A Detection Method and System for Target Objects within the Defense Area of Urban Rail Transit

Abstract

The present invention relates to a method and system for detecting objects within the protection area of an urban rail transit, including: obtaining lidar point cloud data and image data within the protection area of the urban rail transit; segmenting the lidar point cloud data to obtain point cloud data of the region of interest; calibrating the position of the object based on the point cloud data of the region of interest to obtain a point cloud data training sample; segmenting the image data and calibrating the position of the object on the segmented image data to obtain an image data training sample; inputting the point cloud data training sample and the image data training sample into a dual-branch network for training to obtain an object detection model; and using the object detection model to complete the detection of objects within the target protection area of the urban rail transit. By using the dual-branch network structure to train image samples and lidar point cloud samples, the present invention can make full use of the advantages of both, thereby enhancing the learning effect of the object detection model and reducing the possibility of missed detection and false detection.

Description

Technical Field

[0001] The present invention relates to the technical field of target detection, and particularly to a method and system for detecting targets within the defense area of urban rail transit. Background Art

[0002] With the rapid development of urban rail transit, the importance of urban rail transit systems has become increasingly prominent, and safety has also become an urgent problem to be solved. During the operation of urban rail transit, there are many potential safety hazards, among which the detection of obstacles is particularly crucial. The existence of these obstacles may pose a threat to the safe operation of trains. Therefore, timely and accurate detection of targets within the defense area is of great significance for ensuring train operation safety and reducing accidents.

[0003] The existing obstacle detection methods mainly rely on manual inspections. However, manual inspections cannot achieve all-weather real-time monitoring. On urban rails with high loads and high operating efficiency, if obstacles cannot be detected in time, it may endanger train operation safety. In addition, the use of image recognition technology to identify obstacles is greatly affected by the environment and cannot obtain accurate azimuth information of obstacles all the time. Summary of the Invention

[0004] To solve the above problems, an object of the embodiments of the present invention is to provide a method and system for detecting targets within the defense area of urban rail transit.

[0005] A method for detecting targets within the defense area of urban rail transit includes:

[0006] Step 1: Obtain lidar point cloud data and image data within the defense area of urban rail transit;

[0007] Step 2: Segment the lidar point cloud data to obtain point cloud data of the region of interest;

[0008] Step 3: Calibrate the position of the target based on the point cloud data of the region of interest to obtain a point cloud data training sample;

[0009] Step 4: Segment the image data and calibrate the position of the target on the segmented image data to obtain an image data training sample;

[0010] Step 5: Input the point cloud data training sample and the image data training sample into a dual-branch network for training to obtain a target detection model;

[0011] Step 6: Use the target detection model to complete the detection of targets within the target defense area of urban rail transit.

[0012] Preferably, when a target is detected, it further includes:

[0013] Step 6.1: Use an inertial navigation device to obtain the absolute velocity information of the target object at each moment;

[0014] Step 6.2: Use the absolute velocity information of the target object at each moment to correct the point cloud data to obtain the corrected point cloud data;

[0015] Step 6.3: Use the corrected point cloud data to repair the motion distortion of the target object.

[0016] Preferably, in the said Step 6.1, the formula for calculating the absolute velocity of the target object at each moment is:

[0017] front_scale = (Ti - T1) / (T2 - T1)

[0018] back_scale = (T2 - Ti) / (T2 - T1)

[0019] Vi = front_scale * V2 + back_scale * V1

[0020] Wi = front_scale * W2 + back_scale * W1

[0021] Wherein, Vi represents the linear velocity of the target object at the moment of Ti, Wi represents the angular velocity of the target object at the moment of Ti, V1 represents the linear velocity output by the inertial navigation device at the moment of T1, V2 represents the linear velocity output by the inertial navigation device at the moment of T2, W2 represents the angular velocity output by the inertial navigation device at the moment of T2, and W1 represents the angular velocity output by the inertial navigation device at the moment of T1.

