Substation building foundation pit geometric information extraction and detection method based on laser point cloud

Abstract

The invention provides a transformer substation building foundation pit geometric information extraction and detection method based on laser point cloud, and belongs to the technical field of transformer substation building foundation pit information detection. Then, the steps of point cloud filtering, ground removal, multi-view projection, morphological operation, polygon fitting and the like are adopted, the contour of the foundation pit is efficiently and accurately extracted, geometrical information of the contour is calculated, and the precision and reliability of foundation pit detection are remarkably improved. Compared with the prior art, the method has relatively high implementability in an engineering project, particularly has obvious advantages on complex point cloud data, and has high stability and enough precision.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer substation building foundation pit information detection technology, and in particular to a transformer substation building foundation pit geometric information extraction and detection method based on laser point cloud. Background Art

[0002] Substations are key facilities in the power system, and their construction quality directly affects the safety and reliability of power supply. As part of the substation infrastructure, the construction quality of the substation building pit is particularly important. Foundation pit excavation requires precise control to ensure the stability and safety of subsequent equipment installation. Traditional foundation pit detection methods mainly rely on manual measurement, which has problems such as long time consumption, low efficiency, and limited accuracy, and cannot meet the high efficiency and high precision requirements of modern engineering. Therefore, the use of laser point cloud technology to detect substation building foundation pits has become a necessary and effective solution.

[0003] Laser point cloud technology uses laser radar equipment to collect three-dimensional spatial information, which can quickly and accurately obtain detailed data on terrain and buildings. Compared with traditional measurement methods, laser point cloud has the advantages of high resolution, high precision and high efficiency, and can perform comprehensive data collection in complex environments. This is particularly important for the detection of substation foundation pits, because foundation pits are usually located at construction sites with complex and fast-changing environments. Laser point cloud technology can provide a complete three-dimensional model in a short time, providing reliable data support for subsequent analysis and decision-making. In addition, laser point cloud data can also be compared with design drawings to promptly discover and correct construction deviations and ensure construction quality.

[0004] However, the amount of laser point cloud data of the substation building foundation pit is large and there may be occlusion and noise. How to conduct real-time and accurate detection is the main difficulty currently faced. In addition, the measurement difficulties caused by the complex structure of various foundation pits, their irregular shapes, and inconsistent inclinations also require more angle measurements to ensure their stability. Summary of the invention

[0005] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a method for extracting and detecting geometric information of substation building foundation pit based on laser point cloud, which can efficiently and accurately extract the foundation pit contour and calculate its geometric information, significantly improving the accuracy and reliability of foundation pit detection. At the same time, it has strong feasibility in engineering projects, especially has obvious advantages in complex point cloud data, and has high stability and sufficient accuracy.

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

[0007] A method for extracting and detecting geometric information of a substation building foundation pit based on laser point cloud comprises the following steps:

[0008] S1. Obtain the point cloud data of the complete substation building foundation pit through laser point cloud acquisition equipment;

[0009] S2, preprocessing the point cloud data of the substation building foundation pit to obtain sparse point cloud data, and removing the ground point part of the sparse point cloud data to obtain point cloud data of the bottom and pit wall of the substation building foundation pit;

[0010] S3, based on the specific shape and characteristics of the substation building foundation pit, select three orthogonal directions to perform two-dimensional projection on the point cloud data of the bottom and pit wall of the substation building foundation pit, generate a corresponding two-dimensional image, and convert the two-dimensional image into a binary image;

[0011] S4, applying morphological operations to the binary image to eliminate noise and small isolated areas in the binary image to obtain a smooth outline of the substation building foundation pit, and then performing image maximum connected domain detection on the processed binary image to identify and extract the foundation pit edge in the maximum connected domain;

[0012] S5. Perform polygon fitting on the extracted foundation pit edge to form a geometric shape representing the foundation pit contour, and calculate the geometric information of the fitting polygon to obtain the geometric information of the substation building foundation pit.

[0013] Preferably, in S2, the point cloud data of the substation building foundation pit is preprocessed to obtain sparse point cloud data, including:

[0014] S21, removing noise points and outliers in the point cloud data of the substation building pit by a statistical filtering algorithm, the formula is as follows:

[0015]

[0016] Where, d i is the average neighborhood distance of the i-th point, k is the number of neighboring points, and p i and p j are the coordinates of point i and neighboring point j respectively;

[0017] S22, merging the processed point cloud data of the substation building foundation pit and converting them into a unified engineering coordinate system;

[0018] S23, dividing the point cloud data in the unified coordinate system into regular three-dimensional voxel regions, and selecting a representative point in each three-dimensional voxel region to implement point cloud data downsampling, the formula is:

[0019]

[0020] In the formula, v i is the voxel index of point i, l x , ly , l z are the sizes of the voxel in the XYZ directions respectively;

[0021] According to the above, the point cloud data of the substation building foundation pit is filtered, thinned and fused to obtain sparse point cloud data with noise removed.

[0022] Preferably, in S2, the ground point part of the sparse point cloud data is removed to obtain the point cloud data of the bottom and wall of the substation building foundation pit, including:

[0023] S24, randomly select three points in the three-dimensional voxel area of ​​the sparse point cloud data to obtain the initial ground plane equation: Ax+By+Cz+D=0, that is, calculate the distances from all points to the plane:

[0024]

[0025] S25, using the initial ground plane equation, setting the number of iterations k, the inlier threshold t and the minimum inlier ratio d, if the distance from a point to the ground plane is less than the inlier threshold t, then the point is the inlier point P inliers :

[0026] P inliers ={p i |d i <t};

[0027] S26. If the number of inliers in step S25 is greater than the minimum inlier ratio d, the plane model is recorded, and all inliers of the plane model are extracted to obtain ground point cloud data;

[0028] S27, remove the ground point cloud data obtained in step S26, repeat steps S24 to S26, and obtain the point cloud data of the bottom and wall of the substation building foundation pit.

[0029] Preferably, in S3, based on the specific shape and characteristics of the substation building foundation pit, three orthogonal directions are selected to perform two-dimensional projection on the point cloud data of the bottom and pit wall of the substation building foundation pit, generate a corresponding two-dimensional image, and convert the two-dimensional image into a binary image, including:

[0030] S31, obtaining three main directions of the substation building foundation pit part by principal component analysis of the point cloud data of the bottom and pit wall of the substation building foundation pit, wherein the main directions are the top view XOY plane, the front view XOZ plane and the side view YOZ plane;

[0031] First, the point cloud data of the bottom and wall of the substation building foundation pit are centralized, and the original point cloud matrix X is converted to the centralized point cloud matrix X c middle:

[0032] X c =X-μ;

[0033] Where μ is the mean vector of the point cloud;

[0034] Then, calculate the centered point cloud matrix X c The covariance matrix of N is the number of points;

[0035] Finally, the covariance matrix is ​​decomposed into eigenvalues ​​CV = VΛ to obtain the eigenvalue diagonal matrix Λ and the eigenvector V. The eigenvectors corresponding to the diagonal elements in the eigenvalue diagonal matrix Λ are the orthogonal directions of the point cloud data.

[0036] S32, based on the orthogonal direction of the point cloud data determined in step S31, coordinate transformation is performed on the point cloud data so that the obtained orthogonal direction is aligned with the standard coordinate axis;

[0037] S33. After completing step S32, the point cloud data is projected into a two-dimensional image in three orthogonal directions, wherein the plane point cloud is projected into the XOY plane, and the remaining pit wall point clouds are projected into the XOZ and YOZ planes; then the projected point cloud data is rasterized to generate a binary image:

[0038] Grid(i,j)={p k |p k ∈X proj and(x k ,y k )∈cell(i,j)};

[0039] Where, X proj is the point cloud to be projected, cell(i,j) is the grid with row and column index (i,j), p k is any point in the grid cell (i, j).

[0040] Preferably, in said S4, it includes:

[0041] S41, performing n times of erosion operation with a convolution kernel of 5*5 on the binary image to remove noise points in the binary image, so that the foundation pit outline is more obvious:

[0042]

[0043] In the formula, I is a binary image, and the convolution kernel B is 5*5 is a 5*5 all-one matrix;

[0044] S42. After completing step S41, perform 2n+2m times of dilation operation with a convolution kernel of 3*3 on the binary image to expand the white area in the binary image and fill the small holes in the foundation pit outline:

[0045]

[0046] In the formula, the convolution kernel B 3*3 is a 3*3 all-one matrix;

[0047] S43, after completing step S42, performing m times of erosion operation with a convolution kernel of 5*5 on the binary image, and obtaining a foundation pit contour image after restoration and expansion;

[0048] S44, based on the foundation pit contour image, finding the largest connected domain in the foundation pit contour image, and extracting the foundation pit edge in the largest connected domain.

[0049] Preferably, in said S5, it includes:

[0050] S51. For XOY plane projection, the Douglas-Peucker algorithm is used to fit the polygon. All edge points of the XOY plane projection are regarded as vertices of the polygon. The first and last points p0 and p n As the initial point, calculate point by point to the straight line p0p n The straight-line distance of the vertical distance:

[0051]

[0052] In the formula, × represents the cross product of the vector, ||·|| represents the modulus of the vector. Find the point with the largest distance, and then determine the point with the largest distance d max If d max If it is greater than the set threshold ∈, the polygon edge is split into p0p max , p max p n Two parts, and recursively process these two parts separately;

[0053] S52, after completing step S51, obtain a set P of all edge points, reversely project the coordinates of the set of edge points on the XOY plane into a three-dimensional engineering coordinate system, and obtain the polygons at the top and bottom of the foundation pit, the three-dimensional coordinates of the corner points of the polygons, and the lengths of all sides of the polygons;

[0054] S53, executing steps S51 to S52 on the XOZ and YOZ planes, performing polygon fitting, calculating the side length of the foundation pit, and performing cross-validation, and calculating the height of the foundation pit by the height of the side projection of the foundation pit, and determining the geometric information of the substation building foundation pit.

[0055] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0056] The invention provides a method for extracting and detecting geometric information of a transformer substation building pit based on laser point cloud, comprising: obtaining point cloud data of a complete transformer substation building pit by means of a laser point cloud acquisition device; preprocessing the point cloud data of the transformer substation building pit to obtain sparse point cloud data, and removing the ground point part of the sparse point cloud data to obtain point cloud data of the bottom and wall of the transformer substation building pit; based on the specific shape and characteristics of the transformer substation building pit, selecting three orthogonal directions to perform two-dimensional projection on the point cloud data of the bottom and wall of the transformer substation building pit to generate a corresponding two-dimensional image, and converting the two-dimensional image into a binary image; applying morphological operations to the binary image to eliminate noise and small isolated areas in the binary image to obtain a smooth transformer substation building pit contour, and then performing image maximum connected domain detection on the processed binary image to identify and extract the pit edge in the maximum connected domain; performing polygon fitting on the extracted pit edge to form a geometric shape representing the pit contour, and calculating the geometric information of the fitting polygon to obtain the geometric information of the transformer substation building pit. The present invention can efficiently and accurately extract foundation pit contours and calculate their geometric information, significantly improving the accuracy and reliability of foundation pit detection. It is also highly feasible in engineering projects, especially in complex point cloud data, with high stability and sufficient accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A flow chart of the method provided by the present invention;

[0059] Figure 2 A schematic diagram of a plane of ground point cloud data provided in the first embodiment of the present invention;

[0060] Figure 3 A schematic diagram of the plane point cloud data of a foundation pit provided in the first embodiment of the present invention;

[0061] Figure 4 A schematic diagram of point cloud data provided in the first embodiment of the present invention; wherein: Figure 4 (a) with Figure 4 (b) are schematic diagrams of the original point cloud data;

[0062] Figure 5 This is a schematic diagram of point cloud data projection provided in the first embodiment of the present invention; wherein: Figure 5 (a) is a schematic diagram of the projection of point cloud data in the XOY direction. Figure 5 (b) is a schematic diagram of the projection of point cloud data in the XOZ direction. Figure 5 (c) is a schematic diagram of the point cloud data projection in the YOZ direction. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0065] Embodiment 1

[0066] like Figure 1 As shown, the present invention provides a method for extracting and detecting geometric information of a substation building foundation pit based on laser point cloud, comprising the following steps:

[0067] S1. Obtain the point cloud data of the complete substation building foundation pit through laser point cloud acquisition equipment;

[0068] S2, preprocessing the point cloud data of the substation building foundation pit to obtain sparse point cloud data, and removing the ground point part of the sparse point cloud data to obtain point cloud data of the bottom and pit wall of the substation building foundation pit;

[0069] S3, based on the specific shape and characteristics of the substation building foundation pit, select three orthogonal directions to perform two-dimensional projection on the point cloud data of the bottom and pit wall of the substation building foundation pit, generate a corresponding two-dimensional image, and convert the two-dimensional image into a binary image;

[0070] S4, applying morphological operations to the binary image to eliminate noise and small isolated areas in the binary image to obtain a smooth outline of the substation building foundation pit, and then performing image maximum connected domain detection on the processed binary image to identify and extract the foundation pit edge in the maximum connected domain;

[0071] S5. Perform polygon fitting on the extracted foundation pit edge to form a geometric shape representing the foundation pit contour, and calculate the geometric information of the fitting polygon to obtain the geometric information of the substation building foundation pit.

[0072] In this embodiment, in S2, the point cloud data of the substation building foundation pit is preprocessed to obtain sparse point cloud data, including:

[0073] S21, removing noise points and outliers in the point cloud data of the substation building pit by a statistical filtering algorithm, the formula is as follows:

[0074]

[0075] Where, d i is the average neighborhood distance of the i-th point, k is the number of neighboring points, and p i and p j are the coordinates of point i and neighboring point j respectively;

[0076] S22, merging the processed point cloud data of the substation building foundation pit and converting them into a unified engineering coordinate system;

[0077] S23, dividing the point cloud data in the unified coordinate system into regular three-dimensional voxel regions, and selecting a representative point in each three-dimensional voxel region to implement point cloud data downsampling, the formula is:

[0078]

[0079] In the formula, v i is the voxel index of point i, l x , l y , l z are the sizes of the voxel in the XYZ directions respectively;

[0080] According to the above, the point cloud data of the substation building foundation pit is filtered, thinned and fused to obtain sparse point cloud data with noise removed.

[0081] In this embodiment, in S2, the ground point part of the sparse point cloud data is removed to obtain the point cloud data of the bottom and wall of the substation building foundation pit, including:

[0082] S24, randomly select three points in the three-dimensional voxel area of ​​the sparse point cloud data to obtain the initial ground plane equation: Ax+By+Cz+D=0, that is, calculate the distances from all points to the plane:

[0083]

[0084] S25, using the initial ground plane equation, setting the number of iterations k, the inlier threshold t and the minimum inlier ratio d, if the distance from a point to the ground plane is less than the inlier threshold t, then the point is the inlier point P inliers :

[0085] P inliers ={p i |d i <t};

[0086] S26, such as Figure 2 As shown, if the number of inliers in step S25 is greater than the minimum inlier ratio d, the plane model is recorded, and all inliers of the plane model are extracted to obtain ground point cloud data;

[0087] S27, such as Figure 3 As shown, the ground point cloud data obtained in step S26 is removed, and steps S24 to S26 are repeated to obtain the point cloud data of the bottom and wall of the substation building foundation pit.

[0088] In this embodiment, in S3, based on the specific shape and characteristics of the substation building foundation pit, three orthogonal directions are selected to perform two-dimensional projection on the point cloud data of the bottom and pit wall of the substation building foundation pit, generate a corresponding two-dimensional image, and convert the two-dimensional image into a binary image, including:

[0089] S31, obtaining three main directions of the substation building foundation pit part by principal component analysis of the point cloud data of the bottom and pit wall of the substation building foundation pit, wherein the main directions are the top view XOY plane, the front view XOZ plane and the side view YOZ plane;

[0090] First, the point cloud data of the bottom and wall of the substation building foundation pit are centralized, and the original point cloud matrix x is converted to the centralized point cloud matrix X c middle:

[0091] x c =X-μ;

[0092] Where μ is the mean vector of the point cloud;

[0093] Then, calculate the centered point cloud matrix X c The covariance matrix of N is the number of points;

[0094] Finally, the covariance matrix is ​​decomposed into eigenvalues ​​CV = VΛ to obtain the eigenvalue diagonal matrix Λ and the eigenvector V. The eigenvectors corresponding to the diagonal elements in the eigenvalue diagonal matrix Λ are the orthogonal directions of the point cloud data.

[0095] S32, based on the orthogonal direction of the point cloud data determined in step S31, coordinate transformation is performed on the point cloud data so that the obtained orthogonal direction is aligned with the standard coordinate axis;

[0096] S33. After completing step S32, the point cloud data is projected into a two-dimensional image in three orthogonal directions, wherein the plane point cloud is projected into the XOY plane, and the remaining pit wall point clouds are projected into the XOZ and YOZ planes; then the projected point cloud data is rasterized to generate a binary image:

[0097] Grid(i,j)={p k |pk ∈X proj and(x k ,y k )∈cell(i,j)};

[0098] Where, X proj is the point cloud to be projected, cell(i,j) is the grid with row and column index (i,j), p k For any point in the grid cell (i, j), the original point cloud data diagram is as follows: Figure 4 (a) and Figure 4 (b) shows the schematic diagram of the projected point cloud data. The result is as follows Figure 5 (a) Figure 5 (b) and Figure 5 (c) as shown.

[0099] In this embodiment, in said S4, it includes:

[0100] S41, performing n times of erosion operation with a convolution kernel of 5*5 on the binary image to remove noise points in the binary image, so that the foundation pit outline is more obvious:

[0101]

[0102] In the formula, I is a binary image, and the convolution kernel B is 5*5 is a 5*5 all-one matrix;

[0103] S42. After completing step S41, perform 2n+2m times of dilation operation with a convolution kernel of 3*3 on the binary image to expand the white area in the binary image and fill the small holes in the foundation pit outline:

[0104]

[0105] In the formula, the convolution kernel B 3*3 is a 3*3 all-one matrix;

[0106] S43, after completing step S42, performing m times of erosion operation with a convolution kernel of 5*5 on the binary image, and obtaining a foundation pit contour image after restoration and expansion;

[0107] S44, based on the foundation pit contour image, finding the largest connected domain in the foundation pit contour image, and extracting the foundation pit edge in the largest connected domain.

[0108] In this embodiment, S5 includes:

[0109] S51. For XOY plane projection, the Douglas-Peucker algorithm is used to fit the polygon. All edge points of the XOY plane projection are regarded as vertices of the polygon. The first and last points p0 and p nAs the initial point, calculate point by point to the straight line p0p n The straight-line distance of the vertical distance:

[0110]

[0111] In the formula, × represents the cross product of the vector, ||·|| represents the modulus of the vector. Find the point with the largest distance, and then determine the point with the largest distance d max If d max If it is greater than the set threshold ∈, the polygon edge is split into o0p max 、p max p n Two parts, and recursively process these two parts separately;

[0112] S52, after completing step S51, obtain a set P of all edge points, reversely project the coordinates of the set of edge points on the XOY plane into a three-dimensional engineering coordinate system, and obtain the polygons at the top and bottom of the foundation pit, the three-dimensional coordinates of the corner points of the polygons, and the lengths of all sides of the polygons;

[0113] S53, executing steps S51 to S52 on the XOZ and YOZ planes, performing polygon fitting, calculating the side length of the foundation pit, and performing cross-validation, and calculating the height of the foundation pit by the height of the side projection of the foundation pit, and determining the geometric information of the substation building foundation pit.

[0114] Therefore, the present invention adopts the above-mentioned method for extracting and detecting geometric information of substation building foundation pit based on laser point cloud, obtains the complete substation foundation pit point cloud through laser point cloud acquisition equipment, and then uses point cloud filtering, ground removal, multi-view projection, morphological operation and polygon fitting steps to efficiently and accurately extract the foundation pit contour and calculate its geometric information, which significantly improves the accuracy and reliability of foundation pit detection. Compared with the existing technology, the present invention has strong feasibility in engineering projects, especially has obvious advantages in complex point cloud data, and has high stability and sufficient accuracy.

[0115] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for extracting and detecting geometric information of substation building foundation pit based on laser point cloud, characterized in that: The following steps are involved: S1. Obtain the point cloud data of the complete substation building foundation pit through laser point cloud acquisition equipment; S2, preprocessing the point cloud data of the substation building foundation pit to obtain sparse point cloud data, and removing the ground point part of the sparse point cloud data to obtain point cloud data of the bottom and pit wall of the substation building foundation pit; S3, based on the specific shape and characteristics of the substation building foundation pit, select three orthogonal directions to perform two-dimensional projection on the point cloud data of the bottom and pit wall of the substation building foundation pit, generate a corresponding two-dimensional image, and convert the two-dimensional image into a binary image; S4, applying morphological operations to the binary image to eliminate noise and small isolated areas in the binary image to obtain a smooth outline of the substation building foundation pit, and then performing image maximum connected domain detection on the processed binary image to identify and extract the foundation pit edge in the maximum connected domain; S5. Perform polygon fitting on the extracted foundation pit edge to form a geometric shape representing the foundation pit contour, and calculate the geometric information of the fitting polygon to obtain the geometric information of the substation building foundation pit.

2. According to the method for extracting and detecting geometric information of substation building foundation pit based on laser point cloud in claim 1, it is characterized in that: In S2, the point cloud data of the substation building foundation pit is preprocessed to obtain sparse point cloud data, including: S21, removing noise points and outliers in the point cloud data of the substation building pit by a statistical filtering algorithm, the formula is as follows: Where, d i is the average neighborhood distance of the i-th point, k is the number of neighboring points, and p i and p j are the coordinates of point i and neighboring point j respectively; S22, merging the processed point cloud data of the substation building foundation pit and converting them into a unified engineering coordinate system; S23, dividing the point cloud data in the unified coordinate system into regular three-dimensional voxel regions, and selecting a representative point in each three-dimensional voxel region to implement point cloud data downsampling, the formula is: In the formula, v i is the voxel index of point i, l x , l y , l z are the sizes of the voxel in the XYZ directions respectively; According to the above, the point cloud data of the substation building foundation pit is filtered, thinned and fused to obtain sparse point cloud data with noise removed.

3. The method for extracting and detecting geometric information of a substation foundation pit based on laser point cloud according to claim 2 is characterized in that: In S2, the ground point part of the sparse point cloud data is removed to obtain the point cloud data of the bottom and wall of the substation building foundation pit, including: S24, randomly select three points in the three-dimensional voxel area of ​​the sparse point cloud data to obtain the initial ground plane equation: Ax+By+Cz+D=0, that is, calculate the distances from all points to the plane: S25, using the initial ground plane equation, setting the number of iterations k, the inlier threshold t and the minimum inlier ratio d, if the distance from a point to the ground plane is less than the inlier threshold t, then the point is the inlier point P inliers : P inliers ={p i |d i <t}; S26. If the number of inliers in step S25 is greater than the minimum inlier ratio d, the plane model is recorded, and all inliers of the plane model are extracted to obtain ground point cloud data; S27, remove the ground point cloud data obtained in step S26, repeat steps S24 to S26, and obtain the point cloud data of the bottom and wall of the substation building foundation pit.

4. The method for extracting and detecting geometric information of a substation foundation pit based on laser point cloud according to claim 3 is characterized in that: In S3, based on the specific shape and characteristics of the substation building foundation pit, three orthogonal directions are selected to perform two-dimensional projection on the point cloud data of the bottom and pit wall of the substation building foundation pit, generate a corresponding two-dimensional image, and convert the two-dimensional image into a binary image, including: S31, obtaining three main directions of the substation building foundation pit part by principal component analysis of the point cloud data of the bottom and pit wall of the substation building foundation pit, wherein the main directions are the top view XOY plane, the front view XOZ plane and the side view YOZ plane; First, the point cloud data of the bottom and wall of the substation building foundation pit are centralized, and the original point cloud matrix X is converted to the centralized point cloud matrix X c middle: X c =X-μ; Where μ is the mean vector of the point cloud; Then, calculate the centered point cloud matrix X c The covariance matrix of N is the number of points; Finally, the covariance matrix is ​​decomposed into eigenvalues ​​CV = VΛ to obtain the eigenvalue diagonal matrix Λ and the eigenvector V. The eigenvectors corresponding to the diagonal elements in the eigenvalue diagonal matrix Λ are the orthogonal directions of the point cloud data. S32, based on the orthogonal direction of the point cloud data determined in step S31, coordinate transformation is performed on the point cloud data so that the obtained orthogonal direction is aligned with the standard coordinate axis; S33. After completing step S32, the point cloud data is projected into a two-dimensional image in three orthogonal directions, wherein the plane point cloud is projected into the XOY plane, and the remaining pit wall point clouds are projected into the XOZ and YOZ planes; then the projected point cloud data is rasterized to generate a binary image: Grid(i,j)={p k |p k ∈X proj and(x k ,y k )∈cell(i,j)}; Where, X proj is the point cloud to be projected, cell(i,j) is the grid with row and column index (i,j), p k is any point in the grid cell (i, j).

5. The method for extracting and detecting geometric information of substation foundation pit based on laser point cloud according to claim 4 is characterized in that: In said S4, it includes: S41, performing n times of erosion operation with a convolution kernel of 5*5 on the binary image to remove noise points in the binary image, so that the foundation pit outline is more obvious: In the formula, I is a binary image, and the convolution kernel B is 5*5 is a 5*5 all-one matrix; S42. After completing step S41, perform 2n+2m times of dilation operation with a convolution kernel of 3*3 on the binary image to expand the white area in the binary image and fill the small holes in the foundation pit outline: In the formula, the convolution kernel B 3*3 is a 3*3 all-one matrix; S43, after completing step S42, performing m times of erosion operation with a convolution kernel of 5*5 on the binary image, and obtaining a foundation pit contour image after restoration and expansion; S44, based on the foundation pit contour image, finding the largest connected domain in the foundation pit contour image, and extracting the foundation pit edge in the largest connected domain.

6. The method for extracting and detecting geometric information of a substation foundation pit based on laser point cloud according to claim 5 is characterized in that: In said S5, it includes: S51. For XOY plane projection, the Douglas-Peucker algorithm is used to fit the polygon. All edge points of the XOY plane projection are regarded as vertices of the polygon. The first and last points p0 and p n As the initial point, calculate point by point to the straight line p0p n The straight-line distance of the vertical distance: In the formula, × represents the cross product of the vector, ‖·‖ represents the modulus of the vector to find the point with the largest distance, and then determine the maximum distance point d max If d max If it is greater than the set threshold ∈, the polygon edge is split into p0p max , p max p n Two parts, and recursively process these two parts separately; S52, after completing step S51, obtain a set P of all edge points, reversely project the coordinates of the set of edge points on the XOY plane into a three-dimensional engineering coordinate system, and obtain the polygons at the top and bottom of the foundation pit, the three-dimensional coordinates of the corner points of the polygons, and the lengths of all sides of the polygons; S53, executing steps S51 to S52 on the XOZ and YOZ planes, performing polygon fitting, calculating the side length of the foundation pit, and performing cross-validation, and calculating the height of the foundation pit by the height of the side projection of the foundation pit, and determining the geometric information of the substation building foundation pit.

Images