A method, apparatus, device, and storage medium for verifying parameterized tower models.

Abstract

This application discloses a parametric tower model verification method, apparatus, device, and storage medium, relating to the technical fields of computer software and remote sensing data processing. The method includes: acquiring laser point cloud data of transmission lines; locating high-voltage towers based on the laser point cloud data of the transmission lines; extracting high-voltage tower point cloud data from the laser point cloud data of the transmission lines according to the high-voltage tower location results; performing three-dimensional modeling of the high-voltage tower based on the high-voltage tower point cloud data to obtain a high-voltage tower model; and verifying the high-voltage tower model. This application provides more accurate tower model identification based on point cloud data, more timely laser point cloud data, and more accurate latitude and longitude information (i.e., location information) of the tower locations.

Description

Technical Field

[0001] This application relates to the technical fields of computer software and remote sensing data processing, and specifically to a parametric tower model verification method, device, equipment, and storage medium. Background Technology

[0002] With the vigorous advancement of power grid digitalization, digital display, digital operation and maintenance, and digital decision-making in power grid production and operation are becoming increasingly important. Currently, a parametric modeling scheme with semi-automated assembly and semi-manual intervention is used to achieve 3D visualization of power grid transmission lines. This scheme can quickly and in batches construct power elements such as transmission line towers, conductors, ground wires, and insulator strings. However, many problems still exist, the most significant of which are errors in tower type and inaccurate tower coordinates. In the parametric modeling scheme, the tower type of a line is fixed to a single model, which often differs from the actual tower type. At the same time, the tower coordinates are often inaccurate due to untimely updates of tower coordinate information. Summary of the Invention

[0003] To address the problems of incorrect tower type and inaccurate tower coordinates in existing parametric modeling techniques, this application proposes a parametric tower model verification method, apparatus, equipment, and storage medium.

[0004] This application is achieved through the following technical solution:

[0005] A method for verifying a parametric tower model includes:

[0006] Acquire laser point cloud data of power transmission lines;

[0007] Based on the laser point cloud data of the transmission line, the high-voltage tower is located;

[0008] Based on the high-voltage tower positioning results, high-voltage tower point cloud data is extracted from the laser point cloud data of the transmission line.

[0009] Based on the point cloud data of the high-voltage tower, a three-dimensional model of the high-voltage tower is performed to obtain the high-voltage tower model;

[0010] The high-voltage tower model was verified.

[0011] In some embodiments, the high-voltage tower positioning based on the laser point cloud data of the transmission line includes:

[0012] The laser point cloud data of the power transmission line is divided into grids;

[0013] The first type of point cloud data is filtered out based on the relative height threshold of the grid.

[0014] The second type of point cloud data is filtered out based on the porosity threshold of the grid point cloud; wherein the porosity of the grid point cloud is the ratio of the total grid gap to the relative height of the grid.

[0015] The region growing algorithm is used to cluster adjacent grids, and the area and length of each cluster of point cloud data are calculated.

[0016] By filtering out categories that do not meet the requirements using length and area thresholds, coarse high-voltage tower point cloud data is obtained.

[0017] Based on the coarse high-voltage tower point cloud data, a fitting algorithm is used to extract the linear relationship between the height and side length or diagonal length of the high-voltage tower to separate the point cloud data of the main area of ​​the tower.

[0018] The point cloud data of the main area of ​​the tower is divided into layers, and the average value of the center position of the tower in each layer is calculated. This average value is taken as the center position of the high voltage tower, and the average value of the elevation values ​​of the lowest and highest points is taken as the height of the tower center.

[0019] In some embodiments, the extraction of high-voltage tower point cloud data from the laser point cloud data of the transmission line includes:

[0020] The laser point cloud data of the transmission line is preprocessed;

[0021] Based on the spatial geometric features of the towers, the layered point cloud data of the main tower section is extracted from the preprocessed laser point cloud of the transmission line.

[0022] Based on the layered point cloud data of the main tower section, fine extraction of tower point cloud is performed.

[0023] In some embodiments, the extraction of tower trunk layered point cloud data from the preprocessed transmission line laser point cloud includes:

[0024] The preprocessed laser point cloud data of the transmission line is divided into grids.

[0025] The first type of point cloud data is filtered out based on the relative height threshold of the grid.

[0026] The second type of point cloud data is filtered out based on the porosity threshold of the grid point cloud; wherein the porosity of the grid point cloud is the ratio of the total grid gap to the relative height of the grid.

[0027] The region growing algorithm is used to cluster adjacent grids, and the area and length of each cluster of point cloud data are calculated.

[0028] By filtering out categories that do not meet the requirements using length and area thresholds, coarse high-voltage tower point cloud data is obtained.

[0029] Based on the coarse high-voltage tower point cloud data, a fitting algorithm is used to extract the linear relationship between the height and side length or diagonal length of the high-voltage tower to separate the point cloud data of the main area of ​​the tower.

[0030] The point cloud data of the main area of ​​the tower is divided into layers to obtain the layered point cloud data of the main area of ​​the tower.

