Three-dimensional reconstruction method, system and equipment for extra-high voltage power transmission and transformation line

Abstract

The invention discloses a three-dimensional reconstruction method, system and device for an extra-high voltage power transmission and transformation line, and belongs to the technical field of point cloud reconstruction. The three-dimensional reconstruction method comprises the following steps: placing a laser radar along the extra-high voltage power transmission and transformation line to obtain point cloud data of the extra-high voltage power transmission and transformation line; rTK positioning software is placed at the laser radar and the selected reference point to obtain longitude, latitude and height coordinate data; correcting and filtering the obtained point cloud data and longitude and latitude coordinate data of the extra-high voltage power transmission and transformation line; splicing the filtered extra-high voltage power transmission and transformation line point cloud data, and constructing a preliminary reconstruction model; performing point cloud segmentation on the preliminary reconstruction model by using a region growing algorithm, and extracting incomplete power transmission tower point clouds in the preliminary reconstruction model; acquiring three-dimensional models of different types of required power transmission towers, and constructing a standard model library; and matching the incomplete point cloud of the power transmission tower with the constructed standard model library, and placing a matched three-dimensional model in a scene to realize complete point cloud reconstruction.

Description

Technical Field

[0001] The present invention relates to the technical field of point cloud reconstruction, and in particular to a method, system and device for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines. Background Art

[0002] With the rapid development of the power industry, UHV transmission and transformation lines are important national infrastructure, and their safe and efficient operation is of great significance to ensuring national energy security and economic development. However, UHV transmission and transformation lines have large spans and are located in remote areas. Traditional manual inspection methods have problems such as high work intensity, low efficiency, harsh conditions, and inability to operate all-weather, and it is difficult to perform accurate spatial analysis and fault location. Therefore, developing a method that can automatically inspect UHV transmission and transformation lines is of great significance to improving inspection efficiency, reducing operation and maintenance costs, and ensuring power grid security. Among them, the three-dimensional reconstruction method has been applied.

[0003] Existing 3D reconstruction methods include model reconstruction methods based on oblique photography and deep learning modeling methods. The oblique photography modeling method has low modeling accuracy and is mainly used for geographic information collection, which cannot meet the modeling accuracy requirements of transmission towers; the deep learning modeling method requires the construction of a large data set for training and learning.

[0004] In recent years, laser radar (LiDAR) technology has developed rapidly, providing a new solution for power line inspection. The real-time, all-weather, high-efficiency and high-precision characteristics of LiDAR make it an important tool for power line inspection. The three-dimensional point cloud data of ultra-high voltage transmission and transformation lines collected by LiDAR can realize accurate modeling and three-dimensional reconstruction of power lines, towers and other equipment, providing reliable data support for subsequent inspections, monitoring and fault analysis. However, due to the long length of ultra-high voltage transmission and transformation lines and the complex scenes involved, it is impossible to accurately reconstruct their three-dimensional models, which affects the control of the lines by technicians and makes it impossible to smoothly carry out subsequent fault location, data analysis and planning evaluation. Summary of the invention

[0005] The purpose of the present invention is to overcome the problems existing in the prior art and to provide a method, system and device for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines.

[0006] The objective of the present invention is achieved through the following technical solutions:

[0007] In a first aspect, a method for 3D reconstruction of an ultra-high voltage transmission and transformation line is provided, comprising the following steps:

[0008] S1. Place a laser radar along the UHV transmission and transformation line to obtain point cloud data of the UHV transmission and transformation line, and place RTK positioning software at the laser radar and the selected reference point to obtain longitude and latitude high coordinate data;

[0009] S2, correcting the acquired point cloud data and longitude and latitude high coordinate data of the UHV transmission and transformation line to obtain a transformation matrix for posture correction;

[0010] S3. Filter the corrected point cloud data of the UHV transmission and transformation line to remove noise points to avoid the problem of excessive details being deleted by mistake and insufficient high-density compression due to uneven distribution of point cloud data;

[0011] S4, splicing the filtered UHV transmission and transformation line point cloud data to build a preliminary reconstruction model;

[0012] S5. Use a region growing algorithm to perform point cloud segmentation on the preliminary reconstruction model to extract the incomplete transmission tower point cloud;

[0013] S6. Considering the duplication of transmission towers in UHV transmission and transformation lines, obtain the three-dimensional models of different types of transmission towers required and build a standard model library;

[0014] S7. Match the incomplete point cloud of the transmission tower with the constructed standard model library, place the matched three-dimensional model in the scene, and achieve complete point cloud reconstruction.