[0022] Preferably, in the said Step 6.2, the correction formula for the point cloud data is:

[0023] delta_T = Ti - T0

[0024] Angle = Wi * delta_T

[0025] Pi_adjust = rotate(Pi, Angle) + Vi * delta_T

[0026] Wherein, Angle represents the relative motion of the i-th point relative to the 0-th point, Wi represents the angular velocity of the target object at the moment of Ti, T0 represents the moment of the first point of the point cloud, Ti represents the moment of the i-th point in the point cloud data, Pi_adjust represents the corrected point, rotate(Pi, Angle) represents multiplying Pi by the rotation matrix after converting Angle into the rotation matrix, and Pi represents the position of the i-th original point cloud.

[0027] Preferably, step 6.3: Using the corrected point cloud data to repair the motion distortion of the target object, including:

[0028] Step 6.3.1: Calculate the curvature information of adjacent points under the same beam in the current frame of point cloud data;

[0029] Step 6.3.2: Find the matching points with the closest curvature information in the adjacent beams of the previous frame of point cloud;

[0030] Step 6.3.3: Calculate the velocity information of the target object based on the distance information between adjacent matching point pairs;

[0031] Step 6.3.4: Use the velocity information of the target object to repair the motion distortion of the target object.

[0032] Preferably, in step 6.3.1, the calculation formula for the curvature information of adjacent points under the same beam is:

[0033] Curve_i = sqrt(sum(j=-5 to +5)(Pj - Pi))

[0034] where Curve_i represents the curvature information of the i-th point, sqrt represents the square root, sum represents the summation, Pj represents the position of the adjacent point, and Pi represents the position of the i-th point.

[0035] Preferably, in step 6.3.3, the calculation formula for the velocity information of the target object is:

[0036] delta_T = Ti - Ti'

[0037] Vi' = (Pi - P') / delta_T

[0038] where delta_T represents the time between two adjacent frames, Ti represents the i-th frame, Ti' represents the previous frame, Vi' represents the linear velocity of the target object calculated from the point cloud data at time Ti, Pi represents the position of the i-th point in the current frame, and P' represents the position of the i-th point in the previous frame.

[0039] Preferably, in step 6.3.4, the formula is adopted:

[0040] delta_T = Ti - T0

[0041] P_adjust = Pi + Vi' * delta_T

[0042] To repair the motion distortion of the target object; where delta_T represents the time difference between the first point and the i-th point on the target object, P_adjust represents the point after distortion removal, and Pi represents the position of the i-th point in the current frame.

[0043] The present invention also provides a detection system for objects within the defense area of an urban rail transit, comprising:

[0044] A data acquisition module, configured to acquire lidar point cloud data and image data within the defense area of the urban rail transit;

[0045] A point cloud data segmentation module, configured to segment the lidar point cloud data to obtain the point cloud data of the region of interest;

[0046] A calibration module, configured to calibrate the position of the object based on the point cloud data of the region of interest to obtain a point cloud data training sample;

[0047] An image data segmentation module, configured to segment the image data and calibrate the position of the object on the segmented image data to obtain an image data training sample;

[0048] A training module, configured to input the point cloud data training sample and the image data training sample into a dual-branch network for training to obtain an object detection model;

[0049] An object detection module, configured to use the object detection model to complete the detection of objects within the target defense area of the urban rail transit.

[0050] According to the specific embodiments provided by the present invention, the following technical effects are disclosed:

[0051] The present invention relates to a method and system for detecting objects within the defense area of an urban rail transit. Compared with the prior art, by using a dual-branch network structure to train image samples and lidar point cloud samples, the present invention can make full use of the advantages of both, thereby enhancing the learning effect of the object detection model and reducing the possibility of missed detection and false detection.

[0052] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0054] Figure 1 It is a flowchart of a method for detecting objects within the defense area of an urban rail transit provided by the present invention;

[0055] Figure 2 It is a schematic structural diagram of a device for detecting objects within the defense area of an urban rail transit provided by the present invention;

[0056] Figure 3 This is a schematic diagram of the extraction of the region of interest provided by the present invention. Specific embodiments

[0057] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0058] In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0059] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0060] Please refer to Figure 1-2 , a method for detecting objects in the urban rail defense area of the present invention is completed on the basis of a detection device for objects in the urban rail defense area, and mainly consists of four parts, namely a data acquisition unit, a field service unit, a central management unit, and a foreign object detection platform.

