A power transmission tower type identification method and system based on point cloud

Abstract

The application provides a power transmission pole tower type identification method based on point cloud, which comprises the following steps: making a pole tower type data set, converting a standard pole tower model into a consistent height-width image file, and establishing a standard pole tower character library; extracting power transmission pole tower point cloud, eliminating miscellaneous points and power line point cloud in unmanned aerial vehicle measured point cloud, and extracting power transmission pole tower point cloud; calculating a pole tower symmetry axis plane, calculating the symmetry axis plane of the measured pole tower point cloud by counting points in each angle direction; re-projecting the pole tower point cloud by using a coordinate transformation method; and identifying the pole tower type by using a template matching method. The application improves the automation level of power transmission line point cloud data processing, solves the problem of visual identification consuming a large amount of manpower and material resources, and provides a data basis for subsequent pole tower automatic modeling and pole tower deformation detection.

Description

Technical Field

[0001] This invention relates to the field of point cloud data processing technology, and in particular to a method and system for identifying the type of power transmission pole tower based on point clouds. Background Technology

[0002] With the development of smart grid technology, people have placed higher demands on the digitalization and intelligence of power grid management. While SAR satellite-based remote sensing monitoring has advantages such as wide monitoring range and large area coverage, it has high requirements for the sampling period and image resolution of remote sensing images, incurs huge data acquisition costs, and involves complex data processing, making widespread adoption difficult. In recent years, using airborne laser scanning and oblique photogrammetry to reconstruct three-dimensional models of overhead transmission lines has become a widely promoted line inspection method within the State Grid system, significantly improving the efficiency and accuracy of line inspections.

[0003] Tower type is crucial data for tower modeling, serving as a prerequisite for feature point extraction and tower status identification. Traditionally, this is determined visually by professionals. However, with the development of laser scanning and oblique photogrammetry technologies, workers often need to rapidly process hundreds of gigabytes of point cloud data on towers. Manually judging tower type increases the workload of data processing personnel and contradicts the trend towards automation in point cloud data processing. Therefore, an automatic identification method for transmission tower types based on point clouds is needed. Summary of the Invention

[0004] This invention provides a point cloud-based scheme for identifying the type of power transmission tower. By creating a standard tower character set, the point cloud of the power transmission tower is obtained and the axis of symmetry of the point cloud is calculated. The point cloud of the power transmission tower is reprojected, and the reprojected point cloud of the tower is matched with the standard tower dataset to determine the tower type.

[0005] To achieve the above objectives, this invention provides a method for identifying the type of power transmission pole tower based on point clouds, comprising the following steps:

[0006] Step 1: Creating a pole and tower type dataset, including converting standard pole and tower models into image files with consistent height and width, and establishing a standard pole and tower character library;

[0007] Step 2, extraction of power transmission tower point cloud, including removing noise and power line point cloud contained in the point cloud measured by UAV, and extracting the power tower point cloud;

[0008] Step 3, Calculation of the tower's axis of symmetry, including calculating the axis of symmetry of the tower's measured point cloud by counting the number of points in each angular direction;

[0009] Step 4, tower point cloud reprojection, including projecting the measured tower point cloud onto the tower's axis of symmetry using coordinate transformation;

[0010] Step 5, pole type identification, including using template matching method to determine pole type.

[0011] Furthermore, step 2 is implemented by including the following sub-steps:

[0012] Step 2.1: Use UAV lidar or tilt measurement technology to obtain the 3D point cloud of the tower scene;

[0013] Step 2.2: Remove noise data to obtain force survey data that includes power towers, ground lines, and surrounding vegetation;

[0014] Step 2.3, gridding the point cloud, includes projecting the point cloud onto the horizontal XY coordinate system along the vertical direction, dividing it into grids, determining the grid position of each point cloud, and realizing the ordering of the point cloud;

[0015] Step 2.4, extraction of the transmission tower grid region, includes calculating the local maximum and minimum elevation values ​​and local elevation differences in each segmented grid. Considering the characteristic of transmission towers having large elevation differences, an elevation difference threshold is set to remove grid regions containing ground, low vegetation, and other non-transmission tower point clouds. Based on the continuity of the elevation distribution of the tower point clouds, the areas where transmission lines are located are removed. Combining the local extreme elevation characteristics, the maximum elevation value of the tower is used as the standard to quickly filter out tall forest areas, finally obtaining the transmission tower grid region.

