A radar defense area automatic generation method and electronic equipment

Abstract

The application discloses a radar defense area automatic generation method and electronic equipment, comprising the following steps: generating a 2D plane map according to point cloud data, fitting a curve to generate a curve formula of a track group, converting to a 3D space, calculating a point cloud aggregation line through a point cloud set and performing screening to obtain a correct track group curve, generating a center line of each track, intercepting a near end and a far end position of the center line of each track according to a defense area, and extending a left and right extension range of an arbitrary position point of the center line of each track, so that the radar defense area automatic generation is completed. According to the application, the defense area under the scene can be automatically established according to original point cloud data, manual participation is not needed in the calibration process, and the result after calibration is high in accuracy.

Description

Technical Field

[0001] This invention relates to the field of generating orbital radar defense zones, and more specifically to an automatic radar defense zone generation method and electronic equipment. Background Technology

[0002] According to railway standards, a three-dimensional space called the track zone is defined along the railway to ensure that trains traveling within the track zone are not disturbed. Marking the defense zones on the track scanned by lidar, and only detecting and reporting foreign objects intruding within the defense zones, is the foundation for the normal operation of the system. The common practice is to manually set the defense zones using point cloud observation software, combined with on-site measurements and tools. This process requires multiple people and manual adjustments, which is labor-intensive and time-consuming. The results of the adjustments are closely related to the experience and condition of the operators, making it difficult to guarantee the accuracy of the marking. Summary of the Invention

[0003] In view of the above-mentioned shortcomings in the prior art, the present invention provides an automatic radar defense zone generation method and electronic device, which solves the problem that the existing radar defense zone calibration requires manual intervention and is time-consuming and labor-intensive.

[0004] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:

[0005] A method for automatically generating radar defense zones is provided, which includes the following steps:

[0006] S1. Acquire and preprocess radar point cloud data to obtain point cloud data within m meters of the orbit and filter out noise to obtain converted point cloud data.

[0007] S2. Project the converted point cloud data onto the XY plane to generate a 2D planar map;

[0008] S3. Perform mean filtering, edge detection processing, and grayscale conversion on the 2D planar image, and generate the curve formula of the track group by fitting the curve.

[0009] S4. Take any fixed value for the Z value in 3D space to convert the curve formula to 3D space and obtain the trajectory curve in 3D space;

[0010] S5. Collect and perform noise filtering on all point clouds within a range of n meters from the orbit curve in 3D space to obtain a point cloud set;

[0011] S6. Calculate point cloud aggregation lines using point cloud sets, and obtain the spacing and smoothness of each point cloud aggregation line;

[0012] S7. Based on the spacing and smoothness of the point cloud aggregation lines, delete the curves in the point cloud aggregation lines that do not conform to the track characteristics to obtain the correct track group curves.

[0013] S8. Obtain the centerline of each group of tracks;

[0014] S9. Based on the near and far positions of the center line of each group of tracks and the left and right extension range of any position point of the center line of each group of tracks, the radar defense zone is automatically generated.

[0015] Furthermore, the value of parameter m in step S1 is 30.

[0016] Furthermore, the specific method for collecting all point clouds within a range of n meters from the orbital curve in 3D space in step S5 is as follows:

[0017] When the correct track group curve is a straight line, according to the formula:

[0018] d = |x cosθ + y sinθ - r|

[0019] Calculate the distance d of each 3-dimensional point cloud (x, y, z) to the correct orbital curve in the spatial dimension, and obtain the point cloud within 10 cm of the correct orbital curve; where r is the distance from the origin to the line; θ is the difference between 90° and the angle between the line and the opposite direction of the X-axis;

[0020] When the correct orbital group curve is a curve, according to the formula:

[0021] d=|A+sqrt(r 2 -(yB) 2 |

[0022] Calculate the distance d from each 3-dimensional point cloud (x, y, z) to the correct orbital curve in the spatial dimension, and obtain the point cloud within 10 cm of the correct orbital curve; where sqrt represents the square root calculation; (A, B) are the coordinates of the center of the curve.