[0031] In some implementations, the refinement of tower point cloud based on the layered point cloud data of the tower backbone includes:

[0032] The corner coordinates of the stratified point cloud data of the main tower area are extracted based on coordinate system rotation, and a fitting algorithm is used to fit spatial straight lines to obtain the edge line of the main tower area.

[0033] The point cloud data of the high-voltage tower is obtained by refining the point cloud data of the tower by using the ridge line of the main area of ​​the tower.

[0034] In some implementations, the three-dimensional modeling of high-voltage towers includes:

[0035] Based on the high-voltage tower point cloud data, the high-voltage tower is redirected and the high-voltage tower point cloud data in the redirected coordinate system is calculated.

[0036] The high-voltage tower point cloud data in the redirected coordinate system is decomposed into point cloud data of inverted triangular pyramid structure, point cloud data of square frustum structure, and point cloud data of crossarm structure.

[0037] Based on the point cloud data of the inverted triangular pyramid structure, the point cloud data of the frustum structure, and the point cloud data of the crossarm structure, the inverted triangular pyramid structure model, the frustum structure model, and the crossarm structure model are reconstructed respectively.

[0038] The reconstructed inverted triangular pyramid structure model, truncated square structure model, and crossarm structure model are assembled to obtain the high-voltage tower model.

[0039] In some embodiments, the reconstruction of the inverted triangular pyramid structure model, the frustum structure model, and the crossbeam structure model includes:

[0040] The reconstruction of the inverted triangular pyramid structure model first involves projecting the point cloud data of the inverted triangular pyramid structure onto the X'Z' plane and Y'Z' plane under the redirected coordinate system X'Y'Z', and then extracting the left and right edge points.

[0041] Based on the left and right edge points, a fitting algorithm is used to obtain the edge lines;

[0042] The three-dimensional coordinates of the eight vertices are determined based on the division position and the Z' coordinate of the lowest point, and then connected according to their topological relationship to form a three-dimensional model, thus obtaining the inverted triangular pyramid structure model.

[0043] And / or, the reconstruction of the quadrangular frustum structure model first involves projecting the quadrangular frustum structure point cloud data onto the X'Z' plane and Y'Z' plane under the redirected coordinate system X'Y'Z', and extracting the left and right boundary points;

[0044] The boundary is obtained by fitting the left and right boundary points using a fitting algorithm;

[0045] The three-dimensional coordinates of the eight vertices are determined based on the Z' coordinate of the segmentation position, and then connected according to their topological relationship to form a three-dimensional model, thus obtaining the quadrangular frustum structure model.

[0046] And / or, the reconstruction of the crossarm structure model first establishes an abstract template structure based on the crossarm type of the tower.

[0047] The topological relationships between connection points are determined based on the abstract template structure.

[0048] Project the point cloud data of the crossarm structure onto the Y'Z' plane under the redirected coordinate system X'Y'Z';

[0049] A two-dimensional contour extraction algorithm is used to extract the contour, and the Y' and Z' coordinates of the contour corner points are obtained;

[0050] Project the point cloud data of the crossarm structure onto the X'Y' plane under the redirected coordinate system X'Y'Z';

[0051] A two-dimensional contour extraction algorithm is used to extract the contour, and an ensemble algorithm is used to fit the linear equation.

[0052] Based on the Y' coordinates of the corner points, determine their X' coordinates using the fitted line equations.

[0053] The crossarm structure model is obtained by connecting the corner points according to the topological relationship determined by the abstract template.

[0054] Secondly, this application proposes a parameterized tower model verification device, comprising:

[0055] The data acquisition unit is configured to acquire laser point cloud data of the transmission line;

[0056] The positioning unit is configured to: locate high-voltage towers based on the laser point cloud data of the transmission line;

[0057] The extraction unit is configured to: extract high-voltage tower point cloud data from the laser point cloud data of the transmission line based on the high-voltage tower positioning results;

[0058] The modeling unit is configured to perform three-dimensional modeling of the high-voltage tower based on the high-voltage tower point cloud data, and obtain a high-voltage tower model.

[0059] In addition, the verification unit is configured to verify the high-voltage tower model.

[0060] Thirdly, this application proposes an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above-described embodiments of the parameterized tower model verification method.

[0061] Fourthly, this application proposes a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements any of the above-described embodiments of the parameterized tower model verification method.

[0062] This application proposes a parametric tower model verification method. The tower model identification based on point cloud data is more accurate, and the timeliness of laser point cloud data ensures more accurate latitude and longitude information (i.e., location information) of the tower points. Furthermore, the parametric tower model verification for transmission lines based on laser point cloud data is faster, and obtaining tower type information through the acquisition and processing of laser point cloud data is quicker and more convenient than actual field surveys.

[0063] Accordingly, the parametric tower model verification device, equipment, and computer-readable storage medium proposed in this application also possess the same technical effects as described above. Attached Figure Description

[0064] The accompanying drawings, which are included to provide a further understanding of the embodiments of this application and form part of this application, do not constitute a limitation on the embodiments of this application. In the drawings:

[0065] Figure 1 This is a flowchart of the verification method proposed in the embodiments of this application;

[0066] Figure 2 This is a flowchart illustrating the positioning process of high-voltage towers according to an embodiment of this application.

