CN117152172A - Point cloud data-based power transmission line tower and power line extraction method - Google Patents
Point cloud data-based power transmission line tower and power line extraction method Download PDFInfo
- Publication number
- CN117152172A CN117152172A CN202311124624.XA CN202311124624A CN117152172A CN 117152172 A CN117152172 A CN 117152172A CN 202311124624 A CN202311124624 A CN 202311124624A CN 117152172 A CN117152172 A CN 117152172A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- tower
- grid
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 43
- 230000005540 biological transmission Effects 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 40
- 230000009466 transformation Effects 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000011179 visual inspection Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract 2
- 238000013473 artificial intelligence Methods 0.000 abstract 1
- 238000013135 deep learning Methods 0.000 abstract 1
- 238000005457 optimization Methods 0.000 abstract 1
- 238000000513 principal component analysis Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
- G06F9/3885—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a power transmission line tower and a power line extraction method based on point cloud data, which relate to the technical field of point cloud semantic segmentation, and the power transmission line tower and the power line extraction method based on the point cloud data. By introducing parallel computing and distributed processing technologies, the computing load of an algorithm is dispersed to a plurality of computing units, so that the processing speed is greatly improved, and quick extraction of a line tower and a power line is realized; advanced technologies such as deep learning and artificial intelligence are introduced, a highly self-adaptive line pole tower and power line extraction model is constructed, automatic adjustment and optimization can be carried out according to the characteristics of different scenes, accurate extraction of complex scenes is achieved, and accuracy and stability of extraction results are further improved.
Description
Technical Field
The invention relates to the technical field of point cloud semantic segmentation, in particular to a power transmission line tower and power line extraction method based on point cloud data.
Background
Traditional transmission line towers and power line extraction methods mainly rely on manual interpretation of aerial images, remote sensing images or aerial images. And extracting the position information of the line towers and the power lines through manual interpretation. The method for extracting the power transmission line towers and the power lines based on the point cloud data is characterized in that the point cloud data is acquired by using a laser radar or a three-dimensional scanner and the like, and the positions, the shapes and the characteristics of the towers and the power lines in the power transmission line are extracted through a series of algorithms and processing steps.
The existing power transmission line tower and power line extraction method still has the following defects:
1) In the prior art, the extraction method of the transmission line tower and the power line is often limited by the quality of point cloud data, so that the accuracy of an extraction result is not high. The point cloud data may have problems such as noise, occlusion, incompleteness, and the like, and the accuracy of the extraction algorithm is affected.
2) The prior art transmission line towers and power line extraction methods typically require significant computational resources and time. The traditional algorithm usually adopts an iterative or global search mode to identify and extract the line towers and the power lines, and the method has lower efficiency when processing large-scale point cloud data.
3) The power transmission line tower and power line extraction method in the prior art is difficult to adapt to complex scenes and difficult to extract by a traditional rule or template matching method.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a power transmission line tower and power line extraction method based on point cloud data, which solves the problems that the power transmission line tower and power line extraction method in the prior art is often limited by the quality of the point cloud data, so that the accuracy of an extraction result is not high, noise, shielding, incomplete and the like can exist in the point cloud data, the accuracy of an extraction algorithm is influenced, a large amount of calculation resources and time are generally required to be consumed in the power transmission line tower and power line extraction method, the efficiency is low when large-scale point cloud data are processed, and the power transmission line tower and power line extraction method are difficult to adapt to complex scenes and difficult to extract by a traditional rule or template matching method.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a power transmission line pole tower and power line extraction method based on point cloud data specifically comprises the following steps:
s1, inputting point cloud data for data preprocessing;
s2, performing integral redirection on the preprocessed point cloud data;
s3, dividing grids according to given grid sizes, and calculating the point cloud coordinates after rotation;
s4, performing two-dimensional grid division on the rotated point cloud projection to an XY plane, establishing a histogram for Z coordinate values of points in each grid according to the point cloud category distribution conditions in different grids, and acquiring candidate towers and power line distribution areas by judging Z coordinate difference delta Z of the lowest point and the highest point in each grid;
s5, taking a single tower as a processing object, and precisely extracting the tower and the power line through the steps of lower vegetation removal, ground point filtration, tower redirection and accessory part points.
