sampling consistency method to fit the initial main direction of the vehicle. The corner points are determined by the minimum distance R value of the points, and the coordinates are (4.59, 10.32); draw a straight line L through the origin and the corner points. The straight line L divides the vehicle point cloud data into clusters A and B. Cluster B is the cluster of the vehicle head. The straight line L2 after RANSAC fitting of cluster B represents the initial width main direction of the vehicle, as shown in the figure. Figure 3 As shown, L2 can be expressed as: y2=0.23x+9.07.

[0052] Step 5: Calculate the vehicle boundary contour points based on the Alpha Shapes method. Combined with the initial main direction of the vehicle, a mathematical model for designing the bounding box is constructed, and the optimal bounding box is iteratively found. The mathematical model for designing the optimal bounding box uses the slope k of the line L2 as the design variable, and the sum of the area weight and distance weight of the bounding box as the objective function. The optimal function value is found within a suitable range and can be expressed as:

[0053] Min W=w1Area+w2Distance

[0054] Area=a·b

[0055]

[0056]

[0057] Where W is the objective function; Area is the area of ​​the bounding box, which is normalized; a is the width of the bounding box, which is obtained by calculating the Euclidean distance between the projection point of the contour point on the line L2 and the projection boundary point; b is the length of the bounding box, which is obtained by calculating the Euclidean distance between the projection point of the contour point on the line L1 and the projection boundary point, and the line L1 is perpendicular to the line L2; Distance is the sum of the shortest distances from all contour points to the four lines of the bounding box, which is normalized; J is the number of contour points; d i The minimum distance between a contour point and the four straight lines; w1 and w2 are 0.4 and 0.6 respectively; the search step of k is 0.02; k2 is the initial slope of L2, 0.23. After calculation, the optimal value of k2 is 0.0429.

[0058] Then, a line buffer of the optimal bounding box is created to filter out mixed noise points close to the vehicle. The line buffer is a geometric area formed by offsetting the four straight lines that make up the optimal bounding box into the bounding box. Taking L3 as an example, the line buffer of L3 is as follows: Figure 4 As shown, the filtering steps are as follows:

[0059] In the first step, L3 is offset inward by 0.05m to form a buffer zone f1 with the original bounding box. The number of points falling in the buffer zone f1 is recorded, including those on the line.

[0060] In the second step, repeat step (1) above, shifting by 0.05 m each time, to form buffer zones f2, f3, etc. with the original bounding box. Buffering stops if the number of points falling within the buffer zone is greater than 10-D / 10. D is the minimum value of the point cloud's X coordinate, 10.26. The X coordinate value reflects the lane length. Therefore, buffering stops when the number of points in the buffer zone exceeds 9.

[0061] Thirdly, if the number of buffering times is greater than 1, the mixed noise points in the buffer area are filtered. If the number of other points contained in the 0.1m radius range of the point in the buffer area is less than 3, and no new point falls into the buffer area when the buffer area is expanded next time, the point is judged as a mixed noise point. After the mixed noise points are identified, the mixed noise points are filtered out.

[0062] Sixthly, the geometric features of the vehicle are calculated according to the optimal bounding box obtained in step five, and the result is output. The geometric features refer to the length, width, height and skew angle of the vehicle. After calculation, the length is 4.3m, the width is 1.90m, the height is 1.58m, and the skew angle is 2.5°. The skew angle is defined as arctan(k2).

[0063] The point cloud targets segmented by each cluster are processed according to steps four to six. At the same time, the effects of the processed multiple vehicle targets are as shown in Figure 5 .

[0064] In order to verify the superiority of the method, experiments based on the OBB bounding box model and the traditional L model are respectively performed on the continuous data sets 1-10, and the method is compared with the method. The data sets are collected from actual road conditions, and each data set contains 150 frames of data from far to near of the same vehicle.

[0065] Table 1 shows the width error under three vehicle feature extraction algorithms. The width error reflects the deviation degree of the calculated width from the actual vehicle width. The error is expressed by the following formula:

[0066] δ=W th(A) -W th(P)

[0067] In the formula, δ is the error, W th(A) is the actual width of the vehicle, and W th(P) is the calculated width.

[0068] Table 1

[0069]

[0070] The application also provides an embodiment of a dynamic vehicle real-time detection device based on a roadside laser radar. The detection device corresponds to the above-mentioned dynamic vehicle real-time detection method based on a laser radar.

[0071] For details Figure 6 , the application provides a dynamic vehicle real-time detection device based on a roadside laser radar, which comprises a laser radar, a storage, a processor, a PC end and a network interface. The storage stores the collected data and executable codes. The processor is used to realize the dynamic vehicle real-time detection method based on a laser radar in the above-mentioned embodiment. The PC end refers to any computer with data processing capability and display.

[0072] The embodiment of the device for detecting dynamic vehicles in real time based on roadside laser radar provided by the application is realized by combining software and hardware, and can transmit operation instructions from a PC end to a processor or directly run internal processor instructions by the processor. The implementation process of each unit and module is specifically described in the corresponding steps of the above-mentioned method for detecting dynamic vehicles in real time based on roadside laser radar, and will not be repeated here.

[0073] The device embodiments described above can determine the spatial positions of each unit according to actual needs. In addition to the hardware such as laser radar, memory, processor, PC end, network interface, etc., any device with data processing capability in the embodiment can also include other hardware according to the actual function of the device with data processing capability, and will not be repeated here. Those skilled in the art can understand and implement it without creative labor.