[0067] Figure 3 This is the laser point cloud classification data for power transmission lines in this application embodiment;

[0068] Figure 4 This refers to the point cloud data of the main pole area in this application embodiment;

[0069] Figure 5 The above are the point cloud data of high-voltage towers before and after noise reduction in the embodiments of this application;

[0070] Figure 6 The point cloud data of each layer conforming to the optimal straight line model in the embodiments of this application;

[0071] Figure 7 The extracted tower point cloud data is generated for the model in the embodiments of this application;

[0072] Figure 8 This is a flowchart illustrating the tower modeling process according to an embodiment of this application.

[0073] Figure 9 This is a projection view of the redirected high-voltage tower in the Y′Z′ plane according to an embodiment of this application;

[0074] Figure 10 This is a schematic diagram illustrating the fill rate definition in an embodiment of this application;

[0075] Figure 11 This is the result of high-voltage tower segmentation in an embodiment of this application;

[0076] Figure 12 The inverted triangular pyramid structure model reconstructed for the embodiments of this application;

[0077] Figure 13 This is a schematic diagram of the abstract template structure of an embodiment of this application;

[0078] Figure 14 The high-voltage tower model reconstructed according to the embodiments of this application;

[0079] Figure 15 This is a block diagram illustrating the principle of the verification device proposed in the embodiments of this application;

[0080] Figure 16 This is a schematic diagram of the verification system architecture proposed in an embodiment of this application;

[0081] Figure 17 This is a schematic diagram of the electronic device proposed in the embodiments of this application;

[0082] Figure 18 This is a schematic diagram of a computer-readable storage medium proposed in an embodiment of this application;

[0083] Figure reference numerals and corresponding component names:

[0084] 200-Verification device, 201-Data acquisition unit, 202-Positioning unit, 203-Extraction unit, 204-Modeling unit, 205-Verification unit, 300-Verification system, 301-Input device, 302-Output device, 303-Processor A, 304-Memory A, 400-Electronic device, 410-Memory B, 420-Processor B, 411-Computer program A, 500-Computer-readable storage medium, 511-Computer program B. Detailed Implementation

[0085] In the following, the terms “comprising” or “may include” as used in the various embodiments of this application indicate the presence of a function, operation, or element of the invention and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in the various embodiments of this application, the terms “comprising,” “having,” and their cognates are intended only to indicate a specific feature, number, step, operation, element, component, or combination of the foregoing and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or adding one or more combinations of the foregoing.

[0086] In various embodiments of this application, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.

[0087] The terms used in the various embodiments of this application (such as "first," "second," etc.) may modify various constituent elements in the various embodiments, but do not limit the corresponding constituent elements. For example, the above terms do not limit the order and / or importance of the elements. The above terms are only used for the purpose of distinguishing one element from other elements. For example, a first user device and a second user device refer to different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of this application, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element.

[0088] It should be noted that if a description is made of "connecting" one component to another, then the first component can be directly connected to the second component, and a third component can be "connected" between the first and second components. Conversely, when a component is "directly connected" to another component, it can be understood that there is no third component between the first and second components.

[0089] The terminology used in the various embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the various embodiments of this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. The terms (such as those defined in a generally used dictionary) are to be interpreted as having the same meaning as in the context of the relevant technical field and are not to be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0090] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the embodiments and accompanying drawings. The illustrative embodiments and descriptions of this application are only for explaining this application and are not intended to limit this application.

[0091] In existing parametric modeling techniques, there are often discrepancies between the tower type and the actual tower type, and the tower coordinates also suffer from inaccurate positioning. To address this, this application presents a parametric tower model verification method. This method, based on 3D modeling of transmission line corridor laser point clouds, provides more accurate tower model identification, and the timeliness of the laser point cloud data ensures more accurate latitude and longitude information for the tower locations.

[0092] like Figure 1 As shown, the method proposed in this application includes the following steps:

[0093] Step 110: Obtain laser point cloud data of the transmission line;

[0094] Step 120: Locate high-voltage towers based on laser point cloud data of transmission lines;

[0095] Step 130: Based on the high-voltage tower positioning results, extract the high-voltage tower point cloud data from the transmission line laser point cloud data;

[0096] Step 140: Based on the point cloud data of the high-voltage tower, perform 3D modeling of the high-voltage tower to obtain the high-voltage tower model;

[0097] Step 150: Verify the high-voltage tower model.

[0098] Furthermore, in step 110 of this embodiment, an airborne lidar can be used to scan the high-voltage transmission line corridor to obtain laser point cloud data of the transmission line. After obtaining the laser point cloud data of the transmission line, in order to reduce data overlap, anomalies, and errors caused by acquisition equipment, strip scanning, or other reasons during data acquisition, according to the common processing flow, it is necessary to first correct it using marker points or reference points to eliminate point coordinate defects, and then fuse it according to the same ground feature points. The complete line tower point cloud is obtained from multiple scan strips and finally reprojected to facilitate the subsequent calculation of related spatial geometric positions.