[0061] (1) Front-end acquisition system: The 3D lidar and the video camera form the front-end monitoring part of the site, mainly responsible for the real-time acquisition and processing of on-site data and uploading it to the on-site server. In practical applications, the present invention can set up monitoring columns beside the railway tracks, with 2 lidars installed on 1 column, the height is 3 meters, and the distance from the track is 2 meters.

[0062] (2) On-site service system: mainly responsible for data analysis and processing results, extracting characteristic points of the ballast bed, sleeper stones, and rails from the point cloud data collected by the radar, as well as real-time comparison, and judging whether there are obstacles according to the comparison results, and performing alarm operations, etc.; and real-time processing of alarm information sent by each radar, uploading the alarm information to the monitoring center or directly triggering the alarm unit for alarm.

[0063] (3) Central management system: responsible for monitoring the entire monitored section, realizing centralized processing of data from on-site service systems scattered in various places, forwarding and storing data between the on-site service system and the client; and real-time monitoring of the operating status of the on-site main cabinet and each radar.

[0064] (4) Foreign object detection platform: provides a user interface for the three-dimensional detection system of line obstacles, and displays the operating information of on-site equipment, real-time point cloud information, on-site video information, and equipment alarm, fault information, equipment stop and start information, etc. of each section.

[0065] Furthermore, the method for detecting target objects in the urban rail defense area of the present invention includes:

[0066] Step 1: Obtain the lidar point cloud data and image data in the urban rail defense area;

[0067] Step 2: Segment the lidar point cloud data to obtain the point cloud data of the region of interest;

[0068] Since the range of the 3D lidar can reach 300m, the field of view can reach 90° horizontally and 30° vertically, and not only the track point cloud data can be detected in the field of view, but also the surrounding scenes will be covered. This requires us to set the ROI (region of interest) for the track information in the field of view and extract the track point cloud data as the monitoring area of the present invention. As Figure 3 described, the red area is the set ROI, including the ballast bed, sleeper stone, and rail point cloud data.

[0069] Step 3: Calibrate the position of the target object based on the point cloud data of the region of interest to obtain a point cloud data training sample;

[0070] In Step 3, the present invention needs to perform data background sampling on the ballast bed, sleeper stones, rails or target objects in the ROI area, establish a background sample map, and extract characteristic values and collect reflectivity information of different materials, and store them in the database for marking the position of the target object in different situations.

[0071] Step 4: Segment the image data and calibrate the position of the target object on the segmented image data to obtain an image data training sample;

[0072] Since the image data also captures the surrounding scenes, the present invention needs to use seed points to complete the segmentation of the image in a breadth-first search manner.

[0073] Step 5: Input the point cloud data training samples and the image data training samples into a dual-branch network for training to obtain an object detection model.

[0074] Compared with the three-dimensional point cloud information of lidar, the two-dimensional image loses depth information. However, due to the rich semantic information contained in the image, better results can be obtained by more fully mining the semantic information. The present invention adopts a dual-branch network structure, where one branch network structure is used to extract detailed information and the other branch is used to extract semantic information. The features output by the two branches are fused together through a fusion module for feature extraction to complete the training process of the object detection model. In this way, the information of both can be combined to improve the accuracy of object detection.

[0075] Step 6: Use the object detection model to complete the detection of objects within the target urban rail defense area.

[0076] Further, when an object is detected, it further includes: using an inertial navigation device to perform self-motion compensation on the point cloud of the lidar to obtain accurate lidar point cloud data.

[0077] Further, this step includes:

[0078] Step 6.1: Use an inertial navigation device to obtain the absolute velocity information of the object at each moment.

[0079] In practical applications, the present invention first needs to synchronize the sensor time, using GPS for time synchronization between multiple sensors, which is a prerequisite. Then, obtain the absolute velocity information of the moving object. In the present invention, the absolute velocity information of each period of a frame of point cloud can be obtained by interpolation.