Further, in the step S1, the point cloud data includes position information, color information, intensity information, and normal vector information.
Further, in the step S1, the point cloud preprocessing method includes:
s11, data cleaning: the point cloud data may contain outliers, noise, or incomplete portions, requiring data cleansing. Outliers and noise can be removed using gaussian or statistical filtering methods to improve data quality and consistency;
s12, extracting information: extracting position and shape information of a tower and a power line from the point cloud data through algorithms such as feature extraction, target detection and the like;
s13, through a model fitting and optimizing algorithm, accuracy and stability of an extraction result are improved.
Further, in the step S2, the method for redirecting the preprocessed point cloud data integrally includes:
s21, determining a coordinate system: firstly, determining a target coordinate system or a reference frame, wherein the coordinate system is a global coordinate system or a local coordinate system;
s22, calculating rigid transformation parameters: according to the target coordinate system and the initial coordinate system of the point cloud data, calculating rigid transformation parameters including rotation angles, translation matrixes and scaling through matching of corresponding points or characteristic points;
s23, applying a rigid body transformation: using the calculated rigid transformation parameters, implementing integral redirection of the point cloud data through matrix multiplication, and carrying out coordinate transformation on each point in the point cloud;
s24, verifying a redirection effect: the redirected point cloud data is aligned with a target coordinate system or a reference frame, and the redirecting effect is verified through visual inspection, calculation of the overlapping degree or the alignment degree of other data.
Further, in the step S3, the grids are divided according to the given grid size, and the specific method for calculating the point cloud coordinates after rotation is as follows:
s31, determining the mesh size: determining the size of the grids according to the requirements, and using a two-dimensional grid with the grid side length d, wherein the size of the grids is determined by the side length or width of each grid;
s32, rotation transformation: performing rotation transformation on the point cloud according to the requirement, wherein the rotation transformation can be described by a rotation matrix, the rotation matrix comprises a rotation angle and a rotation center, and the rotation matrix can be calculated according to the rotation angle;
s33, grid division: dividing the rotated point cloud into grids, traversing each point in the rotated point cloud, calculating the position coordinates of the point cloud corresponding to the point in the grids, dividing the coordinates of the point cloud by the grid side length, and rounding to obtain the grid index where the point is located;
s34, calculating grid center coordinates: for index (i, j) of each grid, the center coordinates of the grid can be calculated by multiplying (i, j) by the grid side length. Assuming that the lower left corner of the mesh is the origin, the coordinates of the mesh center are (x, y) = (i x d+d/2, j x d+d/2).
Further, in S4, the point clouds in the divided grid may be classified into three types: the system comprises earth surface point cloud data (comprising earth surface points and vegetation points), mixed distribution of power line point cloud and earth surface point cloud data and mixed distribution of electric tower point cloud and earth surface point cloud data respectively.
Further, in S12, the feature extraction method includes calculating a normal vector or curvature of the point cloud or a surface descriptor.
Further, in S4, if Δz is greater than the threshold, it is determined as the candidate region.
Advantageous effects
The invention provides a power transmission line tower and a power line extraction method based on point cloud data. Compared with the prior art, the method has the following beneficial effects:
1. the method comprises the steps of preprocessing point cloud data, including point cloud filtering, point cloud registration and the like, so as to improve the quality and consistency of the data. Then, the position and shape information of the towers and the power lines are extracted from the point cloud data through algorithms such as feature extraction and target detection. Finally, the accuracy and stability of the extraction result are further improved through a model fitting and optimizing algorithm.