[0099] Furthermore, step 120 of this embodiment, based on the local spatial distribution characteristics of various objects in the laser point cloud data of the transmission line and the spatial geometric characteristics of the high-voltage towers, uses a region growing algorithm and the RANSAC (Random Sample Consensus) algorithm to achieve precise positioning of the high-voltage towers. The specific process is as follows: Figure 2 As shown:

[0100] Step 121: Use the region growing algorithm to coarsely extract the point cloud of high-voltage towers.

[0101] The high-voltage transmission corridor mainly includes high-voltage lines, high-voltage towers, vegetation, ground, buildings, roads, rivers, and other natural and man-made structures. The laser point cloud data obtained by airborne lidar is vertically projected onto a horizontal plane. The local area (such as a 2m×2m grid) can be divided into three types of point cloud data: (1) surface point cloud (mixed point cloud of ground, vegetation, buildings, roads, etc.); (2) mixed point cloud of ground to high-voltage lines; and (3) mixed point cloud of ground and towers.

[0102] By analyzing the spatial distribution characteristics of point clouds for each category, such as Figure 3 As shown (where 1 represents the first type of point cloud data, 2 represents the second type of point cloud data, and 3 represents the third type of point cloud data), the following differences can be observed:

[0103] (1) The first type of local point cloud data is continuous in vertical space distribution, while the point cloud data of some high vegetation areas have gaps in the vertical direction.

[0104] (2) The relative height (elevation difference between the highest and lowest points in the grid) of the point cloud data of individual grids in the first and second categories, and the first and third categories, are quite different;

[0105] (3) The point cloud of the second type of grid is represented as a linear point cloud with a certain spatial interval.

[0106] To address the relative height differences in spatial characteristics between the first and third types of point cloud grids, and the spatial continuity differences between the second and third types of point cloud grids, most of the first and second types of grids can be filtered out by setting thresholds for grid relative height and grid point cloud porosity (the ratio of the total grid gap to the grid relative height). Then, adjacent grids can be clustered through region growing, and the area and length of each type of point cloud data can be statistically analyzed. By removing categories that do not meet the requirements through appropriate thresholds, independent coarse high-voltage tower point cloud data can be obtained.

[0107] Based on this, the specific implementation process of step 121 includes: dividing the original point cloud data into grids, then filtering out the first type of point cloud data according to the grid relative height threshold, then filtering out the second type of point cloud data according to the grid point cloud porosity threshold, then clustering adjacent grids through region growth, and calculating the area and length of each type of point cloud data obtained from the clustering, filtering out categories that do not meet the requirements through length thresholds and area thresholds, thus obtaining the coarse high-voltage tower point cloud data.

[0108] Step 122: Determine the center position of the high-voltage tower based on the spatial geometric features of the tower and the fitting algorithm.

[0109] High-voltage towers are symmetrical about their central axis, such as... Figure 4 As shown, the main trunk area is approximately a regular square pyramid frustum with a rectangular cross-section. The lateral and diagonal faces are approximately isosceles trapezoids, with a linear relationship between the side length and the diagonal length. This embodiment uses the RANSAC algorithm to extract the linear relationship between the tower height and the side length or diagonal length to separate the main trunk area. Then, the main trunk area is divided into layers, and the average value of the center position of each layer is calculated and used as the center position of the high-voltage tower. The average elevation values ​​of the lowest and highest points are taken as the height of the tower center.

[0110] Furthermore, in step 130 of this embodiment, based on the spatial geometric features and point cloud distribution characteristics of the high-voltage tower and surrounding terrain features, high-precision extraction of the tower point cloud is achieved using planar grid neighborhood clustering, kd-tree (k-dimensional tree) neighborhood clustering, spatial grid region growing, RANSAC linear fitting, and model growing methods. The specific process is as follows:

[0111] Step 131: Preprocess the laser point cloud data of the transmission line.

[0112] Due to system or equipment errors, diffuse reflection in the propagation space, and the inherent properties of ground features, airborne lidar scanning data contains noise, such as... Figure 5 As shown in the left-middle figure. Therefore, this embodiment of the application uses the kd-tree neighborhood clustering algorithm to filter out noise points in the original point cloud data, retaining the data of the class with the largest amount of point cloud data as the denoised point cloud data, such as... Figure 5 As shown in the middle right figure.

[0113] Step 132: Based on the spatial geometric features of the tower, extract the layered point cloud data of the main tower section from the preprocessed laser point cloud of the transmission line.

[0114] The main trunk of the tower exhibits distinct geometric features and point cloud aggregation characteristics. Based on the overall tower positioning data, the tower's center position is selected. Using this center, a rough outline of the main structure can be determined. Then, the edge morphology of the main trunk is constructed based on the geometric features. Step 132 is similar to step 120 (the tower positioning process) above. First, coarse extraction is performed. Then, the RANSAC algorithm is used to extract the linear relationship between the tower's height and side length or diagonal length to separate the main trunk region. The main trunk region is then layered to obtain layered point cloud data for the main trunk region. The extracted point clouds of each layer of the main trunk region are shown below. Figure 6 As shown.