[0016] Step 2.5, Tower Point Cloud Extraction, includes extracting point clouds at all elevations within a range slightly larger than the grid, centered on the local elevation maximum point of the point cloud at the top of the tower, calculating the minimum elevation within the grid as the ground elevation, setting it as the threshold to remove ground points and tower foot point clouds, and extracting the tower head and tower body point clouds.

[0017] Furthermore, step 3 is implemented by including the following sub-steps:

[0018] Step 3.1: Project the segmented tower point cloud onto the XOY plane to obtain the center point (x0, y0) of the tower plane position, which is the point of maximum local elevation of the tower point cloud;

[0019] Step 3.2: Set the step size θ with the center point of the tower position as the origin. step Let n be the interval number and n·θ be the interval number. Then, we can count the angles and directions for each angle. step The direction with the largest number of points, α0, is taken as the axis of symmetry, and the plane along the Z-axis is used as the axis of symmetry.

[0020] Furthermore, step 4 is implemented by including the following sub-steps:

[0021] Step 4.1, calculate the center point P(x0,y0,z0) of the tower, where z0=(hmax +h min Let point P be the new origin of the three-dimensional spatial coordinate system. The coordinate transformation calculation formula is:

[0022]

[0023] Where x0, y0, and z0 are the coordinates of the center point before the transformation, and x′, y′, and z′ are the coordinates of the center point after the transformation;

[0024] Step 4.2, three-dimensional coordinate rotation, including spatial coordinate rotation, transforming the spatial coordinate system translated in Step 4.1 into a spatial coordinate system with P as the origin and the XOY plane as the axis of symmetry, and remapping the Y-axis to the original Z+ axis position. The equation of the axis of symmetry in the original spatial coordinate system is y′=tanα0·′, and the coordinate transformation formula is:

[0025]

[0026] Where x′, y′, and z′ are the coordinates of the center point before transformation, x″, y″, and z″ are the coordinates of the center point after transformation, and α0 is the angle of the axis of symmetry;

[0027] Step 4.3, Projection Mapping: The transformed 3D spatial coordinates from Step 4.2 are mapped onto the XOY plane using projection. The coordinate transformation formula is:

[0028]

[0029] X, Y, and Z are the projected planar coordinates.

[0030] Furthermore, step 5 is implemented by including the following sub-steps:

[0031] Step 5.1: Binarize the tower point cloud image. In the package, the X and Y values ​​of all point clouds are divided into grids. The width of the projection grid is set. If there are point cloud pixels in the projection grid, the projection grid value is 1; otherwise, the projection grid value is 0. Generate a binary image file with the same size as the standard tower character library. The file size is denoted as M rows and N columns.

[0032] Step 5.2: Calculate the correlation coefficient R between the measured tower's binary image file S(m,n) and the file T(m,n) in the standard tower character library. The correlation coefficient has a maximum value when the measured tower matches the tower type in the standard tower character library. The formula for calculating the correlation coefficient is...

[0033]

[0034] Among them, T i S is a file in the character library for the i-th standard tower, S is a binary image file of the measured tower, and T is a file in the character library for the i-th standard tower. i(,n) represents the value in the m-th row and n-th column of the character library for the i-th standard tower, S(m,n) represents the value in the m-th row and n-th column of the binary image file of the measured tower, and R(S,T) represents the value in the m-th row and n-th column of the binary image file of the measured tower. i ) represents the correlation coefficient between the file in the character library of the i-th standard tower and the binary image file of the measured tower.

[0035] On the other hand, the present invention provides a point cloud-based transmission line tower type identification system for implementing the point cloud-based transmission line tower type identification method described above.

[0036] Moreover, it includes the following modules,

[0037] The first module is used for creating a pole and tower type dataset, including converting standard pole and tower models into image files with consistent height and width, and establishing a standard pole and tower character library.