[0015] Preferably, the step S1 specifically includes:

[0016] Considering the height of the transmission tower, the position of the LiDAR is selected according to the actual scene, and the LiDAR posture is adjusted to ensure that the entire transmission tower point cloud can be obtained from the current viewing angle. The initial posture angle of the LiDAR is recorded at this time.

[0017] Place four different reference points in the laser radar measurement scene, and use RTK positioning software to obtain the longitude and latitude coordinate data at the laser radar and the reference points, wherein the longitude and latitude coordinate data includes longitude, latitude and elevation information;

[0018] Place laser radars along the UHV transmission and transformation lines to obtain point clouds, ensuring that the point clouds taken by adjacent laser radars have a certain degree of overlap.

[0019] Preferably, the step S2 specifically includes:

[0020] There are measurement errors when the laser radar collects data. The initial attitude angle of the laser radar is fine-tuned to find the minimum value of the error;

[0021] The longitude and latitude high-coordinate data are converted to the Earth-centered Earth-fixed coordinate system through coordinate transformation;

[0022] The conversion process between the radar coordinate system and the Earth-centered Earth-fixed coordinate system is regarded as a linear process, and a linear model is established;

[0023] The total least squares estimation method is used to solve the parameters in the linear model, obtain the transformation matrix between the coordinate systems, and achieve preliminary posture correction;

[0024] A reference point is randomly selected from the corrected point cloud data, and the parameters are estimated again according to the Earth-centered Earth-fixed coordinates of the reference point to optimize the linear model.

[0025] Preferably, the step S3 specifically includes:

[0026] The point cloud data of the UHV transmission and transformation line are filtered using a straight-through filter and an adaptive density voxel filtering algorithm, wherein the straight-through filter is used to remove the ground information points and the outliers in the background in the initial point cloud image of the transmission tower to obtain the point cloud image of the transmission tower under the current viewing angle; the adaptive density voxel filtering algorithm is used to divide the point set into two categories of high and low density, and the point neighborhood density is used as a label. Different compression ratios are used to achieve high compression ratio and high quality compression of the point cloud data.

[0027] Preferably, the step S4 specifically includes:

[0028] Take the center point of the laser radar lens as the origin and establish the point cloud coordinate system;

[0029] Taking the center of the earth as the origin, establish the Earth-centered Earth-fixed coordinate system;

[0030] Mapping each coordinate point in the point cloud image of different sections of the UHV transmission and transformation line to each coordinate point of the Earth-centered Earth-fixed coordinate system after coordinate conversion to obtain an absolute coordinate value;

[0031] The mapped point cloud images of the ultra-high voltage transmission and transformation lines under each section are spliced ​​to obtain a preliminary three-dimensional reconstruction model.

[0032] Preferably, the step S5 specifically includes:

[0033] The normal vectors of all data points are calculated by a local surface fitting algorithm, and their curvature values ​​are estimated at the same time;

[0034] All data points are input into the empty queue in ascending order according to the curvature value in their local range, and the minimum curvature point is taken from the queue and added to the seed point set;

[0035] Search for neighboring points of the current seed point. If the angle between the normal of the neighboring point and the normal of the current seed point is less than the set threshold, and the curvature value of these neighboring points is also less than the set threshold, then these neighboring points will be added to the seed point sequence, and then the current seed point will be removed, and then the new seed point will continue to grow;

[0036] Repeat the above process until all seed points have been processed.

[0037] Preferably, the step S6 specifically includes:

[0038] Considering geographical factors, choose transmission towers with safe, open and unobstructed surroundings in the power transmission and transformation lines;

[0039] Obtain point cloud data of the transmission tower from three angles, set four different reference points in each scene, and place RTK positioning software at the lidar and the selected reference points to obtain longitude and latitude coordinates;

[0040] Process the acquired 3D point cloud data and longitude and latitude coordinates to obtain the transformation matrix for posture correction;

[0041] Filtering the three-dimensional point cloud data to obtain filtered point cloud data;

[0042] A three-dimensional point cloud fusion image is constructed according to the filtered point cloud data to obtain a three-dimensional model of the transmission tower.