[0115] Step 133: Based on the layered point cloud data of the main tower section, perform fine extraction of the tower point cloud data.

[0116] Corner coordinates of the stratified point cloud data of the main tower area are extracted based on coordinate system rotation, and spatial straight line fitting is performed using the RANSAC algorithm to obtain the edge line of the main tower area. The point cloud data of the main tower area is then refined using the edge line, resulting in the following: Figure 7 The image shows point cloud data of high-voltage towers.

[0117] Furthermore, in step 140 of this embodiment, the overall structure of the high-voltage tower is divided into three parts: an inverted triangular pyramid structure, a truncated square structure, and a crossarm structure. Different modeling strategies are adopted for different structures, as detailed in the following process. Figure 8 As shown:

[0118] Step 141: Based on the high-voltage tower point cloud data, perform high-voltage tower redirection and calculate the high-voltage tower point cloud data in the redirected coordinate system.

[0119] The high-voltage tower point cloud data extracted from transmission line laser point cloud data is oriented arbitrarily in the XY plane. To fully utilize the symmetry of the high-voltage tower structure, it needs to be redirected. The high-voltage tower point cloud data is projected onto the XY plane, and the eigenvalues ​​and eigenvectors are calculated using the PCA (Principal Component Analysis) algorithm. The X' axis after redirection represents the eigenvector corresponding to the smallest eigenvalue. Finally, the rotation angle is calculated using equation (1). And the repositioned point coordinates. The repositioned high-voltage tower in the Y'Z' projection view is as follows. Figure 9 As shown.

[0120] (1)

[0121] in, These are the projected coordinates of the high-voltage tower point cloud data on the original XY plane. These are the projection coordinates of the redirected high-voltage tower point cloud data onto the redirected XY plane.

[0122] It should be noted that the original XYZ coordinate system in this application embodiment is a geographic coordinate system, that is, a spatial reference coordinate system that uses latitude and longitude coordinates to represent the location of any point on the Earth's surface. Due to the influence of the Earth's curvature, it cannot be directly used for accurate distance calculation. It is necessary to perform a common projection coordinate system transformation and use the projection coordinate system to represent the coordinates of the data points for accurate distance calculation. After the projection transformation, it is then redirected. The redirected X'Y'Z' coordinate system is a coordinate system with the axis of symmetry of the tower as the coordinate axis. According to the axisymmetric characteristics of the tower, the direction where the crossarm of the tower is located is generally chosen as the direction of the X' axis, and the direction perpendicular to the crossarm is chosen as the direction of the Y' axis, or they can be interchanged. Z' is the vertical direction.

[0123] Step 142 involves decomposing the high-voltage tower point cloud data in the repositioned coordinate system into point cloud data for an inverted triangular pyramid structure, a frustum structure, and a crossarm structure. It should be noted that the crossarm structure has multiple layers and can also be considered a complex structure.

[0124] Step 142 uses fill rate to decompose the high-voltage tower point cloud data. The fill rate is defined as follows: Figure 10 As shown, this refers to a fixed length along the Y' axis within a unit space. The data is divided into multiple continuous spaces, and the number or density of points in each space is counted to measure the number of points per unit space. If the fill rate is greater than a preset threshold, it is considered a segmentation location. The tower point cloud data is then decomposed using these segmentation locations as boundaries. The decomposition results are as follows: Figure 11 As shown.

[0125] Step 143: Perform block reconstruction based on the decomposed high-voltage tower point cloud data.

[0126] (1) Reconstruction of the inverted triangular pyramid structure: First, project the point cloud of this part onto the X'Z' plane and the Y'Z' plane respectively, and extract the left and right edge points. Then, fit a straight line based on the RANSAC algorithm. Finally, based on the segmentation location and the Z' coordinate of the lowest point, the eight vertices (i.e., The 3D coordinates of () are connected according to their topological relationships to form a 3D model, resulting in, as follows: Figure 12 The inverted triangular pyramid structure model shown in the figure is composed of four triangular pyramids of equal height, and the bases of the four triangular pyramids ( ) are coplanar, forming a plane ( Then invert it to form an inverted triangular pyramid structure.

[0127] (2) Reconstruction of the quadrangular frustum structure: The quadrangular frustum structure is a reconstruction of the tower frame. First, the point cloud of this part is projected onto the X'Z' plane and the Y'Z' plane respectively, and the left and right boundary points are extracted. Then, a straight line is fitted based on the RANSAC algorithm. Finally, the 3D coordinates of the 8 vertices are determined according to the Z' coordinates of the segmentation position, and connected into a 3D model according to their topological relationship to obtain the quadrangular frustum structure model.

[0128] (3) Reconstruction of the crossarm structure: Based on the crossarm type of the tower, an abstract template structure is established, such as... Figure 13 As shown, the topological relationships between connection points are determined based on an abstract template structure. Then, the point cloud data of the crossarm structure is projected onto the Y'Z' plane, using a 2D Alpha-shape (two-dimensional) model. The contour is extracted using a shape-based algorithm, and the Y' and Z' coordinates of the contour corner points are obtained using the Douglas-Peucker algorithm. Next, the point cloud data is projected onto the X'Y' plane, and the contour is obtained using the 2D Alpha-shape algorithm. The RANSAC algorithm is then used to fit the linear equations, and the X' coordinates of the corner points are determined based on the linear equations according to their Y' coordinates. Finally, the corner points are connected according to the topological relationships determined by the abstract template to obtain the crossarm structure model.