2. The invention relates to a power transmission line pole and power line extraction method based on point cloud data.
3. The invention discloses a power transmission line tower and power line extraction method based on point cloud data.
4. The invention discloses a power transmission line pole and power line extraction method based on point cloud data.
Drawings
FIG. 1 is a diagram of an original point cloud grid division of the present invention;
FIG. 2 is a graph of overall redirection of point clouds and grid partitioning in accordance with the present invention;
FIG. 3 is a histogram of elevation distribution of ground points according to the present invention;
FIG. 4 is a histogram of elevation distribution and segmentation threshold selection of the power line point cloud and the ground point cloud data according to the present invention;
FIG. 5 is a histogram of elevation distribution of point cloud and surface point cloud data for a tower in accordance with the present invention;
FIG. 6 is a graph of 17 adjacent voxel cell units grown downward in accordance with the present invention;
FIG. 7 is a floor filter diagram of the present invention;
FIG. 8 is a projection view of an original tower of the present invention;
FIG. 9 is a projection view of the tower of the present invention after redirection;
FIG. 10 is a view of a neighborhood of an upwardly grown two-dimensional grid 5 of the present invention;
fig. 11 is a graph of the extraction results of the towers, the power lines and the ground points of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1-11, the present invention provides a technical solution: a power transmission line pole tower and power line extraction method based on point cloud data specifically comprises the following steps:
s1, inputting point cloud data for data preprocessing;
s2, performing integral redirection on the preprocessed point cloud data; because the point clouds of the power transmission line are distributed in a band shape and along any trend, if the point clouds are subjected to grid division directly, a large number of empty grids can be generated, memory occupation can be caused, and the calculation efficiency is low, so that in order to improve the grid utilization rate, the original point clouds are rotated by an angle alpha along the Z axis, and the whole trend of the power transmission line is kept parallel to the X axis or the Y axis. The rotation angle and the point cloud after rotation calculation method are as follows:
(1) Randomly sampling Nr points from the original point cloud set p= { pi|pi= (xi, yi, zi), i=1, 2, …, N }, projecting the Nr points to an XY plane, and calculating a feature value λ1, λ2 (λ1> λ2) of the sampling point set pr= { pi|pi= (xi, yi, zi), i=1, 2, …, nr } and a feature vector v1, v2 (v 21, v 22) corresponding thereto by using a principal component analysis (Principal Component Analysis, PCA) algorithm, wherein the calculation formula is as follows:
(2) Calculating the rotation angle alpha by taking v2 as the X axis after rotation
(3) Calculation of post-rotation point coordinates (x) by rotation angle α and original point coordinates i ′y i ′z i ′)。
S3, dividing grids according to given grid sizes, and calculating the point cloud coordinates after rotation;
s4, performing two-dimensional grid division on the rotated point cloud projection to an XY plane, establishing a histogram for Z coordinate values of points in each grid according to the point cloud category distribution conditions in different grids, and acquiring candidate towers and power line distribution areas by judging Z coordinate difference delta Z of the lowest point and the highest point in each grid; two-dimensional grid division is carried out on the projection of the rotated point cloud to an XY plane, and the point cloud in the divided grid can be divided into three types: surface point cloud data (including ground points and vegetation points), a hybrid distribution of power line point clouds and surface point cloud data, and a hybrid distribution of tower point clouds and surface point cloud data. Therefore, according to the distribution condition of the point cloud categories in different grids, a histogram is established for the Z coordinate values of the points in each grid, and candidate towers and power line distribution areas are obtained by judging the Z coordinate difference value of the lowest point and the highest point in each grid. The method comprises the following specific steps:
(1) Because the elevation change of the surface point cloud data is continuous, and the elevation value is usually far lower than the elevation of the pole tower, the elevation histogram of the surface point cloud data can form continuous distribution in a small range in the Z direction, so that the grid does not contain the power line point cloud and the electric tower point cloud, does not need any special classification treatment, and is totally classified as the surface point cloud and marked as a point set G.