[0038] The second module is used for point cloud extraction of power transmission towers, including removing noise and power line point clouds contained in the point cloud measured by UAV, and extracting the point cloud of power transmission towers;

[0039] The third module is used for calculating the symmetry axis of the tower, including calculating the symmetry axis of the tower's measured point cloud by counting the number of points in each angular direction;

[0040] The fourth module is used for reprojection of tower point clouds, including projecting the measured point cloud of the tower onto the tower's axis of symmetry using coordinate transformation.

[0041] The fifth module is used for pole / tower type identification, including determining the pole / tower type using a template matching method.

[0042] Alternatively, it may include a processor and a memory, with the memory used to store program instructions and the processor used to call the stored instructions in the memory to execute a point cloud-based transmission line tower type identification method as described above.

[0043] Alternatively, it may include a readable storage medium storing a computer program that, when executed, implements a point cloud-based method for identifying the type of power transmission pole tower as described above.

[0044] The beneficial effects of this invention are as follows:

[0045] 1) This invention proposes an automatic identification scheme for transmission tower types based on point cloud, which promotes the automation of point cloud data processing for transmission lines, solves the problem of high manpower and material resources required for visual identification, and provides a data foundation for subsequent automatic tower modeling and tower deformation detection.

[0046] 2) The present invention is simple and convenient to implement, highly practical, and solves the problems of low practicality and inconvenience in actual application of related technologies. It can improve user experience and has significant market value. Attached Figure Description

[0047] Figure 1 This is a flowchart of a method according to an embodiment of the present invention;

[0048] Figure 2 This is a local elevation point cloud distribution map according to an embodiment of the present invention. Detailed Implementation

[0049] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0050] like Figure 1 As shown in the embodiment, this method provides a point cloud-based method for identifying the type of power transmission tower, including tower type dataset creation, power transmission tower point cloud extraction, tower symmetry axis plane calculation, tower point cloud reprojection, and tower type identification steps.

[0051] The creation of the pole and tower type dataset includes converting standard pole and tower models (preferably CAD models) into image files with consistent height and width, and establishing a standard pole and tower character library;

[0052] The extraction of power transmission tower point clouds includes removing noise and power line point clouds contained in the point clouds measured by UAVs, and extracting the power tower point clouds;

[0053] The calculation of the tower's axis of symmetry includes calculating the axis of symmetry of the tower's measured point cloud by counting the number of points in each angular direction;

[0054] The reprojection of the tower point cloud includes projecting the measured point cloud of the tower onto the symmetry axis plane of the tower using coordinate transformation.

[0055] The tower type identification includes using a template matching method to determine the tower type.

[0056] Furthermore, the preferred implementation method for point cloud extraction of transmission towers in this embodiment is as follows:

[0057] Step 2.1: Use UAV lidar or tilt measurement technology to obtain the 3D point cloud of the tower scene.

[0058] Step 2.2: Since the acquired point cloud data contains some noise, a common Kalman filter is used to remove the noise data to obtain force survey data that includes power towers, ground lines, and surrounding vegetation.

[0059] Step 2.3, Gridding the Point Cloud. Project the point cloud vertically onto a horizontal XY coordinate system, and divide it into grids of a certain size. Determine the grid position of each point cloud to achieve point cloud ordering. The point cloud gridding formula is:

[0060]

[0061] In the formula, (x, y) are the XY coordinates of the point cloud. min y min This represents the minimum X and Y coordinates of the point cloud. d is the grid size. m and n are the corresponding grid numbers.

[0062] Step 2.4, Transmission Tower Grid Region Extraction. Calculate the local maximum and minimum elevation values ​​and local elevation differences in each segmented grid. Considering the large elevation differences characteristic of transmission towers, set an elevation difference threshold θ. h Remove grid areas containing non-transmission tower point clouds such as ground and low vegetation, and record areas with elevation differences greater than the threshold θ. h The grid area is traversed. Based on the continuity of the tower point cloud's elevation distribution—that is, point cloud distribution exists from the highest point to the lowest point—the grid area is traversed. Figure 2 As shown, point clouds of cables, vegetation, etc., are only distributed within a certain elevation range. Based on the characteristic of continuous elevation distribution, areas where transmission lines are located can be eliminated. In specific implementation, it is preferred to combine local extreme elevation characteristics and set a maximum elevation threshold H based on the maximum elevation of the towers. max The area of ​​tall trees is quickly filtered out, and the area of ​​power transmission tower grid is finally obtained.

