Substation three-dimensional point cloud data acquisition method, system, device and medium

By using drones or unmanned vehicles to perform lidar scanning in substations and applying registration algorithms to process point cloud data, the disorder and conversion invariance of three-dimensional point cloud data are solved, and accurate and stable Point cloud data acquisition.

CN118898544APending Publication Date: 2024-11-05MAINTENANCE BRANCH OF STATE GRID HEBEI ELECTRIC POWER +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411079874.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-05

AI Technical Summary

Technical Problem

The prior art is difficult to overcome the disorder and conversion invariance of three-dimensional point cloud data, resulting in difficulty in obtaining accurate and consistent point cloud data in substations.

Method used

Lidar scanning is performed by drones or unmanned vehicles, point cloud data registration is carried out in combination with ICP algorithm, PL-ICP algorithm, PointDSC method or random sampling consistency algorithm, and stable output is obtained through point cloud image fusion.

Benefits of technology

It realizes accurate registration and stable output of three-dimensional point cloud data of the substation, adapts to various situations, and overcomes the problems of disorder and conversion invariance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118898544A_ABST
    Figure CN118898544A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of substation monitoring, and particularly relates to a substation three-dimensional point cloud data acquisition method, system and device and a medium. According to the method, an unmanned aerial vehicle, an unmanned vehicle or a combination of the unmanned aerial vehicle and the unmanned vehicle is used for scanning a transformer substation, after original data are obtained, the original point cloud data are registered, the selected registration method comprises an ICP algorithm, a PL-ICP algorithm, a Point DSC method or a random sampling consistency algorithm, and based on the registration result, the point cloud data of the transformer substation are registered. According to the method, point cloud image reading, matrix transformation, point cloud assignment and coloring are carried out, multiple registration algorithms are used as selections, the method can adapt to multiple situations, an accurate registration result is obtained, and finally stable output of point cloud data is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of substation monitoring, and in particular relates to a method, system, equipment and medium for acquiring three-dimensional point cloud data of a substation. Background Art

[0002] Point cloud data is a collection of points in Euclidean space, which has the characteristics of disorder, transformation invariance, sparsity, and uneven density. The organization of point cloud data is insensitive to order. No matter how the order of each point in the data is arranged, the point cloud represented by the overall data remains unchanged. At the same time, if the numerical transformation in the point cloud data is caused by spatial transformation, such as rotation or translation, the data still has no substantial change, that is, transformation invariance. Sparsity means that the point cloud is arranged in a scattered manner, which is different from image pixels, and the distance between points is irregular. Affected by equipment and environmental conditions, the density of the point cloud will vary greatly in different areas.

[0003] Point cloud data is generally organized in a two-dimensional matrix, such as O×E, where O represents the number of point clouds and E represents the data dimension. The most basic data of a point cloud is the coordinate information in three-dimensional space. In addition, channel information may also include coordinates, colors, normals, and other information.

[0004] In order to obtain the point cloud data of the substation, three-dimensional point cloud learning needs to overcome its disorder and transformation invariance. It is necessary to obtain the same output for point set data in different orders, and also to obtain the same output for the same point cloud data scanned at different angles. Summary of the invention

[0005] The present invention provides a method, system, device and medium for acquiring three-dimensional point cloud data of a substation, so as to overcome the disorder and conversion invariance of three-dimensional point clouds in the prior art.

[0006] To achieve the above object, the present invention proposes the following technical solutions:

[0007] A method for acquiring three-dimensional point cloud data of a substation comprises the following steps:

[0008] Step 1: Use a drone, an unmanned vehicle, or a combination of a drone and an unmanned vehicle to perform a lidar scan of the entire substation or the transmission line environment to obtain original point cloud data;

[0009] Step 2: perform registration based on the original point cloud data; the registration method is ICP algorithm, PL-ICP algorithm, PointDSC method or random sampling consistency algorithm;

[0010] After registration, the optimal registration result is obtained;

[0011] Step 3: Based on the optimal registration result obtained in step 2, point cloud image fusion is performed;

[0012] Read in point cloud images; use OpenCV to read in image files; use PCL to read in corresponding point cloud files;

[0013] Based on the read-in point cloud image, the transformation matrix is ​​completed according to the coordinate transformation formula calibrated by the kitti data set;

[0014] The coordinates of each point in the point cloud are transformed according to the transformation matrix, and the point cloud is assigned values ​​according to the transformed coordinates;

[0015] The assigned point cloud is colored to achieve the fusion of image data and lidar point cloud data and complete the acquisition of point cloud data.

[0016] Preferably, the ICP algorithm in step 2 is specifically:

[0017] Set the error threshold, take the distance between two points as the error, and calculate:

[0018]

[0019] Among them, R and t are parameters, x i and p i is the point cloud coordinate, N x and N p is the number of point clouds;

[0020] Based on the above formula, we get:

[0021]

[0022] in

[0023] Calculation: R = X = VU T , t=u x -Ru p ;

[0024] Determine whether the error value of R and t is less than the set threshold. If so, end the calculation; if not, perform the next iterative calculation until the error value is less than the threshold.

[0025] Preferably, the PL-ICP algorithm is specifically:

[0026] Get the initial transformation matrix, set the reference frame coordinate system, and preset the proximity threshold and error threshold;

[0027] According to the initial transformation matrix, the current point cloud data is transformed into the reference frame coordinate system. For each point, the two closest points are found, the points whose errors are greater than the proximity threshold are removed, and the error minimization equation is constructed.

[0028] Solve the minimization error equation to obtain the posture transformation matrix;

[0029] The point cloud data is aligned according to the pose conversion matrix.

[0030] Preferably, the initial transformation matrix is ​​obtained by odometer.

[0031] Preferably, the PointDSC method is specifically:

[0032] A set of matching pairs is obtained based on the original point cloud data, and the set is input into the geometric feature extraction module for feature extraction. After the features of the matching pairs are extracted, the initial confidence is set, and the matching pairs are screened using the non-maximum suppression method to obtain reliable and well-distributed matching pairs as seeds. A matching pair subset is established based on the seeds, and propensity score matching is performed to finally obtain the optimal registration.

[0033] Preferably, the random sampling consensus algorithm is specifically:

[0034] Preset the number of iterations, select a random subset from the data, set it as the in-game point, and perform verification;

[0035] The above process is iterated until the optimal solution is found or the number of iterations is reached.

[0036] Preferably, the specific process of the algorithm iteration is:

[0037] The nth point cloud is registered with the n+1th point cloud to obtain the transformation matrix, and the n+1th point cloud is multiplied by the transformation matrix to replace the n+1th point cloud with the obtained new point cloud.

[0038] A substation three-dimensional point cloud data acquisition system includes the following modules:

[0039] Laser scanning module, used for laser radar scanning of the entire substation or transmission line environment to obtain raw point cloud data;

[0040] The point cloud data registration module is used to perform registration based on the original point cloud data from the laser scanning module;

[0041] The point cloud image fusion module is used to perform point cloud image fusion based on the registration results to complete the acquisition of point cloud data.

[0042] An electronic device comprising a memory and a processor;

[0043] Memory for storing computer programs;

[0044] The processor is used to execute the computer program, and when the computer program is executed by the processor, the steps of the method for acquiring three-dimensional point cloud data of a substation are implemented.

[0045] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a method for acquiring three-dimensional point cloud data of a substation are implemented.

[0046] To achieve the above purpose, the present invention proposes the following technical solutions:

[0047] The present invention is beneficial in that:

[0048] The present invention proposes a method for acquiring three-dimensional point cloud data of a substation, and registers the original point cloud data. The selected registration methods include ICP algorithm, PL-ICP algorithm, PointDSC method or random sampling consistency algorithm, and based on the registration results, point cloud image is read in, transformation matrix is ​​completed, point cloud is assigned and colored, and multiple registration algorithms are selected to adapt to various situations, and accurate registration results are obtained, and finally stable output of point cloud data is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 A schematic diagram of a method for acquiring three-dimensional point cloud data of a substation;

[0051] Figure 2 Read in a sample image for point cloud data;

[0052] Figure 3 This is an example of the result of reading in point cloud data;

[0053] Figure 4 It is a schematic diagram showing point cloud data;

[0054] Figure 5 A schematic diagram of an electronic device. DETAILED DESCRIPTION

[0055] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0056] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.

[0057] Embodiment 1:

[0058] See also Figure 1 As shown, the present invention provides a method for acquiring three-dimensional point cloud data of a substation, which specifically includes the following steps:

[0059] Step 1: Scan the entire substation or transmission line environment with a lidar to obtain the original point cloud data;

[0060] Step 2: perform registration based on the original point cloud data;

[0061] Step 3: Based on the registration results, perform point cloud image fusion to complete the acquisition of point cloud data.

[0062] In a specific embodiment, the laser radar scanning can be performed by multiple drones or unmanned vehicles or a combination of the two to perform scanning based on a preset planned route.

[0063] In a specific implementation, the registration in step 2 uses an ICP algorithm, specifically:

[0064] Taking the distance between two points as the error, the formula is:

[0065]

[0066] Among them, R and t are parameters, x i and p i is the point cloud coordinate, N x and N p is the number of point clouds;

[0067] Based on the above formula, R and t are solved as parameters and the error equation is simplified to:

[0068]

[0069] From the above formula, we can get:

[0070]

[0071] in

[0072] Assuming that matrix A is a positive definite symmetric matrix, then for any orthogonal matrix B, Trace(A)≥Trace(BA). Perform SVD decomposition on H: H=UΛV T Let X = VU T , then X is an orthogonal matrix. XH=VU T UΛV T =VΛV TA positive symmetric matrix is ​​obtained. Then: Trace(XH)≥Trace(BXH). B is an arbitrary orthogonal matrix, and X is also an orthogonal matrix, so BX can cover all orthogonal matrices. Therefore, BX also includes the rotation matrix T that needs to be solved, so Trace(RH)≤Trace(XH). When R=X, the equation holds. Therefore, R=X=VU T , then t=u x -Ru p The calculated R and t are calculated in the next iteration until the error value is less than the set threshold.

[0073] In a specific implementation, the registration method in step 2 adopts the PL-ICP algorithm, and the PL-ICP uses the distance from a point to the line connecting its two nearest points, specifically:

[0074] Given the initial transformation matrix, set the reference frame coordinate system, preset the proximity threshold and error threshold, and transform the current point cloud to the reference frame coordinate system. For each point in the current laser frame, find its two nearest points j1 and j2. Remove points whose errors are greater than the proximity threshold and construct the error minimization equation. Solve the pose transformation matrix.

[0075] The initial transformation matrix in the PL-ICP method is obtained through odometry.

[0076] The pose transformation matrix is ​​used for the next iterative calculation, and the one required for the subsequent iterative calculation is obtained by the previous algorithm iterative calculation until the error value is less than the error threshold.

[0077] In a specific implementation, the registration method in step 2 adopts PointDSC, and the PointDSC is mainly composed of three modules, one is a non-local geometric feature extraction module SCNonlocalModule guided by spatial consistency features; a differentiable spectral matching module; and finally a seed selection module of a seed mechanism for solving low overlap situations, which selects multiple seeds with high confidence and their fields as subsets, solves R and t, and selects R and t with the smallest objective function values ​​under all point clouds.

[0078] A set of matching pairs is obtained based on the original point cloud data, and the set is input into the geometric feature extraction module for feature extraction. After the features of the matching pairs are extracted, the initial confidence is set, and the matching pairs are screened using the non-maximum suppression method to obtain reliable and well-distributed matching pairs as seeds. A matching pair subset is established based on the seeds, and propensity score matching (NSM) is performed to finally obtain the optimal solution [R, t] for the registration.

[0079] The non-local geometric feature extraction module is used to extract features from a set.

[0080] The differentiable spectrum matching module and the seed selection module cooperate to complete the setting of the initial confidence, seed screening and propensity score matching and finally obtain the optimal solution.

[0081] In a specific embodiment, the registration method in step 2 adopts a random sampling consensus algorithm (RANSAC), which can estimate the parameters of a mathematical model from a set of observation data containing "outliers" in an iterative manner; this algorithm achieves its goal by repeatedly selecting a set of random subsets in the data. The selected subsets are assumed to be inliers and verified, and the above process is iterated until the best model is found or the number of iterations is reached.

[0082] Optional solutions for the algorithm iteration include:

[0083] At the same time, the first point cloud is started backward and the nth point cloud is started forward for registration, and finally they overlap.

[0084] The nth point cloud is registered with the n+1th point cloud to obtain the transformation matrix, and the n+1th point cloud is multiplied by the transformation matrix to replace the n+1th point cloud with the obtained new point cloud.

[0085] The nth point cloud is registered with the n+1th point cloud to obtain the transformation matrix, and the n+1th point cloud is multiplied by the transformation matrix. The new point cloud is spliced ​​with the nth point cloud, and then the n+1th point is replaced.

[0086] In this embodiment, the nth point cloud is selected to be registered with the n+1th point cloud to obtain a transformation matrix, and the n+1th point cloud is multiplied by the transformation matrix to replace the n+1th point cloud with the obtained new point cloud.

[0087] In a specific implementation, the point cloud image fusion in step 3 is specifically as follows:

[0088] Step 3.1, read in the point cloud image; use OpenCV to read in the png image file; use PCL to read in the corresponding pcd point cloud file; Figure 2 and Figure 3 As shown;

[0089] Step 3.2, transformation matrix preparation; according to the coordinate transformation formula calibrated when the kitti data set was collected, calculate the transformation from the point x (x, y, z, 1) in the point cloud coordinates to the y (u, v, 1) in the image coordinates:

[0090]

[0091] Where T is the coordinate transformation rotation and translation matrix;

[0092] R(0) is the correction matrix from each camera to camera 0;

[0093] P is the intrinsic parameter matrix of each camera;

[0094] In engineering calculations, each matrix needs to be expanded in rows and columns:

[0095]

[0096] Calculate P*R*T in advance for the next step of coordinate transformation;

[0097] Step 3.3, perform coordinate transformation on each point in the point cloud, read out the image pixel RGB according to the transformed image coordinates, and assign it to the point cloud.

[0098] Step 3.4, display the colored point cloud; based on the PCL point cloud library, OpenCV library, and kitti data set, complete the coloring of the point cloud data, that is, the fusion of image data and lidar point cloud data, such as Figure 4 shown.

[0099] In a specific implementation, in step 3.4, the colored point cloud is displayed using Visualization of the PCL library.

[0100] Embodiment 2:

[0101] The present invention provides a three-dimensional point cloud data acquisition system for a substation, which is used to implement a point cloud image fusion module method described in the above-mentioned embodiment 1, and specifically includes a laser scanning module, a point cloud data registration module and a point cloud image fusion module.

[0102] The laser scanning module is used to implement step 1 described in the above embodiment 1, relying on drones and unmanned vehicles to perform laser radar scanning on the entire substation or transmission line environment to obtain original point cloud data.

[0103] The point cloud data registration module is used to implement step 2 described in the above embodiment 1, and performs registration based on the original point cloud data from the laser scanning module.

[0104] The point cloud image fusion module is used to implement step 3 described in the above embodiment 1, and perform point cloud image fusion based on the registration result to complete the acquisition of point cloud data.

[0105] In a specific embodiment, in a structured environment, step 2 selects PL-ICP instead of ICP.

[0106] In a specific implementation, the PointDSC is applied when the length consistency requirement is not strong and the number of outliers is moderate.

[0107] In a specific embodiment, the random sampling consensus algorithm can estimate high-precision parameters from a data set containing a large number of outliers, so the random sampling consensus algorithm is selected when processing data containing a large number of outliers.

[0108] In a specific embodiment, the number of iterations of the random sampling consensus algorithm can be modified according to the accuracy requirements.

[0109] Embodiment 3:

[0110] See also Figure 5 As shown, the present invention also provides an electronic device 100; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0111] The memory 101 can be used to store the computer program 103, and the processor 102 implements the steps of the method for acquiring substation three-dimensional point cloud data described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0112] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0113] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0114] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for acquiring three-dimensional point cloud data of a substation, and the processor 102 can execute the plurality of instructions to implement:

[0115] Step 1: Scan the entire substation or transmission line environment with a lidar to obtain the original point cloud data;

[0116] Step 2: perform registration based on the original point cloud data;

[0117] Step 3: Based on the registration results, perform point cloud image fusion to complete the acquisition of point cloud data.

[0118] Embodiment 4:

[0119] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0120] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM).

[0121] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.

[0122] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0124] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for acquiring three-dimensional point cloud data of a substation, characterized in that: The steps include: Step 1: Use a drone, an unmanned vehicle, or a combination of a drone and an unmanned vehicle to perform a lidar scan of the entire substation or the transmission line environment to obtain original point cloud data; Step 2: perform registration based on the original point cloud data; the registration method is ICP algorithm, PL-ICP algorithm, PointDSC method or random sampling consistency algorithm; After registration, the optimal registration result is obtained; Step 3: Based on the optimal registration result obtained in step 2, point cloud image fusion is performed; Point cloud image reading; use OpenCV to read image files; Use PCL to read the corresponding point cloud file; Based on the read-in point cloud image, the transformation matrix is ​​completed according to the coordinate transformation formula calibrated by the kitti data set; The coordinates of each point in the point cloud are transformed according to the transformation matrix, and the point cloud is assigned values ​​according to the transformed coordinates; The assigned point cloud is colored to achieve the fusion of image data and lidar point cloud data and complete the acquisition of point cloud data.

2. A method for acquiring three-dimensional point cloud data of a substation according to claim 1, characterized in that: The ICP algorithm in step 2 is specifically: Set the error threshold, take the distance between two points as the error, and calculate: Among them, R and t are parameters, xi and pi are point cloud coordinates, Nx and Np are the number of point clouds; Based on the above formula, we get: in The calculation results show that: R = X = VUT, t = ux-Rup; Determine whether the error value of R and t is less than the set threshold. If so, end the calculation; if not, perform the next iterative calculation until the error value is less than the threshold.

3. A method for acquiring three-dimensional point cloud data of a substation according to claim 1, characterized in that: The PL-ICP algorithm is specifically: Get the initial transformation matrix, set the reference frame coordinate system, and preset the proximity threshold and error threshold; According to the initial transformation matrix, the current point cloud data is transformed into the reference frame coordinate system. For each point, the two closest points are found, the points whose errors are greater than the proximity threshold are removed, and the error minimization equation is constructed. Solve the minimization error equation to obtain the posture transformation matrix; The point cloud data is aligned according to the pose conversion matrix.

4. A method for acquiring three-dimensional point cloud data of a substation according to claim 3, characterized in that: The initial transformation matrix is ​​obtained through odometry.

5. A method for acquiring three-dimensional point cloud data of a substation according to claim 1, characterized in that: The PointDSC method is specifically: A set of matching pairs is obtained based on the original point cloud data, and the set is input into the geometric feature extraction module for feature extraction. After the features of the matching pairs are extracted, the initial confidence is set, and the matching pairs are screened using the non-maximum suppression method to obtain reliable and well-distributed matching pairs as seeds. A matching pair subset is established based on the seeds, and propensity score matching is performed to finally obtain the optimal registration.

6. A method for acquiring three-dimensional point cloud data of a substation according to claim 1, characterized in that: The random sampling consensus algorithm is specifically: Preset the number of iterations, select a random subset from the data, set it as the in-game point, and perform verification; The above process is iterated until the optimal solution is found or the number of iterations is reached.

7. A method for acquiring three-dimensional point cloud data of a substation according to claim 6, characterized in that: The specific process of the algorithm iteration is: The nth point cloud is registered with the n+1th point cloud to obtain the transformation matrix, and the n+1th point cloud is multiplied by the transformation matrix to replace the n+1th point cloud with the obtained new point cloud.

8. A substation three-dimensional point cloud data acquisition system, characterized in that: Includes the following modules: Laser scanning module, used for laser radar scanning of the entire substation or transmission line environment to obtain raw point cloud data; The point cloud data registration module is used to perform registration based on the original point cloud data from the laser scanning module; The point cloud image fusion module is used to perform point cloud image fusion based on the registration results and complete the acquisition of point cloud data.

9. An electronic device, characterized in that: including memory and processor; Memory for storing computer programs; A processor is used to execute the computer program, and when the computer program is executed by the processor, the steps of the method for acquiring three-dimensional point cloud data of a substation as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the method for acquiring three-dimensional point cloud data of a substation as described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Automatic acquisition method and system for vehicle point clouds at specific locations and angles

    CN120065195B