(2) Because the elevation of the power line point cloud is greatly different from the elevation of the ground surface point cloud, the point clouds in the grid are discontinuously distributed in the Z direction. Therefore, according to a certain height value corresponding to the blank area in the elevation histogram as the segmentation threshold T1, the points with the elevations greater than T1 are the power line point clouds, the points are added into the power line point set L, the points with the elevations less than T1 are the earth surface point clouds, and the points are classified into the point set G.
(3) Since the tower body is high, it is continuously distributed in the Z direction, and there is a large variation in the height difference. Therefore, meshes with histograms continuously distributed and maximum height difference values within the mesh greater than the height threshold T2 are considered candidate tower meshes. Meanwhile, since a single mesh does not fully contain the trunk structure of the tower, 8 meshes adjacent to the equivalent previous mesh are marked as candidate tower meshes, and points in the meshes are regarded as candidate tower points and marked as a point set T.
S5, taking a single tower as a processing object, and precisely extracting the tower and the power line through the steps of lower vegetation removal, ground point filtration, tower redirection and accessory part points.
And S4, regarding the candidate tower points in the adjacent grids as coming from the same tower, and taking a single tower as a processing object. However, the grid division method cannot accurately extract the towers, and the obtained candidate tower points comprise vegetation points, ground points and power line points connected with the towers.
Removing the vegetation on the lower layer: because the tower point clouds are closely connected from top to bottom and the lower part of the tower is in a prismatic structure, the candidate tower points are processed by adopting a downward voxel unit 17 neighborhood growing algorithm, and the aim is to remove the vegetation point clouds of the lower layer. The specific process flow is as follows:
a. dividing the candidate tower points into voxel units with the unit sizes of (Vx, vy, vz), taking the voxel with the highest point as an initial seed point, and storing the initial seed point into a queue;
b. the blue voxel unit is a seed voxel unit, the adjacent 17 voxels are traversed, the voxels with point cloud are sequentially stored in a queue, the traversed voxels are marked, and then the first element in the queue is deleted;
c. repeating the step (b) until the queue is empty, completing voxel growth, and adding the removed lower vegetation point cloud (green point cloud in fig. 5) into the point set G.
And (5) ground point filtration: performing ground point filtering on candidate tower points according to a cloth filtering algorithm (CSF), and adding the filtered ground point cloud (yellow point cloud in FIG. 5) into a point set G;
tower redirection: the tower point cloud extracted from the power transmission line point cloud is oriented at will in the horizontal direction, and in order to fully utilize the symmetry of the tower structure, the main direction of the tower needs to be rotated so as to be aligned with the coordinate axis. The tower redirection flow is as follows:
PCA analysis. PCA analysis is carried out on plane coordinates of 1/3 height point clouds on the tower, and the obtained first feature vector is the cross arm direction (Y'); the second eigenvector is the power line direction (X').
b. And (5) coordinate conversion. According to the geometric relationship, calculating coordinates of the point cloud under a new coordinate system:
wherein n is a second feature vector (new x-axis direction vector), and x ', y' are coordinates of the point cloud under a new coordinate system; x and y are original plane coordinates of the point cloud; x0 and y0 are central coordinates of the tower point cloud. And (5) calculating the coordinates of the point cloud after rotation according to the formula (4).
Because the point cloud at the upper part of the tower still has accessory component points, such as wires, jumpers and the like connected with the tower, the point cloud is processed by adopting an upward two-dimensional grid 5 neighborhood growing algorithm. The method comprises the following specific steps:
a. projecting the redirected tower point cloud to a Y 'Z plane to carry out two-dimensional grid division, wherein the grid size is (Gy', gz), taking the grid where the highest point is located as an initial seed grid, and storing the initial seed grid into a queue;
b. the blue grid is a seed grid, 5 adjacent grids are traversed, the grids with point clouds are sequentially stored into a queue, the grids are marked, and then the first element in the queue is deleted;
c. repeating the step (b) until the queue is empty, completing the growth of the grid neighborhood, regarding the removed point cloud as a power line point and adding the power line point into the point set L.