[0063] Step 2.5, Tower Point Cloud Extraction. Using the local maximum elevation point of the tower top as the center, extract point clouds at all elevations within a slightly larger area than the grid. Preferably calculate the minimum elevation within the grid as the ground elevation and set it as the minimum elevation threshold H. min Remove ground points and tower foot point clouds, and extract tower head and tower body point clouds.

[0064] Furthermore, the preferred implementation method for calculating the tower's symmetry axis plane in the embodiment is as follows:

[0065] Step 3.1: Project the segmented tower point cloud onto the XOY plane (the plane determined by the horizontal and vertical axes) to obtain the center point (x0, y0) of the tower plane position, which is the point of maximum local elevation of the tower point cloud.

[0066] Step 3.2: Set the step size θ with the center point of the tower position as the origin. step Given the interval α, calculate the n·θ values ​​for each angle direction. step The number of points (n is the interval number), i.e., the sector region [n·θ] step-α,n·θ step The direction α0 with the largest number of points within +α] is the axis of symmetry, and the plane of symmetry is formed by stretching along the Z-axis (vertical axis).

[0067] In the above technical solution, the specific implementation method of the tower point cloud reprojection is as follows:

[0068] Step 4.1, calculate the center point P(x0,y0,z0) of the tower, where z0=(H max +H min Let point P be the new origin of the three-dimensional spatial coordinate system. The coordinate transformation calculation formula is:

[0069]

[0070] Where x0, y0, and z0 are the coordinates of the center point before transformation, and x′, y′, and z′ are the coordinates of the center point after transformation, H max H is the maximum elevation threshold. min The minimum elevation threshold has been determined in step 2.

[0071] Step 4.2, 3D coordinate rotation: This step rotates the spatial coordinate system translated in Step 4.1 into a spatial coordinate system with P as the origin and the XOY plane as the axis of symmetry. The Y-axis is remapped to its original Z+ axis position. The equation of the axis of symmetry in the original spatial coordinate system is y′=tanα0·x′, and the coordinate transformation formula is:

[0072]

[0073] Where x′, y′, and z′ are the coordinates of the center point before the transformation, x″, y″, and z″ are the coordinates of the center point after the transformation, and α0 is the angle of the axis of symmetry.

[0074] Step 4.3, Projection Mapping: The transformed 3D spatial coordinates from Step 4.2 are mapped onto the XOY plane using projection. The coordinate transformation formula is:

[0075]

[0076] X, Y, and Z are the projected planar coordinates.

[0077] Furthermore, the specific preferred implementation method for identifying the type of transmission line tower in this embodiment is as follows:

[0078] Step 5.1: Binarize the tower point cloud image. Divide the X and Y values ​​of all point clouds into a grid and set the width of the projection grid. If there are point cloud pixels in the projection grid, the projection grid value is 1; otherwise, the projection grid value is 0. Generate a binary image file with the same size as the standard tower character library, i.e., M rows and N columns.

[0079] Step 5.2: Calculate the correlation coefficient R between the measured tower's binary image file S(m,n) and the file T(m,n) in the standard tower character library. The correlation coefficient has a maximum value when the measured tower matches the tower type in the standard tower character library. The formula for calculating the correlation coefficient is:

[0080]

[0081] Among them, T i S is a file in the character library for the i-th standard tower, S is a binary image file of the measured tower, and T is a file in the character library for the i-th standard tower. i (m,n) represents the value in the m-th row and n-th column of the character library for the i-th standard tower, S(m,n) represents the value in the m-th row and n-th column of the binary image file of the measured tower, and R(S,T) represents the value in the n-th row and n-th column of the binary image file of the measured tower. i ) represents the correlation coefficient between the file in the character library of the i-th standard tower and the binary image file of the measured tower.