[0129] Step 144: Assemble the model to obtain the high-voltage tower model.

[0130] The inverted triangular pyramid structure model, the square frustum structure model, and the crossarm structure model are combined to obtain the final high-voltage tower model, such as... Figure 14 As shown, Figure 14 The reconstruction effect diagrams of different tower types are shown, where (a), (b), (c), and (d) are drum-shaped tower, gan-shaped tower, gan-shaped tower, and ram's horn tower, respectively.

[0131] Furthermore, in step 150 of this embodiment, the verification of the high-voltage tower model includes coordinate verification and tower type verification. Coordinate verification involves matching the coordinates in the three-dimensional tower model with the tower coordinates extracted from the point cloud to determine that the coordinate information of the tower model is correct. Tower type verification involves verifying the tower type of the three-dimensional tower model obtained after laser point cloud tower reconstruction using this technology to ensure that the tower type of the three-dimensional model is correct.

[0132] Based on the same technical concept described above, this application also proposes a parameterized tower model verification device, such as... Figure 15 As shown, the verification device 200 includes:

[0133] The data acquisition unit 201 is configured to acquire laser point cloud data of the transmission line. The specific method for acquiring point cloud data is as described in step 110 above, and will not be repeated here.

[0134] Positioning unit 202 is configured to locate high-voltage towers based on laser point cloud data of transmission lines. The specific high-voltage tower positioning process is as described in step 120 above, and will not be repeated here.

[0135] Extraction unit 203 is configured to extract high-voltage tower point cloud data from the laser point cloud data of the transmission line based on the high-voltage tower positioning results. The specific data extraction process is as described in step 130 above, and will not be repeated here.

[0136] Modeling unit 204 is configured to perform 3D modeling of high-voltage towers based on point cloud data, thereby obtaining a high-voltage tower model. The specific modeling process is as described in step 140 above, and will not be repeated here.

[0137] Furthermore, the verification unit 205 is configured to verify the high-voltage tower model. The specific verification process is as described in step 150 above, and will not be repeated here.

[0138] Based on the same technical concept described above, this application also proposes a parameterized tower model verification system, such as... Figure 16 As shown, the verification system 300 proposed in this application includes:

[0139] The system comprises an input device 301, an output device 302, a processor A303, and a memory A304; wherein the number of processors A303 and memory A304 can be one or more. Figure 16 The following description uses a processor A303 and a memory A304 as an example. The input device 301, output device 302, processor A303, and memory A304 can be connected via a bus or other means. Figure 16 Taking the example of a connection between China and Israel via a bus.

[0140] Specifically, by calling the operation instructions stored in memory A304, processor A303 executes the following steps:

[0141] Acquire laser point cloud data of power transmission lines;

[0142] High-voltage tower positioning is performed based on laser point cloud data of transmission lines;

[0143] Based on the high-voltage tower positioning results, extract the high-voltage tower point cloud data from the transmission line laser point cloud data;

[0144] Based on the point cloud data of high-voltage towers, a 3D model of the high-voltage towers is obtained.

[0145] Verify the high-voltage tower model.

[0146] Optionally, by calling the operation instructions stored in memory A304, processor A303 is also used to execute any of the embodiments in the corresponding examples of the above verification method.

[0147] Based on the same technical concept described above, this application also proposes an electronic device, such as... Figure 17 As shown, the electronic device 400 includes: a memory B410, a processor B420, and a computer program A411 stored in the memory B410 and executable on the processor B420. When the processor B420 executes the computer program A411, it performs the following steps:

[0148] Acquire laser point cloud data of power transmission lines;

[0149] High-voltage tower positioning is performed based on laser point cloud data of transmission lines;

[0150] Based on the high-voltage tower positioning results, extract the high-voltage tower point cloud data from the transmission line laser point cloud data;

[0151] Based on the point cloud data of high-voltage towers, a 3D model of the high-voltage towers is obtained.

[0152] Verify the high-voltage tower model.

[0153] Optionally, when processor B420 executes computer program A411, it can implement any of the embodiments in the corresponding examples of the above verification method.

[0154] It should be noted that the electronic device proposed in this application embodiment is a device used to implement the above verification method. Therefore, based on the above verification method proposed in this application embodiment, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this application embodiment. Therefore, how the electronic device specifically implements the above verification method will not be described in detail here. Any electronic device used by those skilled in the art to implement the above verification method falls within the scope of protection of this application.

[0155] Based on the same technical concept described above, embodiments of this application also propose a computer-readable storage medium, such as... Figure 18 As shown, the computer-readable storage medium 500 stores a computer program B511, which, when executed by a processor, performs the following steps:

[0156] Acquire laser point cloud data of power transmission lines;

[0157] High-voltage tower positioning is performed based on laser point cloud data of transmission lines;

[0158] Based on the high-voltage tower positioning results, extract the high-voltage tower point cloud data from the transmission line laser point cloud data;

[0159] Based on the point cloud data of high-voltage towers, a 3D model of the high-voltage towers is obtained.