In conclusion, the extraction of the pole tower point, the power line point and the ground surface point is completed.
In the embodiment of the present invention, in S1, the point cloud data includes location information: each point has a coordinate value in three-dimensional space, i.e., (x, y, z). These coordinate values may represent the geometric position of the point; color information: for some point cloud data, there may be color information representing the RGB values or other color attributes of the point. This color information may be used for visualization of the point cloud or other analysis tasks. Intensity information: the intensity information in the point cloud data represents an intensity value of each point on a certain attribute. For example, for laser scanning point cloud data, the intensity information may represent the intensity of the signal returned by the laser; normal vector information: for point cloud data generated using a ray tracing method or other computational geometry method, a normal vector for each point is calculated for representing the orientation of the point and the curvature of the surface.
In the embodiment of the invention, in S1, the point cloud preprocessing method comprises the following steps:
s11, data cleaning: the point cloud data may contain outliers, noise, or incomplete portions, requiring data cleansing. Outliers and noise can be removed using gaussian or statistical filtering methods to improve data quality and consistency;
s12, extracting information: extracting position and shape information of a tower and a power line from the point cloud data through algorithms such as feature extraction, target detection and the like;
s13, through a model fitting and optimizing algorithm, accuracy and stability of an extraction result are improved.
In the embodiment of the present invention, in S2, the method for redirecting the preprocessed point cloud data integrally includes:
s21, determining a coordinate system: firstly, determining a target coordinate system or a reference frame, wherein the coordinate system is a global coordinate system or a local coordinate system;
s22, calculating rigid transformation parameters: according to the target coordinate system and the initial coordinate system of the point cloud data, calculating rigid transformation parameters including rotation angles, translation matrixes and scaling through matching of corresponding points or characteristic points;
s23, applying a rigid body transformation: using the calculated rigid transformation parameters, implementing integral redirection of the point cloud data through matrix multiplication, and carrying out coordinate transformation on each point in the point cloud;
s24, verifying a redirection effect: the redirected point cloud data is aligned with a target coordinate system or a reference frame, and the redirecting effect is verified through visual inspection, calculation of the overlapping degree or the alignment degree of other data.
In S3, dividing grids according to given grid sizes, and calculating the point cloud coordinates after rotation specifically comprises the following steps:
s31, determining the mesh size: determining the size of the grids according to the requirements, and using a two-dimensional grid with the grid side length d, wherein the size of the grids is determined by the side length or width of each grid;
s32, rotation transformation: performing rotation transformation on the point cloud according to the requirement, wherein the rotation transformation can be described by a rotation matrix, the rotation matrix comprises a rotation angle and a rotation center, and the rotation matrix can be calculated according to the rotation angle;
s33, grid division: dividing the rotated point cloud into grids, traversing each point in the rotated point cloud, calculating the position coordinates of the point cloud corresponding to the point in the grids, dividing the coordinates of the point cloud by the grid side length, and rounding to obtain the grid index where the point is located;
s34, calculating grid center coordinates: for index (i, j) of each grid, the center coordinates of the grid can be calculated by multiplying (i, j) by the grid side length. Assuming that the lower left corner of the mesh is the origin, the coordinates of the mesh center are (x, y) = (i x d+d/2, j x d+d/2).
In the embodiment of the present invention, in S4, the point clouds in the divided grid may be classified into three types: the system comprises earth surface point cloud data (comprising earth surface points and vegetation points), mixed distribution of power line point cloud and earth surface point cloud data and mixed distribution of electric tower point cloud and earth surface point cloud data respectively.
In the embodiment of the invention, in S12, the feature extraction method includes calculating a normal vector or curvature or surface descriptor of the point cloud.