[0082] In specific implementation, the method proposed in the technical solution of this invention can be automatically executed by those skilled in the art using computer software technology. System devices for implementing the method, such as computer-readable storage media storing the corresponding computer program of the technical solution of this invention and computer equipment including the computer program running the corresponding computer program, should also be within the protection scope of this invention.

[0083] In some possible embodiments, a point cloud-based power transmission tower type identification system is provided, including the following modules:

[0084] The first module is used for creating a pole and tower type dataset, which includes converting standard pole and tower CAD models into image files with consistent height and width, and establishing a standard pole and tower character library.

[0085] The second module is used for point cloud extraction of power transmission towers, including removing noise and power line point clouds contained in the point cloud measured by UAV, and extracting the point cloud of power transmission towers;

[0086] The third module is used for calculating the symmetry axis of the tower, including calculating the symmetry axis of the tower's measured point cloud by counting the number of points in each angular direction;

[0087] The fourth module is used for reprojection of tower point clouds, including projecting the measured point cloud of the tower onto the tower's axis of symmetry using coordinate transformation.

[0088] The fifth module is used for pole / tower type identification, including determining the pole / tower type using a template matching method.

[0089] In some possible embodiments, a point cloud-based transmission line tower type identification system is provided, including a processor and a memory. The memory is used to store program instructions, and the processor is used to call the stored instructions in the memory to execute a point cloud-based transmission line tower type identification method as described above.

[0090] In some possible embodiments, a point cloud-based transmission line tower type identification system is provided, including a readable storage medium on which a computer program is stored. When the computer program is executed, it implements the point cloud-based transmission line tower type identification method described above.

[0091] The specific embodiments described herein are merely illustrative of the spirit of the invention. Those skilled in the art to which this invention pertains may make various modifications or additions to the described specific embodiments or use similar methods to substitute them, without departing from the spirit of the invention or exceeding the scope defined by the appended claims.

Claims

1. A method for identifying the type of power transmission tower based on point cloud, characterized in that: Includes the following steps, Step 1: Creating a pole and tower type dataset, including converting standard pole and tower models into image files with consistent height and width, and establishing a standard pole and tower character library; Step 2, extraction of power transmission tower point cloud, including removing noise and power line point cloud contained in the point cloud measured by UAV, and extracting the power tower point cloud; Step 3, Calculation of the tower's axis of symmetry, including calculating the axis of symmetry of the tower's measured point cloud by counting the number of points in each angular direction; The implementation includes the following sub-steps: Step 3.1: Project the segmented tower point cloud onto the XOY plane to obtain the center point of the tower's planar position. That is, the point where the local elevation of the tower point cloud is the maximum value; Step 3.2: Set the step size with the center point of the tower location as the origin. and interval Let n be the interval number, and count the directions of each angle. Count the points, the direction with the largest quantity. As the axis of symmetry, it is stretched along the Z-axis to serve as the plane of symmetry; Step 4, reprojection of tower point cloud, including projecting the measured point cloud of the tower onto the tower's axis of symmetry using coordinate transformation; The implementation method includes the following sub-steps: Step 4.1, calculate the center point P of the tower. ,in Taking point P as the new origin of the three-dimensional spatial coordinate system, the coordinate transformation calculation formula is: in, The coordinates of the center point before transformation. These are the coordinates of the center point after transformation; Step 4.2, three-dimensional coordinate rotation, including spatial coordinate rotation, rotating the spatial coordinate system translated in Step 4.1 into a spatial coordinate system with P as the origin and the XOY plane as the axis of symmetry, and remapping the Y-axis to the original Z+ axis position, wherein the equation of the axis of symmetry in the original spatial coordinate system is: The coordinate transformation formula is: in, The coordinates of the center point before transformation. These are the coordinates of the center point after transformation. Angle of symmetry; Step 4.3, Projection Mapping: The transformed 3D spatial coordinates from Step 4.2 are mapped onto the XOY plane using projection. The coordinate transformation formula is: X, Y, and Z are the projected planar coordinates; Step 5, pole type identification, including using template matching method to determine pole type; The implementation includes the following sub-steps: Step 5.1: Binarize the tower point cloud image. In the package, the X and Y values ​​of all point clouds are divided into grids. The width of the projection grid is set. If there are point cloud pixels in the projection grid, the projection grid value is 1; otherwise, the projection grid value is 0. Generate a binary image file with the same size as the standard tower character library. The file size is denoted as M rows and N columns. Step 5.2: Calculate the correlation coefficient between the binary image file S(m,n) of the measured tower and the file T(m,n) in the standard tower character library. R When the measured tower type matches the tower type in the standard tower character library, the correlation coefficient has a maximum value. The formula for calculating the correlation coefficient is: in, S is a file in the character library for the i-th standard tower, and S is a binary image file of the measured tower. Let be the value in the m-th row and n-th column of the file in the i-th standard tower character library. Let m be the value of the m-th row and n-th column of the binary image file of the measured tower. Let be the correlation coefficient between the file in the character library of the i-th standard tower and the binary image file of the measured tower.

2. The point cloud-based method for identifying transmission line tower types according to claim 1, characterized in that: Step 2 is implemented by including the following sub-steps: Step 2.1: Use UAV lidar or tilt measurement technology to obtain the 3D point cloud of the tower scene; Step 2.2: Remove noise data to obtain force survey data that includes power towers, ground lines, and surrounding vegetation; Step 2.3, gridding the point cloud, includes projecting the point cloud onto the horizontal XY coordinate system along the vertical direction, dividing it into grids, determining the grid position of each point cloud, and realizing the ordering of the point cloud; Step 2.4, extraction of the transmission tower grid region, includes calculating the local maximum and minimum elevation values ​​and local elevation differences in each segmented grid. Considering the characteristic of transmission towers having large elevation differences, an elevation difference threshold is set to remove grid regions containing ground, low vegetation, and other non-transmission tower point clouds. Based on the continuity of the elevation distribution of the tower point clouds, the areas where transmission lines are located are removed. Combining the local extreme elevation characteristics, the maximum elevation value of the tower is used as the standard to quickly filter out tall forest areas, finally obtaining the transmission tower grid region. Step 2.5, Tower Point Cloud Extraction, includes extracting point clouds at all elevations within a range slightly larger than the grid, centered on the local elevation maximum point of the point cloud at the top of the tower, calculating the minimum elevation within the grid as the ground elevation, setting it as the threshold to remove ground points and tower foot point clouds, and extracting the tower head and tower body point clouds.

3. A point cloud-based power transmission tower type identification system, characterized in that: This method is used to implement a point cloud-based method for identifying the type of power transmission pole as described in any one of claims 1-2.

4. The point cloud-based transmission line tower type identification system according to claim 3, characterized in that: Includes the following modules, The first module is used for creating a pole and tower type dataset, including converting standard pole and tower models into image files with consistent height and width, and establishing a standard pole and tower character library. The second module is used for point cloud extraction of power transmission towers, including removing noise and power line point clouds contained in the point cloud measured by UAV, and extracting the point cloud of power transmission towers; The third module is used for calculating the symmetry axis of the tower, including calculating the symmetry axis of the tower's measured point cloud by counting the number of points in each angular direction; The fourth module is used for reprojection of tower point clouds, including projecting the measured point cloud of the tower onto the tower's axis of symmetry using coordinate transformation. The fifth module is used for pole / tower type identification, including determining the pole / tower type using a template matching method.

5. The point cloud-based transmission line tower type identification system according to claim 3, characterized in that: It includes a processor and a memory, the memory being used to store program instructions, and the processor being used to call the stored instructions in the memory to execute the point cloud-based transmission line tower type identification method as described in any one of claims 1-2.

6. The point cloud-based transmission line tower type identification system according to claim 3, characterized in that: The method includes a readable storage medium on which a computer program is stored, and when the computer program is executed, it implements a point cloud-based method for identifying the type of power transmission pole tower as described in any one of claims 1-2.

Images