[0160] Verify the high-voltage tower model.

[0161] Optionally, when the computer program B511 is executed by the processor, it can implement any of the embodiments corresponding to the above verification method.

[0162] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0163] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0164] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0165] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0166] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0167] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above description is only a specific embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for verifying a parametric tower model, characterized in that, include: Acquire laser point cloud data of power transmission lines; Based on the laser point cloud data of the transmission line, the high-voltage tower is located; Based on the high-voltage tower positioning results, high-voltage tower point cloud data is extracted from the laser point cloud data of the transmission line. Based on the point cloud data of the high-voltage tower, a three-dimensional model of the high-voltage tower is performed to obtain the high-voltage tower model; The high-voltage tower model was verified. The aforementioned 3D modeling of high-voltage towers includes: Based on the high-voltage tower point cloud data, the high-voltage tower is redirected and the high-voltage tower point cloud data in the redirected coordinate system is calculated. The high-voltage tower point cloud data in the redirected coordinate system is decomposed into point cloud data of inverted triangular pyramid structure, point cloud data of square frustum structure, and point cloud data of crossarm structure. Based on the point cloud data of the inverted triangular pyramid structure, the point cloud data of the frustum structure, and the point cloud data of the crossarm structure, the inverted triangular pyramid structure model, the frustum structure model, and the crossarm structure model are reconstructed respectively. The reconstructed inverted triangular pyramid structure model, truncated square structure model, and crossarm structure model are assembled to obtain the high-voltage tower model; The reconstruction of the inverted triangular pyramid structure model, the square frustum structure model, and the crossbeam structure model includes: The reconstruction of the inverted triangular pyramid structure model first involves projecting the point cloud data of the inverted triangular pyramid structure onto the X'Z' plane and Y'Z' plane under the redirected coordinate system X'Y'Z', and then extracting the left and right edge points. Based on the left and right edge points, a fitting algorithm is used to obtain the edge lines; The three-dimensional coordinates of the eight vertices are determined based on the division position and the Z' coordinate of the lowest point, and then connected according to their topological relationship to form a three-dimensional model, thus obtaining the inverted triangular pyramid structure model. And / or, the reconstruction of the quadrangular frustum structure model first involves projecting the quadrangular frustum structure point cloud data onto the X'Z' plane and Y'Z' plane under the redirected coordinate system X'Y'Z', and extracting the left and right boundary points; The boundary is obtained by fitting the left and right boundary points using a fitting algorithm; The three-dimensional coordinates of the eight vertices are determined based on the Z' coordinate of the segmentation position, and then connected according to their topological relationship to form a three-dimensional model, thus obtaining the quadrangular frustum structure model. And / or, the reconstruction of the crossarm structure model first establishes an abstract template structure based on the crossarm type of the tower. The topological relationships between connection points are determined based on the abstract template structure. Project the point cloud data of the crossarm structure onto the Y'Z' plane under the redirected coordinate system X'Y'Z'; A two-dimensional contour extraction algorithm is used to extract the contour, and the Y' and Z' coordinates of the contour corner points are obtained; Project the point cloud data of the crossarm structure onto the X'Y' plane under the redirected coordinate system X'Y'Z'; A two-dimensional contour extraction algorithm is used to extract the contour, and an ensemble algorithm is used to fit the linear equation. Based on the Y' coordinates of the corner points, determine their X' coordinates using the fitted line equations. The crossarm structure model is obtained by connecting the corner points according to the topological relationship determined by the abstract template.

2. The method for verifying a parameterized tower model according to claim 1, characterized in that, The method of locating high-voltage towers based on the laser point cloud data of the transmission line includes: The laser point cloud data of the power transmission line is divided into grids; The first type of point cloud data is filtered out based on the relative height threshold of the grid. The second type of point cloud data is filtered out based on the porosity threshold of the grid point cloud; wherein the porosity of the grid point cloud is the ratio of the total grid gap to the relative height of the grid. The region growing algorithm is used to cluster adjacent grids, and the area and length of each cluster of point cloud data are calculated. By filtering out categories that do not meet the requirements using length and area thresholds, coarse high-voltage tower point cloud data is obtained. Based on the coarse high-voltage tower point cloud data, a fitting algorithm is used to extract the linear relationship between the height and side length or diagonal length of the high-voltage tower to separate the point cloud data of the main area of ​​the tower. The point cloud data of the main area of ​​the tower is divided into layers, and the average value of the center position of the tower in each layer is calculated. This average value is taken as the center position of the high voltage tower, and the average value of the elevation values ​​of the lowest and highest points is taken as the height of the tower center.

3. The method for verifying a parametric tower model according to claim 1, characterized in that, The extraction of high-voltage tower point cloud data from the laser point cloud data of the transmission line includes: The laser point cloud data of the transmission line is preprocessed; Based on the spatial geometric features of the towers, the layered point cloud data of the main tower section is extracted from the preprocessed laser point cloud of the transmission line. Based on the layered point cloud data of the main tower section, fine extraction of tower point cloud is performed.