[0074] The application also provides a computer readable storage medium, which can be non-volatile or volatile. The computer readable storage medium stores a method for detecting dynamic vehicles in real time based on roadside laser radar, which can be executed by a computer. The specific working process of the system can refer to the corresponding steps in the above-mentioned method embodiment. The computer readable storage medium can be used as an internal storage unit of the PC end in the above-mentioned device embodiment, or as an external storage device with data processing capability, which can include a mobile hard disk, an SD card, an optical disc, etc.

[0075] The above description only represents a preferred embodiment of the application, and does not limit the application. Any modification, equivalent replacement and improvement within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. A real-time dynamic vehicle detection method based on roadside laser radar, characterized in that: The method comprises the following steps: Step 1: Obtain 3D point cloud data of the real-time road conditions; Step 2: Perform stationary point filtering and outlier filtering on the 3D point cloud data; Step 3: Cluster the filtered 3D point cloud data to obtain single target point cloud data, and determine whether it is a dynamic vehicle, ultimately obtaining vehicle point cloud data. The specific method is to reduce the dimension of the clustered target point cloud data to the 2D plane of the ground, and then calculate the quantity and range characteristics of the point cloud. If the following equation is satisfied, the target point cloud data is dynamic vehicle data. ， ； Where, is the number of point clouds, is the horizontal viewing angle resolution of the lidar, and E is the correction coefficient for the sparsity change of the point cloud; is the maximum value of the Y coordinate, is the minimum value of the Y coordinate, which reflects the lane width. Reflects the width range of the vehicle; Step 4: Calculate the corner points of the vehicle point cloud data, segment the front part of the vehicle based on the corner points, and then fit the initial width main direction of the vehicle. The corner points are determined by the minimum radial distance of the point cloud. Then, draw a straight line L through the origin and the corner points. The straight line L segments the vehicle point cloud data into cluster A and cluster B. Cluster B is the cluster of the front part of the vehicle. The straight line L2 of cluster B after RANSAC fitting represents the initial width main direction of the vehicle. Cluster A is the point cloud of the vehicle side. Step 5: Calculate the vehicle boundary contour points, combine the initial width main direction of the vehicle, and use the minimum sum of the area weight and distance weight of the bounding box as the objective function to construct a mathematical model of the bounding box. Use the initial width main direction slope of the vehicle as the design variable, iteratively search for the optimal bounding box, and filter out mixed noise points. The mathematical model of the optimal bounding box design refers to using the slope of the straight line L2 as the design variable, the sum of the area weight and distance weight of the bounding box as the objective function, and finding the value of the optimal function within a suitable range. The specific expression is as follows: Where, is the objective function; is the area of ​​the bounding box, normalized; is the width of the bounding box, is the length of the bounding box; It is the sum of the shortest distances from all contour points to the four straight lines of the bounding box. After normalization, J is the number of contour points. The minimum value of the distance from the contour point i to the four straight lines; , are weights respectively; is the initial slope of L2, is the search step length; Step 6: Based on the optimal bounding box obtained in step 5, calculate the geometric features of the vehicle and output the detection results.

2. The method for real-time dynamic vehicle detection based on roadside laser radar according to claim 1, characterized in that: In step 1, three-dimensional point cloud data of the real-time road conditions is obtained by using a laser radar. The laser radar system equipment is arranged outside the motor vehicle road, at a distance of L m, wherein the direction of the laser radar is opposite to the direction of vehicle travel, and the center line of the laser radar is parallel to the lane line or facing the lane.

3. The method for real-time dynamic vehicle detection based on roadside laser radar according to claim 1, characterized in that: In step 2, the static point filtering method is to filter the point cloud data separated by fixed frames. Subtract the currently acquired point cloud data The outlier filtering adopts radius filtering based on continuous search, and the threshold of radius filtering has adaptive characteristics, and its calculation formula is: ； Where, The first OK, The radius threshold and radial distance of the column points, is the minimum resolution of the distance analysis; E is the correction coefficient for the change in point cloud sparsity. The correction coefficient is set according to the expected value based on the relative volume fraction indicator for experimental testing based on the radial distance of the vehicle.

4. The method for real-time dynamic vehicle detection based on roadside laser radar according to claim 1, characterized in that: In step five, the mixed noise is filtered by creating a line buffer, gradually moving the four straight lines that make up the optimal bounding box closer to the inside of the bounding box, and determining whether there are mixed noise points in the continuously changing line buffer.

5. The method for real-time dynamic vehicle detection based on roadside laser radar according to claim 1, characterized in that: In step 6, the geometric features are the length, width, height, and skew angle of the vehicle. The output result refers to uploading the vehicle's geometric features to the cloud platform and storing and displaying them.

6. A dynamic vehicle real-time detection device based on roadside laser radar, comprising a laser radar, a memory, a processor, a PC, and a network interface, wherein the memory stores executable code, characterized in that: When the processor executes the executable code, a dynamic vehicle real-time detection method based on a roadside lidar as described in any one of claims 1 to 5 is implemented.

7. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by the processor, a real-time dynamic vehicle detection method based on a roadside lidar as described in any one of claims 1 to 5 is implemented.

Images