[0080] Since the output frequency of the inertial navigation device is much higher than the frequency of a frame of lidar point cloud, for each point's moment, the velocity information can be obtained by interpolation calculation. For example, for a point Pi that falls between the moments T1 and T2 and has a timestamp of Ti, the velocity information at the moment Ti is:

[0081] front_scale = (Ti - T1) / (T2 - T1)

[0082] back_scale = (T2 - Ti) / (T2 - T1)

[0083] Vi = front_scale * V2 + back_scale * V1

[0084] Wi = front_scale * W2 + back_scale * W1

[0085] Where Angle represents the relative motion of the i-th point relative to the 0-th point, Wi represents the angular velocity of the target object at time Ti, T0 represents the time of the first point of the point cloud, Ti represents the time of the i-th point in the point cloud data, Pi_adjust represents the corrected point, rotate(Pi, Angle) represents multiplying Pi after converting Angle into a rotation matrix, and Pi represents the position of the i-th original point cloud.

[0086] Step 6.2: Use the absolute velocity information of the target object at each moment to correct the point cloud data to obtain the corrected point cloud data;

[0087] In Step 6.2, the motion repair for the i-th point is as follows. Here, aligning the corrected point cloud to the time of the first point of a frame of point cloud is T0.

[0088] delta_T = Ti - T0

[0089] Angle = Wi * delta_T

[0090] Pi_adjust = rotate(Pi, Angle) + Vi * delta_T

[0091] Where Angle represents the relative motion of the i-th point relative to the 0-th point, Wi represents the angular velocity of the target object at time Ti, T0 represents the time of the first point of the point cloud, Ti represents the time of the i-th point in the point cloud data, Pi_adjust represents the corrected point, rotate(Pi, Angle) represents multiplying Pi after converting Angle into a rotation matrix, and Pi represents the position of the i-th original point cloud.

[0092] Step 6.3: Use the corrected point cloud data to repair the motion distortion of the target object.

[0093] Furthermore, Step 6.3 includes:

[0094] Step 6.3.1: Calculate the curvature information of adjacent points in the same beam of the current frame of point cloud data;

[0095] In the said Step 6.3.1, the calculation formula for the curvature information of adjacent points in the same beam is:

[0096] Curve_i = sqrt(sum(j=-5 to +5)(Pj - Pi))

[0097] Among them, Curve_i represents the curvature information of the i-th point, sqrt represents the square root, sum represents the summation, Pj represents the position of the adjacent point, and Pi represents the position of the i-th point.

[0098] Step 6.3.2: Find the matching points with the closest curvature information within the adjacent beam clusters in the previous frame of point cloud; In step 6.3.2, when finding the matching points in the previous frame, use the curvature information of the 5 adjacent points in the current frame, and find some of the closest Curve points within the range of ±10 points and ±3 beam clusters at the same position in the same beam cluster of the previous frame. The L1 distance can be directly used.

[0099] Step 6.3.3: Calculate the velocity information of the target object based on the distance information between adjacent matching point pairs;

[0100] In the said step 6.3.3, the calculation formula for the velocity information of the target object is:

[0101] delta_T = Ti - Ti'

[0102] Vi' = (Pi - P') / delta_T

[0103] Among them, delta_T represents the time between two adjacent frames, Ti represents the i-th frame, Ti' represents the previous frame, Vi' represents the linear velocity of the target object calculated from the point cloud data at the Ti moment, Pi represents the position of the i-th point in the current frame, and P' represents the position of the i-th point in the previous frame.

[0104] Step 6.3.4: Use the velocity information of the target object to correct the motion distortion of the target object;

[0105] In the said step 6.3.4, the formula is adopted:

[0106] delta_T = Ti - T0

[0107] P_adjust = Pi + Vi * delta_T

[0108] Correct the motion distortion of the target object; Among them, delta_T represents the time difference between the first point and the i-th point on the target object, P_adjust represents the point after distortion correction, and Pi represents the position of the i-th point in the current frame.