In the embodiment of the present invention, in S4, Δz is greater than a threshold, and it is determined as a candidate region.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A power transmission line pole tower and power line extraction method based on point cloud data is characterized in that: the method specifically comprises the following steps:
s1, inputting point cloud data for data preprocessing;
s2, performing integral redirection on the preprocessed point cloud data;
s3, dividing grids according to given grid sizes, and calculating the point cloud coordinates after rotation;
s4, performing two-dimensional grid division on the rotated point cloud projection to an XY plane, establishing a histogram for Z coordinate values of points in each grid according to the point cloud category distribution conditions in different grids, and acquiring candidate towers and power line distribution areas by judging Z coordinate difference delta Z of the lowest point and the highest point in each grid;
s5, taking a single tower as a processing object, and precisely extracting the tower and the power line through the steps of lower vegetation removal, ground point filtration, tower redirection and accessory part points.
2. The method for extracting the power transmission line tower and the power line based on the point cloud data according to claim 1, wherein the method comprises the following steps of: in the step S1, the point cloud data includes position information, color information, intensity information, and normal vector information.
3. The method for extracting the power transmission line tower and the power line based on the point cloud data according to claim 1, wherein the method comprises the following steps of: in the step S1, the point cloud preprocessing method comprises the following steps:
s11, data cleaning: the point cloud data may contain outliers, noise, or incomplete portions, requiring data cleansing. Outliers and noise can be removed using gaussian or statistical filtering methods to improve data quality and consistency;
s12, extracting information: extracting position and shape information of a tower and a power line from the point cloud data through algorithms such as feature extraction, target detection and the like;
s13, through a model fitting and optimizing algorithm, accuracy and stability of an extraction result are improved.
4. The method for extracting the power transmission line tower and the power line based on the point cloud data according to claim 1, wherein the method comprises the following steps of: in the step S2, the method for redirecting the preprocessed point cloud data integrally includes:
s21, determining a coordinate system: firstly, determining a target coordinate system or a reference frame, wherein the coordinate system is a global coordinate system or a local coordinate system;
s22, calculating rigid transformation parameters: according to the target coordinate system and the initial coordinate system of the point cloud data, calculating rigid transformation parameters including rotation angles, translation matrixes and scaling through matching of corresponding points or characteristic points;
s23, applying a rigid body transformation: using the calculated rigid transformation parameters, implementing integral redirection of the point cloud data through matrix multiplication, and carrying out coordinate transformation on each point in the point cloud;
s24, verifying a redirection effect: the redirected point cloud data is aligned with a target coordinate system or a reference frame, and the redirecting effect is verified through visual inspection, calculation of the overlapping degree or the alignment degree of other data.
5. The method for extracting the power transmission line tower and the power line based on the point cloud data according to claim 1, wherein the method comprises the following steps of: in the step S3, the grids are divided according to the given grid size, and the specific method for calculating the point cloud coordinates after rotation is as follows:
s31, determining the mesh size: determining the size of the grids according to the requirements, and using a two-dimensional grid with the grid side length d, wherein the size of the grids is determined by the side length or width of each grid;
s32, rotation transformation: performing rotation transformation on the point cloud according to the requirement, wherein the rotation transformation can be described by a rotation matrix, the rotation matrix comprises a rotation angle and a rotation center, and the rotation matrix can be calculated according to the rotation angle;
s33, grid division: dividing the rotated point cloud into grids, traversing each point in the rotated point cloud, calculating the position coordinates of the point cloud corresponding to the point in the grids, dividing the coordinates of the point cloud by the grid side length, and rounding to obtain the grid index where the point is located;
s34, calculating grid center coordinates: for index (i, j) of each grid, the center coordinates of the grid can be calculated by multiplying (i, j) by the grid side length. Assuming that the lower left corner of the mesh is the origin, the coordinates of the mesh center are (x, y) = (i x d+d/2, j x d+d/2).
6. The method for extracting the power transmission line tower and the power line based on the point cloud data according to claim 1, wherein the method comprises the following steps of: in the step S4, the point clouds in the divided grids may be classified into three types: the system comprises earth surface point cloud data (comprising earth surface points and vegetation points), mixed distribution of power line point cloud and earth surface point cloud data and mixed distribution of electric tower point cloud and earth surface point cloud data respectively.