4. The method for verifying a parametric tower model according to claim 3, characterized in that, The extraction of layered point cloud data for the main tower section from the preprocessed laser point cloud of the transmission line includes: The preprocessed laser point cloud data of the transmission line is divided into grids. The first type of point cloud data is filtered out based on the relative height threshold of the grid. The second type of point cloud data is filtered out based on the porosity threshold of the grid point cloud; wherein the porosity of the grid point cloud is the ratio of the total grid gap to the relative height of the grid. The region growing algorithm is used to cluster adjacent grids, and the area and length of each cluster of point cloud data are calculated. By filtering out categories that do not meet the requirements using length and area thresholds, coarse high-voltage tower point cloud data is obtained. Based on the coarse high-voltage tower point cloud data, a fitting algorithm is used to extract the linear relationship between the height and side length or diagonal length of the high-voltage tower to separate the point cloud data of the main area of ​​the tower. The point cloud data of the main area of ​​the tower is divided into layers to obtain the layered point cloud data of the main area of ​​the tower.

5. The method for verifying a parametric tower model according to claim 3, characterized in that, The aforementioned method of refining the tower point cloud based on the layered point cloud data of the tower backbone includes: The corner coordinates of the stratified point cloud data of the main tower area are extracted based on coordinate system rotation, and a fitting algorithm is used to fit spatial straight lines to obtain the edge line of the main tower area. The point cloud data of the high-voltage tower is obtained by refining the point cloud data of the tower by using the ridge line of the main area of ​​the tower.

6. A parametric tower model verification device, characterized in that, include: The data acquisition unit is configured to acquire laser point cloud data of the transmission line; The positioning unit is configured to: locate high-voltage towers based on the laser point cloud data of the transmission line; The extraction unit is configured to: extract high-voltage tower point cloud data from the laser point cloud data of the transmission line based on the high-voltage tower positioning results; The modeling unit is configured to perform three-dimensional modeling of the high-voltage tower based on the high-voltage tower point cloud data, and obtain a high-voltage tower model. And, the verification unit is configured to: verify the high-voltage tower model; The aforementioned 3D modeling of high-voltage towers includes: Based on the high-voltage tower point cloud data, the high-voltage tower is redirected and the high-voltage tower point cloud data in the redirected coordinate system is calculated. The high-voltage tower point cloud data in the redirected coordinate system is decomposed into point cloud data of inverted triangular pyramid structure, point cloud data of square frustum structure, and point cloud data of crossarm structure. Based on the point cloud data of the inverted triangular pyramid structure, the point cloud data of the frustum structure, and the point cloud data of the crossarm structure, the inverted triangular pyramid structure model, the frustum structure model, and the crossarm structure model are reconstructed respectively. The reconstructed inverted triangular pyramid structure model, truncated square structure model, and crossarm structure model are assembled to obtain the high-voltage tower model; The reconstruction of the inverted triangular pyramid structure model, the square frustum structure model, and the crossbeam structure model includes: The reconstruction of the inverted triangular pyramid structure model first involves projecting the point cloud data of the inverted triangular pyramid structure onto the X'Z' plane and Y'Z' plane under the redirected coordinate system X'Y'Z', and then extracting the left and right edge points. Based on the left and right edge points, a fitting algorithm is used to obtain the edge lines; The three-dimensional coordinates of the eight vertices are determined based on the division position and the Z' coordinate of the lowest point, and then connected according to their topological relationship to form a three-dimensional model, thus obtaining the inverted triangular pyramid structure model. And / or, the reconstruction of the quadrangular frustum structure model first involves projecting the quadrangular frustum structure point cloud data onto the X'Z' plane and Y'Z' plane under the redirected coordinate system X'Y'Z', and extracting the left and right boundary points; The boundary is obtained by fitting the left and right boundary points using a fitting algorithm; The three-dimensional coordinates of the eight vertices are determined based on the Z' coordinate of the segmentation position, and then connected according to their topological relationship to form a three-dimensional model, thus obtaining the quadrangular frustum structure model. And / or, the reconstruction of the crossarm structure model first establishes an abstract template structure based on the crossarm type of the tower. The topological relationships between connection points are determined based on the abstract template structure. Project the point cloud data of the crossarm structure onto the Y'Z' plane under the redirected coordinate system X'Y'Z'; A two-dimensional contour extraction algorithm is used to extract the contour, and the Y' and Z' coordinates of the contour corner points are obtained; Project the point cloud data of the crossarm structure onto the X'Y' plane under the redirected coordinate system X'Y'Z'; A two-dimensional contour extraction algorithm is used to extract the contour, and an ensemble algorithm is used to fit the linear equation. Based on the Y' coordinates of the corner points, determine their X' coordinates using the fitted line equations. The crossarm structure model is obtained by connecting the corner points according to the topological relationship determined by the abstract template.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the parameterized tower model verification method according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the parameterized tower model verification method according to any one of claims 1-5.

Images