[0109] The present invention can fully utilize the advantages of both by using a dual-branch network structure to train image samples and lidar point cloud samples, thereby enhancing the learning effect of the target object detection model and reducing the possibility of missed detection and false detection.

[0110] The present invention also provides a detection system for target objects within the defense area of urban rail transit, including:

[0111] A data acquisition module for acquiring lidar point cloud data and image data within the urban rail defense area;

[0112] A point cloud data segmentation module for segmenting the lidar point cloud data to obtain the point cloud data of the region of interest;

[0113] A calibration module for calibrating the position of the target object based on the point cloud data of the region of interest to obtain a point cloud data training sample;

[0114] An image data segmentation module for segmenting the image data and calibrating the position of the target object on the segmented image data to obtain an image data training sample;

[0115] A training module for inputting the point cloud data training sample and the image data training sample into a dual-branch network for training to obtain a target object detection model;

[0116] A target object detection module for using the target object detection model to complete the detection of the target object within the target urban rail defense area.

[0117] Compared with the prior art, the beneficial effects of a target object detection system within the urban rail defense area provided by the present invention are the same as those of the target object detection method within the urban rail defense area described in the above technical solution, and will not be elaborated here.

[0118] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of technical solutions of changes or substitutions, which should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A detection method for a target object within a defense area of an urban rail transit, characterized in that, Including: Step 1: Obtain lidar point cloud data and image data within the urban rail defense area; Step 2: Segment the lidar point cloud data to obtain the point cloud data of the region of interest; Step 3: Calibrate the position of the target object based on the point cloud data of the region of interest to obtain the point cloud data training sample; Step 4: Segment the image data and calibrate the position of the target object on the segmented image data to obtain the image data training sample; Step 5: Input the point cloud data training sample and the image data training sample into a dual-branch network for training to obtain a target object detection model; Step 6: Use the target object detection model to complete the detection of the target object within the target urban rail defense area; When a target object is detected, it further includes: Step 6.1: Use an inertial navigation device to obtain the absolute velocity information of the target object at each moment; In the said Step 6.1, the calculation formula for the absolute velocity of the target object at each moment is: front_scale = (Ti - T1) / (T2 - T1) back_scale = (T2 - Ti) / (T2 - T1) Vi = front_scale * V2 + back_scale * V1 Wi = front_scale * W2 + back_scale * W1 Wherein, Vi represents the linear velocity of the target object at the moment of Ti, Wi represents the angular velocity of the target object at the moment of Ti, V1 represents the linear velocity output by the inertial navigation device at the moment of T1, V2 represents the linear velocity output by the inertial navigation device at the moment of T2, W2 represents the angular velocity output by the inertial navigation device at the moment of T2, and W1 represents the angular velocity output by the inertial navigation device at the moment of T1; Step 6.2: Use the absolute velocity information of the target object at each moment to correct the point cloud data to obtain the corrected point cloud data; In the said Step 6.2, the correction formula for the point cloud data is: delta_T = Ti - T0 Angle = Wi * delta_T Pi_adjust = rotate(Pi, Angle) + Vi * delta_T Wherein, Angle represents the relative motion of the i-th point relative to the 0-th point, Wi represents the angular velocity of the target object at the moment of Ti, T0 represents the moment of the first point of the point cloud, Ti represents the moment of the i-th point in the point cloud data, Pi_adjust represents the corrected point, rotate(Pi, Angle) represents multiplying Pi by the rotation matrix after converting Angle, and Pi is the point falling between the moments of T1 and T2, and its timestamp is Ti; Step 6.3: Use the corrected point cloud data to repair the motion distortion of the target object; The said Step 6.3: Using the corrected point cloud data to repair the motion distortion of the target object, including: Step 6.3.1: Calculate the curvature information of adjacent points in the same beam of the current frame point cloud data; Step 6.3.2: Find the matching point with the closest curvature information in the adjacent beams of the previous frame point cloud; Step 6.3.3: Calculate the velocity information of the target object based on the distance information between adjacent matching point pairs; Step 6.3.4: Repair the motion distortion of the target using the velocity information of the target.