[0023] Furthermore, the specific method for obtaining the spacing of the point cloud aggregation lines in step S6 is as follows:

[0024] According to the formula:

[0025] Dis = fabs(r1-r2)

[0026] Get the spacing Dis of the point cloud aggregation lines; where fabs(·) represents the absolute value function; when the track curve is a straight line, r1 and r2 are the distances from the origin to the two straight lines, respectively; when the track curve is a concentric circle, r1 and r2 are the radii of the concentric circle, respectively.

[0027] Furthermore, the specific method for obtaining the smoothness of the point cloud aggregation line in step S6 is as follows:

[0028] The standard deviation of each point cloud aggregation line is used as the smoothness of the point cloud aggregation line.

[0029] Furthermore, the specific method for deleting curves that do not conform to the orbital characteristics in the point cloud aggregation lines in step S7 based on the spacing of the point cloud aggregation lines is as follows:

[0030] If the spacing Dis of the point cloud aggregation lines is less than 1.3 meters or greater than 1.5 meters, it is determined to be a curve that does not conform to the orbit characteristics and is deleted.

[0031] Furthermore, the specific method for deleting curves that do not conform to the trajectory characteristics in the point cloud aggregation line based on the smoothness of the point cloud aggregation line in step S7 is as follows:

[0032] If the standard deviation of a single point cloud aggregation line is less than 0.5 feet, and the standard deviation of a single possible orbit group is less than 0.1 feet, then it is judged as a curve that meets the orbit characteristics and is retained; otherwise, it is judged as a curve that does not meet the orbit characteristics and is deleted.

[0033] An electronic device is provided, comprising:

[0034] Memory, which stores executable instructions; and

[0035] The processor is configured to execute executable instructions in the memory to implement the automatic radar zone generation method.

[0036] The beneficial effects of this invention are: this invention can automatically establish the defense zone in the scene based on the original point cloud data, without the need for manual intervention in the calibration process, and the accuracy of the calibration results is very high. Attached Figure Description

[0037] Figure 1 This is a flowchart illustrating the method.

[0038] Figure 2 A schematic diagram illustrating the effect of automatic calibration of straight-line defense zones;

[0039] Figure 3 A schematic diagram illustrating the effect of automatically calibrating the protection zone of a curved turnout;

[0040] Figure 4 This is a schematic diagram of curve fitting when the trajectory is a straight line. Detailed Implementation

[0041] The specific embodiments of the present invention are described below to enable those skilled in the art to understand the present invention. However, it should be understood that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, various changes are obvious as long as they are within the spirit and scope of the present invention as defined and determined by the appended claims. All inventions utilizing the concept of the present invention are protected.

[0042] like Figure 1As shown, the automatic radar zone generation method includes the following steps:

[0043] S1. Acquire and preprocess radar point cloud data to obtain point cloud data within m meters of the orbit and filter out noise to obtain converted point cloud data.

[0044] S2. Project the converted point cloud data onto the XY plane to generate a 2D planar map;

[0045] S3. Perform mean filtering, edge detection processing, and grayscale conversion on the 2D planar image, and generate the curve formula of the track group by fitting the curve.

[0046] S4. Take any fixed value for the Z value in 3D space to convert the curve formula to 3D space and obtain the trajectory curve in 3D space;

[0047] S5. Collect and perform noise filtering on all point clouds within a range of n meters from the orbit curve in 3D space to obtain a point cloud set;

[0048] S6. Calculate point cloud aggregation lines using point cloud sets, and obtain the spacing and smoothness of each point cloud aggregation line;

[0049] S7. Based on the spacing and smoothness of the point cloud aggregation lines, delete the curves in the point cloud aggregation lines that do not conform to the track characteristics to obtain the correct track group curves.

[0050] S8. Obtain the centerline of each group of tracks;

[0051] S9. Based on the near and far positions of the center line of each group of tracks and the left and right extension range of any position point of the center line of each group of tracks, the radar defense zone is automatically generated.

[0052] In the specific implementation process, the value of parameter m in step S1 is 30.

[0053] The specific method for collecting all point clouds within a range of n meters from the orbit curve in 3D space in step S5 is as follows:

[0054] like Figure 4 As shown, when the correct track group curve is a straight line, according to the formula:

[0055] d = |x cosθ + y sinθ - r|

[0056] Calculate the distance d of each 3-dimensional point cloud (x, y, z) to the correct orbital curve in the spatial dimension, and obtain the point cloud within 10 cm of the correct orbital curve; where r is the distance from the origin to the line; θ is the difference between π / 2 and the angle between the line and the opposite direction of the X-axis, and π is 180°;

[0057] When the correct orbital group curve is a curve, according to the formula:

[0058] d=|A+sqrt(r 2 -(yB) 2 |

[0059] Calculate the distance d from each 3-dimensional point cloud (x, y, z) to the correct orbital curve in the spatial dimension, and obtain the point cloud within 10 cm of the correct orbital curve; where sqrt represents the square root calculation; (A, B) are the coordinates of the center of the curve.

[0060] The specific method for obtaining the spacing of the point cloud aggregation lines in step S6 is as follows: According to the formula:

[0061] Dis = fabs(r1-r2)

[0062] Get the spacing Dis of the point cloud aggregation lines; where fabs(·) represents the absolute value function; when the track curve is a straight line, r1 and r2 are the distances from the origin to the two straight lines, respectively; when the track curve is a concentric circle, r1 and r2 are the radii of the concentric circle, respectively.

[0063] The specific method for obtaining the smoothness of the point cloud aggregation line in step S6 is as follows: the standard deviation Var of each point cloud aggregation line is used as the smoothness of the point cloud aggregation line.

[0064] Var=sqrt(((x1-mean)^2+(x2-mean)^2+......(x n -mean)^2) / (n-1))

[0065] mean = (x1 + x2 + ... + x) n ) / n

[0066] Where x1 to x n For each point, a coordinate value of a certain dimension is used, typically the Z value is taken for calculation.

[0067] The specific method for deleting curves that do not conform to the track characteristics in point cloud aggregation lines in step S7 is as follows: if the spacing Dis of point cloud aggregation lines is less than 1.3 meters or greater than 1.5 meters, then it is determined to be a curve that does not conform to the track characteristics and is deleted.

[0068] In step S7, the specific method for deleting curves in the point cloud aggregation line that do not conform to the track characteristics based on the smoothness of the point cloud aggregation line is as follows: if the standard deviation of a single point cloud aggregation line is less than 0.5 feet, and the standard deviation of a single possible track group is less than 0.1 feet, then it is determined to be a curve that conforms to the track characteristics and is retained; otherwise, it is determined to be a curve that does not conform to the track characteristics and is deleted.

[0069] The specific method for step S8 is as follows:

[0070] According to the formula:

[0071] C pos = (r1+r2) / 2

[0072] Get the translation C pos ; Shift the left-hand track curve in the direction of the right-hand track curve by C. pos .

[0073] The electronic device includes:

[0074] Memory, which stores executable instructions; and

[0075] The processor is configured to execute executable instructions in the memory to implement the automatic radar zone generation method.

[0076] In the actual implementation process, the mean filtering, edge detection processing, and grayscale conversion methods can all use existing image algorithms.

[0077] In one embodiment of the present invention, such as Figure 2 and Figure 3 As shown, railway tracks can be abstractly divided into two main categories: straight tracks and circular tracks. Complex scenarios involve combinations of these two types, and the fitted curve formulas are defined as follows:

[0078] x*cosθ+y*sinθ=r, where (x,y) are the coordinates of any point on the line represented by the formula, r is the distance from the origin to the line, and θ is the difference between π / 2 and the angle between the line and the opposite x-axis.

[0079] (xA) 2 +(yB) 2 =r 2 , where (x,y) are the coordinates of any point on the arc represented by the formula, (A,B) are the coordinates of the center of the circle, and r is the radius of the arc.

[0080] This invention allows for a default defense zone with a near-end distance of 7 meters and a far-end distance of 40 meters. For continuous radar protection, the far-end portion of the defense zone of adjacent radars covers the near-end blind zone of the far-end radar, creating seamless defense zone coverage. Based on the configurable default defense zone, which extends to the left and right of any point on the center line of each group of tracks within a specified range, complete defense zones from near to far can be generated by grouping tracks.

[0081] In summary, this invention can automatically establish defense zones in a given scenario based on raw point cloud data, without requiring manual intervention during the calibration process, and the calibration results are highly accurate.

Claims

1. A radar defense zone automatic generation method, characterized by, Includes the following steps: S1. Acquire and preprocess radar point cloud data to obtain point cloud data within m meters of the orbit and filter out noise to obtain converted point cloud data. S2. Project the converted point cloud data onto the XY plane to generate a 2D planar map; S3. Perform mean filtering, edge detection processing, and grayscale conversion on the 2D planar image, and generate the curve formula of the track group by fitting the curve. S4. Take any fixed value for the Z value in 3D space to convert the curve formula to 3D space and obtain the trajectory curve in 3D space; S5. Collect and perform noise filtering on all point clouds within a range of n meters from the orbit curve in 3D space to obtain a point cloud set; S6. Calculate point cloud aggregation lines using point cloud sets, and obtain the spacing and smoothness of each point cloud aggregation line; S7. Based on the spacing and smoothness of the point cloud aggregation lines, delete the curves in the point cloud aggregation lines that do not conform to the track characteristics to obtain the correct track group curves. S8. Obtain the centerline of each group of tracks; S9. Based on the near and far positions of the center line of each group of tracks and the left and right extension range of any position point of the center line of each group of tracks, the radar defense zone is automatically generated. The specific method for obtaining the smoothness of point cloud aggregation lines is as follows: the standard deviation of each point cloud aggregation line is used as the smoothness of the point cloud aggregation line; The specific method for deleting curves that do not conform to the trajectory characteristics in the point cloud aggregation line in step S7 based on the smoothness of the point cloud aggregation line is as follows: If the standard deviation of a single point cloud aggregation line is less than 0.5 feet, and the standard deviation of a single possible orbit group is less than 0.1 feet, then it is judged as a curve that meets the orbit characteristics and is retained; otherwise, it is judged as a curve that does not meet the orbit characteristics and is deleted.

2. The radar defense zone automatic generation method according to claim 1, characterized by, In step S1, the value of parameter m is 30.

3. The radar defense zone automatic generation method according to claim 1, characterized by, The specific method for collecting all point clouds within a range of n meters from the orbit curve in 3D space in step S5 is as follows: When the correct track group curve is a straight line, according to the formula: ; Calculate the spatial distance d from each 3D point cloud (x, y, z) to the correct orbital curve, and obtain the point cloud within a 10 cm radius of the correct orbital curve; where r The distance from the origin to the line; It is the difference between 90° and the angle between the line and the opposite direction of the X-axis; When the correct orbital group curve is a curve, according to the formula: ； Calculate the distance d of each 3-dimensional point cloud (x, y, z) to the correct orbital curve in the spatial dimension, and obtain the point cloud within 10 cm of the correct orbital curve; Where sqrt represents the square root calculation; (A, B) are the coordinates of the center of the curve.

4. The automatic radar defense zone generation method according to claim 1, characterized in that, The specific method for obtaining the spacing of the point cloud aggregation lines in step S6 is as follows: According to the formula: ； Obtain the spacing Dis of the point cloud aggregation lines; where This represents the function for finding the absolute value; when the trajectory curve is a straight line, r1 and r2 are the distances from the origin to the two straight lines, respectively; when the trajectory curve is a concentric circle, r1 and r2 are the radii of the concentric circles, respectively.

5. The automatic radar defense zone generation method according to claim 4, characterized in that, The specific method for deleting curves that do not conform to the orbital characteristics in the point cloud aggregation lines in step S7 based on the spacing of the point cloud aggregation lines is as follows: If the spacing Dis of the point cloud aggregation lines is less than 1.3 meters or greater than 1.5 meters, it is determined to be a curve that does not conform to the orbit characteristics and is deleted.

6. An electronic device, characterized in that, include: Memory, which stores executable instructions; as well as The processor is configured to execute executable instructions in the memory to implement the automatic radar zone generation method according to any one of claims 1 to 5.

Images