[0043] Preferably, the step S7 specifically includes:

[0044] Matching the incomplete transmission tower extracted after the point cloud segmentation with the three-dimensional model of the transmission tower in the standard library model, wherein the incomplete transmission tower after the point cloud segmentation is matched with the three-dimensional model of the transmission tower in the standard library model using an ICP registration algorithm;

[0045] The successfully matched 3D model is placed in the scene to realize the 3D model reconstruction of the UHV transmission and transformation line.

[0046] In a second aspect, a three-dimensional reconstruction system for ultra-high voltage transmission and transformation lines is provided, comprising:

[0047] The data acquisition module is used to place a laser radar along the UHV transmission and transformation line to obtain the point cloud data of the UHV transmission and transformation line, and to place an RTK positioning software at the laser radar and the selected reference point to obtain the longitude and latitude high coordinate data;

[0048] The correction module is used to correct the acquired point cloud data and longitude and latitude high coordinate data of the UHV transmission and transformation line to obtain the transformation matrix of posture correction;

[0049] A filtering module is used to filter the corrected point cloud data of the UHV transmission and transformation line;

[0050] The splicing module is used to splice the filtered point cloud data of the UHV transmission and transformation line to build a preliminary reconstruction model;

[0051] A point cloud segmentation module, used to perform point cloud segmentation on the preliminary reconstruction model using a region growing algorithm, and extract the incomplete transmission tower point cloud therein;

[0052] The standard library module is used to obtain the 3D models of different types of transmission towers and build a standard model library;

[0053] The matching module is used to match the incomplete point cloud of the transmission tower with the constructed standard model library, place the matched 3D model in the scene, and realize complete point cloud reconstruction.

[0054] According to a third aspect, an electronic device is provided, comprising a memory and a processor, wherein the memory stores computer instructions executable on the processor, and the processor executes any one of the methods for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines when executing the computer instructions.

[0055] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the methods for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines is implemented.

[0056] It should be further explained that the technical features corresponding to the above options can be combined or replaced with each other to form a new technical solution if there is no conflict.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] (1) The present invention realizes accurate reconstruction of UHV transmission and transformation lines through automated processing flow and high-precision 3D modeling technology, which can adapt to complex scenarios and ensure that technicians can accurately control the lines. It also realizes fault location, data analysis and planning evaluation.

[0059] (2) High-precision modeling: The UHV transmission and transformation line reconstruction method based on 3D point cloud data can accurately describe the surface features of the power scene and restore the geometric shapes of equipment such as power lines and transmission towers, providing a more reliable and accurate data basis for model equipment and shape measurement.

[0060] (3) Automated processing: This method uses an automated processing flow, including point cloud capture, filtering, correction, splicing, and matching, to achieve rapid construction of a three-dimensional model of UHV transmission and transformation lines, greatly improving work efficiency.

[0061] (4) All-weather operation: LiDAR technology has the ability to operate in all weather conditions and is less affected by weather and lighting conditions. It has high real-time performance and can perform data collection and 3D reconstruction at any time.

[0062] (5) Spatial analysis capability: 3D point cloud data not only provides geometric information of power equipment, but also contains rich spatial position relationship information. Through the analysis of 3D models, it is possible to accurately measure and analyze parameters such as the spatial configuration structure, type, gross error points, and span length of power lines, providing strong support for subsequent operation and maintenance management and fault handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A flowchart of a method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines shown in an embodiment of the present invention;

[0064] Figure 2 A flow chart of a region growing algorithm shown in an embodiment of the present invention;

[0065] Figure 3 This is a functional module diagram of a three-dimensional reconstruction system for ultra-high voltage transmission and transformation lines according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various configurations. 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.

[0067] It should be noted that the defects existing in the solutions in the above-mentioned prior art are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above-mentioned problems and the solutions proposed in the embodiments of the present application for the above-mentioned problems below should all be the contributions made by the inventor to the present application in the process of invention and creation, and should not be understood as technical contents known to technical personnel in this field.

[0068] In view of the technical problems pointed out in the background technology, the embodiments provided by the present invention are as follows:

[0069] Embodiment 1

[0070] In an exemplary embodiment, if Figure 1 As shown, a method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines using a point cloud reconstruction method is provided, and the reconstruction method includes:

[0071] Step 1: Place a laser radar along the UHV transmission and transformation line to obtain the point cloud data of the transmission and transformation line, and place RTK positioning software at the laser radar and the selected reference point to obtain the longitude and latitude coordinates. Step 1 specifically includes:

[0072] Step 1.1: Set up a laser radar along the UHV transmission and transformation line to ensure that the point cloud data obtained from all viewing angles can cover the entire UHV transmission and transformation line of the section, and record the initial attitude angle of the laser radar at this time;

[0073] Step 1.2: Place a reference point in the LiDAR measurement scene and use RTK positioning software to obtain the longitude and latitude coordinates of the LiDAR and reference point, including longitude, latitude, and elevation information.

[0074] In practical applications, in order to ensure the integrity of the finally reconstructed UHV transmission and transformation lines, the laser radars installed between adjacent sections need to ensure that the point clouds obtained from each other have a certain degree of overlap, and 4 reference points are set in each laser radar measurement scene.

[0075] Step 2: Process the obtained point cloud data and longitude and latitude coordinates of the power transmission and transformation line to obtain a transformation matrix for posture correction; Step 2 specifically includes:

[0076] Step 2.1: There is a measurement error when the laser radar collects data. Fine-tune the initial attitude angle of the laser radar to find the minimum value of the error;

[0077] In practical applications, the A* algorithm in the search algorithm is used to evaluate each search branch in the state space, select the current optimal branch, and consider the previously selected branch. When the sum of the two is optimal, continue searching from this branch to achieve the minimum error.

[0078] Step 2.2: The longitude and latitude coordinates are converted into the Earth-centered Earth-fixed coordinate system in the absolute coordinate system through coordinate transformation;

[0079] In practical applications, coordinate conversion is performed according to formula (1). Where lon is longitude, lat is latitude, alt is elevation, and e is the eccentricity of the ellipsoid is the radius of curvature of the reference ellipsoid, a=6378137 is the major radius of the earth, and b=6356752.314 is the minor radius of the earth;

[0080]

[0081] Step 2.3: Approximate the conversion process between the radar coordinate system and the Earth-centered Earth-fixed coordinate system as a linear process and establish a linear model;

[0082] In practical applications, the coordinate transformation process is approximately regarded as a linear model (A+E)θ=(b+e), where E and e are the errors generated in the measurement process, the m*n dimensional data matrix A composed of the point cloud coordinates and the m*1 dimensional data vector b composed of the earth-centered earth-fixed coordinates, and the n*1 dimensional vector θ composed of the parameters to be estimated. Let the augmented matrix B=[-b,A], the matrix A, the parameter vector θ and the data vector b are shown in formula (2), where (x1, y1, z1) are the coordinates in the radar coordinate system, and (x2, y2, z2) are the coordinates in the earth-centered earth-fixed coordinate system;

[0083]

[0084] θ=[a1,a2,a3,a4,a5,a6,a7,a8,a9] T (2)

[0085] b=[x2,y2,z2] T

[0086] Step 2.4: Apply the total least squares estimation method to solve the parameters in the linear model, obtain the transformation matrix between the coordinate systems, and achieve preliminary posture correction. Step 2.4 specifically includes:

[0087] Step 2.4.1: Calculate the SVD of the augmented matrix B, as shown in formula (3), and store the right singular matrix V, where ∑ p =diag(σ1,σ2,...,σ p ,0,...,0) is a diagonal matrix;

[0088]

[0089] Step 2.4.2: Determine the effective rank p of the augmented matrix B, that is, only p of the parameter vectors are linearly independent;

[0090] Step 2.4.3: Use formula (4) and formula (5) to calculate the (p+1)*(p+1) matrix S (p) , where ν(i,j) is the element in the i-th row and j-th column of the right singular matrix V;

[0091]

[0092] Step 2.4.4: Find S (p) The inverse matrix S -(p) , and the optimal least squares approximate solution is obtained according to formula (6), where S -1(p) (i+1,1) is S -(p) The element in the i+1th row and 1st column of the matrix.

[0093] θ TLS (i) = S-(p) (i+1,1) / S -1(p) (1,1),i=1,2,...,p (6)

[0094] Step 2.5: Randomly select reference points from the corrected point cloud data, perform several parameter estimations based on the Earth-centered Earth-fixed coordinates of the reference points, and optimize the linear model.

[0095] Step 3: Filter the point cloud data to remove noise points to avoid the problem of excessive details being deleted by mistake and insufficient high-density compression due to uneven distribution of point cloud data. Step 3 specifically includes:

[0096] Step 3.1: Set the filtering range in three dimensions, use straight-through filtering to exclude irrelevant background and interference objects in the initial point cloud image of the UHV transmission and transformation line, and only retain points in a specific area to obtain a point cloud image of the current section;

[0097] Step 3.2: Use the adaptive density voxel filtering algorithm to divide the point set into high and low density categories, use the point neighborhood density as a label, and use different compression ratios to achieve high compression ratio and high quality compression of the point cloud data. Step 3.2 specifically includes:

[0098] Step 3.2.1: The current road segment point cloud dataset is X = {p i =(x i ,y i ,z i )|i=1,2,…,M}, the average distance from the point to the nearest point is calculated as shown in formula (7), where d i is the average distance, d i,j is the Euclidean distance;

[0099]

[0100] If d i Subordinate to the normal distribution N(μ,σ 2 ), calculate the global average distance The standard deviation σ and density threshold T are

[0101]

[0102] Where n is the standard deviation density.

[0103] Step 3.2.2: Put the points within and outside the threshold range into the high-density point set D respectively. h ={X i |d i ≤T} and high-density point set D l ={X i |d i ≥T};

[0104] Step 3.2.3: Set up high and low density point set networks and map the point space to the corresponding grids;

[0105] Step 3.2.4: Take the center of gravity X of the grid midpoint c Replace other points and merge the remaining points to obtain the compressed point cloud data of UHV transmission and transformation lines.

[0106] Step 4: Stitching is performed based on the filtered point cloud to construct a preliminary reconstruction model.

[0107] Step 5: Use the region growing algorithm to segment the preliminary reconstruction model and extract the incomplete transmission tower point cloud. Figure 2 , step 5 specifically includes:

[0108] Step 5.1: Calculate the normal vectors of all data points through the local surface fitting algorithm and estimate their curvature values. Step 5.1 specifically includes:

[0109] Step 5.1.1: Calculate the normal vector for point p in the point cloud i , first calculate its K nearest neighbor points p1, p2, ... p k}. Then, according to the least squares principle, a local plane is fitted using K neighboring points. Finally, by fitting the point p i The covariance matrix C of the corresponding K neighboring points is decomposed by eigenvalues ​​to calculate the normal vector of the point. i The normal vector of is the eigenvector corresponding to the minimum eigenvalue, as shown in (10). i The number of neighboring elements of For p i The centroid of all neighboring points, λ j is the j-th eigenvalue of the covariance matrix, is the jth eigenvector of the covariance matrix. Eigenvalue Represents the three main directions of the region. If λ1<λ2<λ3, the eigenvector corresponding to λ1 is Defined as the normal vector of point P;

[0110]

[0111] Step 5.1.2: Determine the direction of the normal vector by comparing the angle between the normal vector of the point and the vector from the point to the viewpoint. If the angle between the normal vector of the point and the vector from the point to the viewpoint is acute, that is, the scalar product of the two vectors is greater than 0, as shown in formula (11), where V p represents the viewpoint, set to (0,0,0), p k represents any point in space, For point p k The normal vector of

[0112]

[0113] Step 5.1.3: Obtain the surface curvature of the point cloud by calculating the eigenvalues ​​of the covariance matrix. The eigenvalue λ1 represents the change along the normal vector, while λ2 and λ3 describe the distribution of points in the neighborhood on the tangent plane. i The curvature σ of can be approximated as the relationship between these eigenvalues.

[0114]

[0115] Step 5.2: Input all data points into the empty queue in ascending order according to the curvature value in their local range, and take the minimum curvature point from the queue and add it to the seed point set;

[0116] Step 5.3: Search for neighboring points of the current seed point. If the angle between the normal of the neighboring point and the normal of the current seed point is less than the set threshold, and the curvature value of these neighboring points is also less than the set threshold, then these neighboring points will be added to the seed point sequence, and then the current seed point will be removed, and then the new seed point will continue to grow;

[0117] Step 5.4: Repeat the above process until all seed points have been processed.

[0118] Step 6: Considering the repetitiveness of transmission towers in UHV transmission and transformation lines, build 3D models of different types of transmission towers and construct a standard model library. Step 6 specifically includes:

[0119] Step 6.1: Considering geographical factors, select transmission towers with safe surroundings, open space and no obstructions in the UHV transmission and transformation lines;

[0120] Step 6.2: Obtain point cloud data of the transmission tower from three angles, set four different reference points in each scene, and place RTK positioning software at the lidar and the selected reference points to obtain longitude and latitude coordinates;

[0121] Step 6.3: Process the obtained 3D point cloud data and longitude and latitude coordinates to obtain the transformation matrix for posture correction, refer to step 2;

[0122] Step 6.4: Filter the three-dimensional point cloud data to obtain filtered point cloud data, refer to step 3;

[0123] Step 6.5: construct a 3D point cloud fusion image based on the filtered point cloud data to obtain a 3D model of the transmission tower. Step 6.5 specifically includes:

[0124] Step 6.5.1: Establish a point cloud coordinate system with the center point of the laser radar lens as the origin;

[0125] Step 6.5.2: Establish an Earth-centered Earth-fixed coordinate system with the center of the Earth as the origin;

[0126] Step 6.5.3: Map each coordinate point in the point cloud image of the transmission tower at different viewing angles to each coordinate point of the Earth-centered Earth-fixed coordinate system after coordinate conversion to obtain an absolute coordinate value;

[0127] Step 6.5.4: Fusing the mapped point cloud images of the transmission tower at different viewing angles to obtain a three-dimensional model of the transmission tower.

[0128] In practical applications, the ICP algorithm is used to perform three-dimensional point cloud fusion on the point cloud images of each viewpoint mapped to the Earth-centered Earth-fixed coordinate system after coordinate transformation. Step 6.5.4 specifically includes:

[0129] Step 6.5.4.1: Select a point set p∈P in the target point cloud P;

[0130] Step 6.5.4.2: In the source point cloud Q, select the corresponding point set q∈Q so that the value of |qp| is minimized;

[0131] Step 6.5.4.3: Calculate the rotation matrix R and the translation matrix T based on the corresponding point set so that the distance error calculated by formula (13) is minimized;

[0132]

[0133] Step 6.5.4.4: Use the rotation matrix R and translation matrix T to correct the position of p and obtain a new corresponding point set p'={Rp'+t,p'∈p};

[0134] Step 6.5.4.5: Use formula (13) to calculate the average distance d between p' and the corresponding point set q;

[0135] Step 6.5.4.6: If d is less than the given distance threshold or the number of iterations reaches the preset maximum value, the iteration stops, and the calculated rotation matrix and translation matrix can realize the point cloud position calibration, otherwise return to step 6.5.4.2 until the stopping condition is met.

[0136] Step 7: Match the incomplete transmission tower with the constructed standard model library, place the matched model in the scene, and achieve complete point cloud reconstruction. Step 7 specifically includes:

[0137] Step 7.1: matching the incomplete transmission tower extracted after the point cloud segmentation with the three-dimensional model of the transmission tower in the standard library model;

[0138] Step 7.2: Place the successfully matched 3D model in the scene to achieve 3D model reconstruction of the UHV transmission and transformation line.

[0139] In practical applications, the ICP algorithm is used to solve the conversion matrix from the standard model library to the device point cloud, and the corresponding model in the model library is placed at the corresponding position of the device point cloud, thereby realizing the construction of a complete three-dimensional scene model of the ultra-high voltage transmission and transformation line.

[0140] Embodiment 2

[0141] Reference Figure 3 Based on the same inventive concept as in the first embodiment, a three-dimensional reconstruction system for ultra-high voltage transmission and transformation lines is provided, comprising:

[0142] The data acquisition module is used to place a laser radar along the UHV transmission and transformation line to obtain the point cloud data of the UHV transmission and transformation line, and to place an RTK positioning software at the laser radar and the selected reference point to obtain the longitude and latitude high coordinate data;

[0143] A correction module is used to correct the acquired point cloud data and longitude and latitude coordinate data of the ultra-high voltage transmission and transformation line to obtain a transformation matrix for posture correction; wherein each coordinate point in the point cloud image along the ultra-high voltage transmission and transformation line is mapped to the earth-centered earth-fixed coordinate system after coordinate transformation to obtain an absolute coordinate value;

[0144] The filtering module is used to filter the corrected UHV transmission and transformation line point cloud data to remove noise points, avoid the problem of excessive details being deleted by mistake and insufficient high-density compression due to uneven distribution of point cloud data, and obtain filtered point cloud data;

[0145] The splicing module is used to splice the filtered point cloud data of the UHV transmission and transformation line to build a preliminary reconstruction model;

[0146] A point cloud segmentation module, used to perform point cloud segmentation on the preliminary reconstruction model using a region growing algorithm, and extract the incomplete transmission tower point cloud therein;

[0147] The standard library module is used to obtain the 3D models of different types of transmission towers and build a standard model library;

[0148] The matching module is used to match the incomplete point cloud of the transmission tower with the constructed standard model library, place the matched 3D model in the scene, and realize complete point cloud reconstruction.

[0149] It should be noted that each module in the system realizes the functions and technical effects corresponding to each step in the method of Example 1, which will not be elaborated here.

[0150] Embodiment 3

[0151] Based on the same inventive concept as that of the first embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines provided in the embodiment of the present invention is implemented. Based on such an understanding, the technical solution of this embodiment, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0152] Embodiment 4

[0153] Based on the same inventive concept as that of the first embodiment, an electronic device is provided, including a memory and a processor, wherein the memory stores computer instructions that can be executed on the processor, and when the processor executes the computer instructions, the three-dimensional reconstruction method of the ultra-high voltage transmission and transformation line provided in the embodiment of the present invention is executed.

[0154] The processor may be a single-core or multi-core central processing unit or a specific integrated circuit, or one or more integrated circuits configured to implement the present invention.

[0155] Embodiments of the subject matter and functional operations described in this specification may be implemented in: tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagated signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode and transmit information to a suitable receiver device for execution by the data processing device.

[0156] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuits, such as FPGAs (field programmable gate arrays) or ASICs (application-specific integrated circuits), and the apparatus can also be implemented as special purpose logic circuits.

[0157] Processors suitable for executing computer programs include, for example, general and / or special microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, the computer will also include one or more large-capacity storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or the computer will be operably coupled to this large-capacity storage device to receive data from it or to transmit data to it, or both. However, the computer does not necessarily have such a device. In addition, the computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, just to name a few.

[0158] It should be understood that each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] The above specific implementation methods are detailed descriptions of the present invention. It cannot be determined that the specific implementation methods of the present invention are limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions and substitutions can be made without departing from the concept of the present invention, which should be regarded as belonging to the protection scope of the present invention.

Claims

1. A method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines, characterized in that: The following steps are involved: S1. Place a laser radar along the UHV transmission and transformation line to obtain point cloud data of the UHV transmission and transformation line, and place RTK positioning software at the laser radar and the selected reference point to obtain longitude and latitude high coordinate data; S2, correcting the acquired point cloud data and longitude and latitude high coordinate data of the UHV transmission and transformation line to obtain a transformation matrix for posture correction; S3, filtering the corrected point cloud data of the UHV transmission and transformation line; S4, splicing the filtered UHV transmission and transformation line point cloud data to build a preliminary reconstruction model; S5. Use a region growing algorithm to perform point cloud segmentation on the preliminary reconstruction model to extract the incomplete transmission tower point cloud; S6. Obtain the three-dimensional models of different types of transmission towers required and build a standard model library; S7. Match the incomplete point cloud of the transmission tower with the constructed standard model library, place the matched three-dimensional model in the scene, and achieve complete point cloud reconstruction.

2. A method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines according to claim 1, characterized in that: The step S1 specifically includes: Select the location for placing the laser radar according to the actual scene, adjust the laser radar posture, ensure that the entire transmission tower point cloud can be obtained from the current viewing angle, and record the initial posture angle of the laser radar at this time; Place four different reference points in the laser radar measurement scene, and use RTK positioning software to obtain the longitude and latitude coordinate data at the laser radar and the reference points, wherein the longitude and latitude coordinate data includes longitude, latitude and elevation information; Place laser radars along the UHV transmission and transformation lines to obtain point clouds, ensuring that the point clouds taken by adjacent laser radars have a certain degree of overlap.

3. A method for 3D reconstruction of UHV power transmission and transformation lines according to claim 2, characterized in that: The step S2 specifically includes: Fine-tune the initial attitude angle of the laser radar to find the minimum error; The longitude and latitude high-coordinate data are converted to the Earth-centered Earth-fixed coordinate system through coordinate transformation; The conversion process between the radar coordinate system and the Earth-centered Earth-fixed coordinate system is regarded as a linear process, and a linear model is established; The total least squares estimation method is used to solve the parameters in the linear model, obtain the transformation matrix between the coordinate systems, and achieve preliminary posture correction; A reference point is randomly selected from the corrected point cloud data, and the parameters are estimated again according to the Earth-centered Earth-fixed coordinates of the reference point to optimize the linear model.

4. The method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines according to claim 1, characterized in that: The step S3 specifically includes: The point cloud data of UHV transmission and transformation lines are filtered using the straight-through filter and adaptive density voxel filtering algorithm.

5. The method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines according to claim 1, characterized in that: The step S4 specifically includes: Take the center point of the laser radar lens as the origin and establish the point cloud coordinate system; Taking the center of the earth as the origin, establish the Earth-centered Earth-fixed coordinate system; Mapping each coordinate point in the point cloud image of different sections of the UHV transmission and transformation line to each coordinate point of the Earth-centered Earth-fixed coordinate system after coordinate conversion to obtain an absolute coordinate value; The mapped point cloud images of the ultra-high voltage transmission and transformation lines under each section are spliced ​​to obtain a preliminary three-dimensional reconstruction model.

6. The method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines according to claim 1, characterized in that: The step S5 specifically includes: The normal vectors of all data points are calculated by a local surface fitting algorithm, and their curvature values ​​are estimated at the same time; All data points are input into the empty queue in ascending order according to the curvature value in their local range, and the minimum curvature point is taken from the queue and added to the seed point set; Search for neighboring points of the current seed point. If the angle between the normal of the neighboring point and the normal of the current seed point is less than the set threshold, and the curvature value of these neighboring points is also less than the set threshold, then these neighboring points will be added to the seed point sequence, and then the current seed point will be removed, and then the new seed point will continue to grow; Repeat the above process until all seed points have been processed.

7. The method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines according to claim 1, characterized in that: The step S7 specifically includes: Use the ICP registration algorithm to match the incomplete transmission tower after point cloud segmentation with the three-dimensional model of the transmission tower in the standard library model; The successfully matched 3D model is placed in the scene to realize the 3D model reconstruction of the UHV transmission and transformation line.

8. A three-dimensional reconstruction system for ultra-high voltage transmission and transformation lines, characterized in that: include: The data acquisition module is used to place a laser radar along the UHV transmission and transformation line to obtain the point cloud data of the UHV transmission and transformation line, and to place an RTK positioning software at the laser radar and the selected reference point to obtain the longitude and latitude high coordinate data; The correction module is used to correct the acquired point cloud data and longitude and latitude high coordinate data of the UHV transmission and transformation line to obtain the transformation matrix of posture correction; A filtering module is used to filter the corrected point cloud data of the UHV transmission and transformation line; The splicing module is used to splice the filtered point cloud data of the UHV transmission and transformation line to build a preliminary reconstruction model; A point cloud segmentation module, used to perform point cloud segmentation on the preliminary reconstruction model using a region growing algorithm, and extract the incomplete transmission tower point cloud therein; The standard library module is used to obtain the 3D models of different types of transmission towers and build a standard model library; The matching module is used to match the incomplete point cloud of the transmission tower with the constructed standard model library, place the matched 3D model in the scene, and realize complete point cloud reconstruction.

9. An electronic device comprising a memory and a processor, wherein the memory stores computer instructions that can be executed on the processor, wherein: When the processor runs the computer instructions, it executes the three-dimensional reconstruction method of the ultra-high voltage transmission and transformation line described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for three-dimensional reconstruction of ultra-high voltage transmission and transformation lines described in any one of claims 1 to 7 is implemented.

Images