2. The detection method of the target object in the urban rail defense area according to claim 1, wherein, In the step 6.3.1, the calculation formula for the curvature information of adjacent points under the same beam is: Curve_i = sqrt(sum(j=-5 to +5)(Pj_adjust - Pi_adjust)) where Curve_i represents the curvature information of the i-th point, sqrt represents the square root, and sum represents the summation.

3. The detection method of the target object within the urban rail defense area according to claim 2, characterized in that, In the step 6.3.3, the calculation formula for the velocity information of the target is: delta_Ta = Ti - Ti' Vi' = (Pi_adjust - P') / delta_Ta where delta_Ta represents the time between two adjacent frames, Ti represents the time of the i-th point in the point cloud data, Ti' represents the time of the i-th point in the previous frame of point cloud data, and Vi' represents the linear velocity of the target calculated from the point cloud data at the time of Ti.

4. The detection method of the target object in the urban rail defense area according to claim 3, characterized in that In the step 6.3.4, the formula: delta_Tb = Ti - T0 P_adjust = Pi_adjust + Vi' * delta_Tb is used to repair the motion distortion of the target; where delta_Tb represents the time difference between the first point and the i-th point on the target, and P_adjust represents the point after distortion removal.

5. A detection system for target objects within the defense area of an urban rail transit, characterized in that, It includes: A data acquisition module for acquiring lidar point cloud data and image data within the urban rail defense area; A point cloud data segmentation module for segmenting the lidar point cloud data to obtain the point cloud data of the region of interest; A calibration module for calibrating the position of the target based on the point cloud data of the region of interest to obtain a point cloud data training sample; An image data segmentation module for segmenting the image data and calibrating the position of the target on the segmented image data to obtain an image data training sample; A training module for inputting the point cloud data training sample and the image data training sample into a dual-branch network for training to obtain a target detection model; A target detection module for using the target detection model to complete the detection of the target within the target urban rail defense area; When a target is detected, it further includes: Step 6.1: Use an inertial navigation device to obtain the absolute velocity information of the target at each moment; In the step 6.1, the calculation formula for the absolute velocity of the target at each moment is: front_scale = (Ti - T1) / (T2 - T1) back_scale = (T2 - Ti) / (T2 - T1) Vi = front_scale * V2 + back_scale * V1 Wi = front_scale * W2 + back_scale * W1 where Vi represents the linear velocity of the target at the time of Ti, Wi represents the angular velocity of the target at the time of Ti, V1 represents the linear velocity output by the inertial navigation device at the time of T1, V2 represents the linear velocity output by the inertial navigation device at the time of T2, W2 represents the angular velocity output by the inertial navigation device at the time of T2, and W1 represents the angular velocity output by the inertial navigation device at the time of T1; Step 6.2: Correct the point cloud data using the absolute velocity information of the target at each moment to obtain the corrected point cloud data; In the said Step 6.2, the correction formula for the point cloud data is: delta_T = Ti - T0 Angle = Wi * delta_T Pi_adjust = rotate(Pi, Angle) + Vi * delta_T where Angle represents the relative motion of the i-th point relative to the 0-th point, Wi represents the angular velocity of the target at the moment Ti, T0 represents the moment of the first point of the point cloud, Ti represents the moment of the i-th point in the point cloud data, Pi_adjust represents the corrected point, rotate(Pi, Angle) represents multiplying Pi by the rotation matrix after converting Angle into it, Pi is the point falling between the moments T1 and T2, and its timestamp is Ti; Step 6.3: Repair the motion distortion of the target using the corrected point cloud data; The said Step 6.3: Repair the motion distortion of the target using the corrected point cloud data, including: Step 6.3.1: Calculate the curvature information of adjacent points in the same beam of the current frame of point cloud data; Step 6.3.2: Find the matching points with the closest curvature information in the adjacent beams of the previous frame of point cloud; Step 6.3.3: Calculate the velocity information of the target based on the distance information between adjacent pairs of matching points; Step 6.3.4: Repair the motion distortion of the target using the velocity information of the target.

Images