7. A transmission line tower and power line extraction method based on point cloud data according to claim 3, wherein: in S12, the feature extraction method includes calculating a normal vector or curvature of the point cloud or a surface descriptor.
8. The method for extracting the power transmission line tower and the power line based on the point cloud data according to claim 1, wherein the method comprises the following steps of: in S4, if Δz is greater than the threshold value, it is determined as a candidate region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311124624.XA CN117152172A (en) | 2023-09-01 | 2023-09-01 | Point cloud data-based power transmission line tower and power line extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311124624.XA CN117152172A (en) | 2023-09-01 | 2023-09-01 | Point cloud data-based power transmission line tower and power line extraction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117152172A true CN117152172A (en) | 2023-12-01 |
Family
ID=88900250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311124624.XA Pending CN117152172A (en) | 2023-09-01 | 2023-09-01 | Point cloud data-based power transmission line tower and power line extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152172A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117994469A (en) * | 2024-04-07 | 2024-05-07 | 国网浙江省电力有限公司宁波供电公司 | Unmanned aerial vehicle-based power line panoramic image generation method and system |
-
2023
- 2023-09-01 CN CN202311124624.XA patent/CN117152172A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117994469A (en) * | 2024-04-07 | 2024-05-07 | 国网浙江省电力有限公司宁波供电公司 | Unmanned aerial vehicle-based power line panoramic image generation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108198244B (en) | Apple leaf point cloud simplification method and device | |
| CN112070769B (en) | Layered point cloud segmentation method based on DBSCAN | |
| CN111598916A (en) | Preparation method of indoor occupancy grid map based on RGB-D information | |
| US9064151B2 (en) | Device and method for detecting plantation rows | |
| CN111598780B (en) | Terrain adaptive interpolation filtering method suitable for airborne LiDAR point cloud | |
| CN112883878B (en) | Automatic point cloud classification method under transformer substation scene based on three-dimensional grid | |
| CN111783721B (en) | Lane line extraction method of laser point cloud and electronic equipment | |
| CN115049925B (en) | Field ridge extraction method, electronic device and storage medium | |
| CN115222625A (en) | Laser radar point cloud denoising method based on multi-scale noise | |
| CN116704333B (en) | Single tree detection method based on laser point cloud data | |
| CN117152172A (en) | Point cloud data-based power transmission line tower and power line extraction method | |
| CN113920134A (en) | Slope ground point cloud segmentation method and system based on multi-line laser radar | |
| CN115797813B (en) | Water environment pollution detection method based on aerial image | |
| WO2024120437A1 (en) | Bottom surface segmentation method and apparatus for three-dimensional point cloud, and electronic device and storage medium | |
| CN114842262A (en) | Laser point cloud ground object automatic identification method fusing line channel orthographic images | |
| CN113345094A (en) | Electric power corridor safety distance analysis method and system based on three-dimensional point cloud | |
| CN116523898A (en) | Tobacco phenotype character extraction method based on three-dimensional point cloud | |
| CN115410036A (en) | Automatic classification method for key element laser point clouds of high-voltage overhead transmission line | |
| CN117635615B (en) | Defect detection method and system for realizing punching die based on deep learning | |
| CN114898118A (en) | Automatic statistical method and system for power transmission line house removal amount based on multi-source point cloud | |
| CN109712116B (en) | Fault identification method for power transmission line and accessories thereof | |
| CN116186864B (en) | Deep foundation pit model rapid modeling method and system based on BIM technology | |
| CN117541786A (en) | Single plant vegetation fine segmentation method integrating multi-source point cloud data | |
| CN116452604A (en) | Complex substation scene segmentation method, device and storage medium | |
| CN114743059B (en) | Automatic classification method for submarine geographic entities by integrating topographic features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |