CN117808287A - Comprehensive evaluation method for potential risk of overhead line - Google Patents
Comprehensive evaluation method for potential risk of overhead line Download PDFInfo
- Publication number
- CN117808287A CN117808287A CN202311755143.9A CN202311755143A CN117808287A CN 117808287 A CN117808287 A CN 117808287A CN 202311755143 A CN202311755143 A CN 202311755143A CN 117808287 A CN117808287 A CN 117808287A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- transmission line
- power transmission
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 17
- 230000005540 biological transmission Effects 0.000 claims abstract description 174
- 238000000034 method Methods 0.000 claims abstract description 38
- 230000003068 static effect Effects 0.000 claims abstract description 24
- 238000012502 risk assessment Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 23
- 230000011218 segmentation Effects 0.000 claims description 15
- 239000000725 suspension Substances 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 5
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 6
- 238000013075 data extraction Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000013209 evaluation strategy Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000003102 growth factor Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012732 spatial analysis Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to the field of power transmission line risk assessment, and particularly discloses a comprehensive assessment method for potential risks of an overhead line, which comprises the following steps: acquiring point cloud data of an overhead line and preprocessing the point cloud data; dividing the preprocessed point cloud data into ground point cloud data, transmission line point cloud data, pole tower point cloud data, building point cloud data and vegetation point cloud data; constructing a cylindrical bounding box according to the power transmission line point cloud data, evaluating potential risks of a static target ground and a building to an overhead line based on the cylindrical bounding box, the ground point cloud data and the building point cloud data, and evaluating potential risks of a dynamic target power transmission line and vegetation to the overhead line based on preset power transmission line and vegetation swing data, the power transmission line point cloud data and the vegetation point cloud data. The method can realize comprehensive evaluation based on the static target and the dynamic target, and effectively solve the problem that the potential risk of the power transmission line cannot be comprehensively evaluated due to the fact that the dynamic target analysis is absent in the prior art.
Description
Technical Field
The invention belongs to the field of power transmission line risk assessment, and particularly relates to a comprehensive assessment method for potential risks of an overhead line.
Background
Overhead lines are a common transmission mode during long-distance transmission and terrain crossing, and many potential safety hazards exist around the overhead lines, so that specific line inspection personnel need to be regularly arranged for safety inspection. In addition, in the working area where the power transmission line cannot enter or is dangerous, the accurate judgment of whether the power transmission line has potential safety hazard by line inspection personnel is still a difficult task. With the development of unmanned aerial vehicle and laser radar technology, unmanned aerial vehicle at present stage can rely on laser radar to acquire three-dimensional space information around the transmission line fast and accurately, and this can also help the personnel of patrolling and examining to patrol and examine in the dangerous area that can't get into when improving operating efficiency, has ensured personnel's safety of patrolling and examining personnel. The airborne laser radar can rapidly and safely acquire point cloud data around the power transmission line, but the power transmission line point cloud has the problems of large data volume, lack of semantic information and the like, so that the potential risk assessment of the line cannot be automatically or semi-automatically performed.
Currently, existing power line risk assessment methods can detect potential hazards based on point cloud data. However, most methods analyze based on the assumption that the detection target is a static object, and the detection result will deviate greatly from the actual situation over time. The space Euclidean distance detection method based on static assumption does not consider the condition that the power transmission line or vegetation is influenced by wind power to deviate, and can not predict potential risks. In addition, due to the limitation of line inspection work arrangement and the number of unmanned aerial vehicle equipment, the revisiting time interval of the power transmission line is longer, and vegetation can grow continuously along with the time during the revisiting time interval. Therefore, when the vegetation is in an idle stage in which the transmission line cannot be revisited, the vegetation and the transmission line are easy to generate contact risks. Therefore, the current method has the problems that dynamic target analysis is omitted or vegetation growth rate is ignored, so that potential risks of the power transmission line cannot be comprehensively evaluated.
Disclosure of Invention
Aiming at the defects or improvement demands of the prior art, the invention provides a comprehensive evaluation method for potential risks of an overhead line, which aims to solve the problems of incomplete evaluation and inaccurate results in the prior art.
In order to achieve the above purpose, the invention provides a comprehensive evaluation method for potential risks of an overhead line, which comprises the following steps: s1, acquiring point cloud data of an overhead line and preprocessing the point cloud data;
s2, dividing the preprocessed point cloud data into ground point cloud data and non-ground point cloud data; extracting power line point cloud data from non-ground point cloud data, and taking the rest point cloud data as non-power line point cloud data; dividing non-transmission line point cloud data into tower point cloud data and non-tower point cloud data; extracting building point cloud data from non-tower point cloud data, and taking the rest data as vegetation point cloud data;
and S3, constructing a cylindrical bounding box according to the power transmission line point cloud data, evaluating potential risks of the static target ground and the building to the overhead line based on the cylindrical bounding box, the ground point cloud data and the building point cloud data, and evaluating potential risks of the dynamic target power transmission line and the vegetation to the overhead line based on preset power transmission line and vegetation swing data, the power transmission line point cloud data and the vegetation point cloud data, so that comprehensive evaluation of the potential risks of the overhead line is realized.
As a further preferred aspect, the preprocessing is specifically voxel segmentation of the point cloud data based on a preset voxel size.
As a further preferred feature, the division of the point cloud data into ground point cloud data and non-ground point cloud data is specifically: firstly, extracting each column of voxels of the preprocessed point cloud data along the Z-axis direction, then taking the first non-empty voxel from bottom to top of each column of voxels as a ground candidate voxel, finally extracting ground points from all the ground candidate voxels as final ground point cloud data, and taking the rest point cloud data as non-ground point cloud data.
As a further preferred aspect, the following method is used to extract the power line point cloud data:
(1) Taking non-ground point cloud data as input data, using a vertical axis to represent a Z coordinate range of the voxels, and using a horizontal axis to represent the number of point clouds contained in the voxels to construct a two-dimensional histogram of each column of voxels;
(2) Extracting voxels higher than a preset suspension height H from the two-dimensional histogram of each column of voxels as power transmission line candidate voxels;
(3) Extracting voxels with the number of point clouds larger than T from the transmission line candidate voxels as the transmission line candidate point clouds, wherein the calculation formula of T is as follows:
wherein N represents the number of point clouds in the range from a preset suspension height H to maxZ in each column of voxels; Δh represents the number of voxels ranging from a preset suspension height H to maxZ in each column of voxels, and maxZ represents the maximum value of the Z axis direction determined during preprocessing;
(4) And carrying out neighborhood search on all the power transmission line candidate point clouds, carrying out principal component analysis on each point, obtaining the characteristic value of each power transmission line candidate point cloud, and screening out point cloud data meeting the conditions based on the characteristic value to serve as power transmission line point cloud data.
As a further preferred aspect, the division of the non-power line point cloud data into the tower point cloud data and the non-tower point cloud data is specifically:
(1) Taking non-power line point cloud data as input data, counting the number of voxels containing the input data in each column of voxels of the point cloud data after preprocessing, and taking the column of voxels with the number greater than that of other columns in a neighborhood range as alternative tower data;
(2) And analyzing all the alternative tower data, and considering the alternative tower voxels as tower data if the transmission line voxels exist in the neighborhood of the alternative tower voxels, or else, judging the alternative tower voxels as non-tower data.
As a further preferred aspect, the building point cloud data is extracted by: and extracting a plane with adjacent relation to the building point cloud from the rest of the potential building plane point clouds by adopting a recursion method as a new building point cloud until the building point cloud does not exist in the potential building plane point clouds, thereby completing the extraction of the building point cloud data.
As a further preferred, step S3 comprises the following sub-steps:
s31, constructing a cylindrical bounding box based on the power transmission line point cloud data;
s32, static target potential risk assessment:
s321 calculates the distance d of each ground point and building point to the nearest cylindrical bounding box according to the following equation:
wherein vector c represents the axial vector of the cylinder, p a Representing ground points or building points;
s322 judges whether or not the distance d isPreset safety distance r a Inner: if d is less than or equal to r a The ground points or the building points are considered to be in the cylindrical bounding box, so that potential safety hazards of the overhead line are indicated; if d>r s And if the ground point or the building point is not in the cylindrical bounding box, the overhead line is considered to have no potential safety hazard.
S33, dynamic target potential risk assessment:
s331, calculating the nearest distances between different power lines or between the power lines and vegetation by adopting the following formula:
l h ＝H ab -S a -S b
wherein l h Represents the nearest distance, H ab Represents the horizontal distance between object a and object b, S a And S is b Representing the horizontal swing distance of target a and target b;
s332 calculates a safe distance d between transmission lines using the following formula:
wherein c 1 And c 2 Axial quantity of cylindrical bounding box representing different power lines, o 1 And o 2 Representing points on the cylinder axis, |·| representing norms;
calculating the safety distance d between vegetation and a power transmission line by adopting the following steps:
wherein vector c represents the axial vector of the cylinder, p T Representing vegetation points;
s333, judging whether the nearest distance between different power transmission lines or between the power transmission lines and vegetation is larger than the corresponding safety distance, if so, indicating that the overhead line has no safety hidden trouble, and if not, indicating that the overhead line has the safety hidden trouble.
As a further preferred embodiment, step S33 further comprises the following sub-steps:
s334, calculating time T for vegetation to reach the safety range of the power transmission line by adopting the following formula, and performing early warning in advance:
wherein H represents the vertical height from the top of the vegetation to the cylindrical bounding box of the transmission line right above the vegetation, and G represents the growth rate.
As a further preferred aspect, the step S31 includes the following substeps:
s311, taking the power transmission line point cloud data as input data, and acquiring an independent power transmission line point cloud set L= { L 1 ,l 2 ,…l i …l n N represents the number of power lines;
s312, taking out a power transmission line point cloud L from the power transmission line point cloud set L i From l i Any point is selected as a starting point to carry out depth-first traversal, and a traversal end point is used as l i Suspension point S of (2) L In S form L Depth-first traversal is performed with the traversal end point as l i Suspension point S at the other end of (2) R The power transmission line l i The minimum point of Z value is taken as the minimum point S D ；
S313 calculation S L To S D Number of transmission line segments n l Calculate S R To S D The number of transmission line segments n R According to the number n of segments L And n R Pair l i Dividing to obtain a divided segment set C= { C 1 ,c 2 ,…c i …c n N represents the sum of the values of l i Is a number of segments;
s314, a segment of the segmentation point cloud C is taken out of the segmentation segment set C i C i The connecting line of the two end points is used as a cylinder axis vector and a preset safety distance r is used as a connecting line of the two end points s Constructing a cylindrical bounding box as a radius;
s315, repeating the step S314 until the construction of the cylindrical bounding boxes of all the partitioned point cloud segments in the partitioned segment set C is completed;
s316, repeating the steps S312-S315 until the construction of the cylindrical bounding boxes of all the power transmission line point clouds in the power transmission line point cloud set L is completed.
As a further preferred aspect, the transmission line segment number n L The following formula is adopted for calculation:
wherein p is L Represent S L To S D Distance in transmission line of section is defined by S L And S is D Three-dimensional coordinates, x, of the point with the furthest vector D ,y D ,z D Is S D Coordinate value of x L ,y L ,z L Is S D Is set in the coordinate value of (a).
As a further preferred aspect, the transmission line segment number n R The following formula is adopted for calculation:
wherein p is R Represent S R To S D Distance in transmission line of section is defined by S R And S is D Three-dimensional coordinates, x, of the point with the furthest vector D ,y D ,z D Is S D Coordinate value of x R ,y R ,z R Is S R Is set in the coordinate value of (a).
In general, compared with the prior art, the above technical solution conceived by the present invention mainly has the following technical advantages:
1. according to the method, ground, power transmission line, pole tower, building and vegetation data are extracted from overhead line point cloud data one by one, static targets, namely ground and building data, are effectively distinguished from dynamic targets, namely power transmission line and vegetation data, risk assessment is carried out based on the static targets and the dynamic targets, comprehensive assessment based on the static targets and the dynamic targets can be achieved, comprehensiveness and accuracy of assessment are guaranteed, and the problem that potential risks of a power transmission line cannot be comprehensively assessed in the prior art is effectively solved.
2. The method also considers the influence of vegetation growth, integrates vegetation growth factors into the evaluation method, and can effectively solve the problem that the potential risk of the power transmission line cannot be comprehensively evaluated due to the fact that the vegetation growth rate is ignored in the existing method.
3. The invention also provides improvement on the extraction of the ground point cloud data, and the accuracy of the ground point cloud extraction can be effectively improved by firstly extracting each column of voxels of the preprocessed point cloud data along the Z-axis direction and then taking the first non-empty voxel of each extracted column of voxels from bottom to top as a ground alternative voxel.
4. The invention also provides improvement on the extraction of the building and vegetation point cloud data, and the building and vegetation point cloud is distinguished by recursively extracting the planes in the point cloud, so that an accurate data basis is provided for analyzing the potential risk of the overhead line.
5. Aiming at the characteristic of sag distribution of the power transmission line, the method acquires single power transmission line point cloud data from the power transmission line point cloud data, then segments the power transmission line according to sag conditions and constructs a cylindrical bounding box, and compared with a traditional bounding box construction method, the method can more accurately detect potential risks near the power transmission line.
6. According to the method, corresponding evaluation strategies are provided in a targeted manner by combining the characteristics of different static targets and different dynamic targets and the correspondingly extracted point cloud data, and comprehensive and accurate evaluation of the safety of the power transmission line can be realized through comprehensive evaluation of the static targets and the dynamic targets.
Drawings
Fig. 1 is a flowchart of a comprehensive evaluation method for potential risks of an overhead line according to an embodiment of the present invention;
fig. 2 is a block flow diagram of step S2 in the comprehensive evaluation method for potential risk of overhead line according to the embodiment of the present invention;
fig. 3 is a block flow diagram of step S3 in the comprehensive evaluation method for potential risk of overhead line according to the embodiment of the present invention;
fig. 4 is a graph of a point cloud data preprocessing result for a certain power transmission line scene provided by an embodiment of the present invention;
fig. 5 is a graph of a point cloud data separation result for a certain power transmission line scene according to an embodiment of the present invention;
fig. 6 is a diagram of risk assessment results for a certain power transmission line scenario according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
As shown in fig. 1, the embodiment of the invention provides a comprehensive evaluation method for potential risks of an overhead line, which comprises the following steps:
s1, acquiring point cloud data of an overhead line and preprocessing the point cloud data;
s2, dividing the preprocessed point cloud data into ground point cloud data and non-ground point cloud data; extracting power line point cloud data from non-ground point cloud data, and taking the rest point cloud data as non-power line point cloud data; dividing non-transmission line point cloud data into tower point cloud data and non-tower point cloud data; extracting building point cloud data from non-tower point cloud data, and taking the rest data as vegetation point cloud data;
and S3, constructing a cylindrical bounding box according to the power transmission line point cloud data, evaluating potential risks of the static target ground and the building to the overhead line based on the cylindrical bounding box, the ground point cloud data and the building point cloud data, and evaluating potential risks of the dynamic target power transmission line and the vegetation to the overhead line based on preset power transmission line and vegetation swing data, the power transmission line point cloud data and the vegetation point cloud data, so that comprehensive evaluation of the potential risks of the overhead line is realized.
By the method, the data of the static targets (ground, buildings) and the dynamic targets (power transmission lines and vegetation) in the overhead line can be respectively extracted, and the comprehensive assessment of the potential risk of the overhead line is realized based on the characteristics of the static targets and the dynamic targets.
Specifically, in step S1, the unmanned aerial vehicle may acquire point cloud data of the overhead line, and the unmanned aerial vehicle may periodically acquire related data.
Further, in step S1, the preprocessing is specifically to perform voxel segmentation on the point cloud data based on a preset voxel size.
More specifically, the pretreatment includes the steps of:
1) Voxel size setting
According to actual requirements, the size of the voxels is set, for example, the length, width and height dimensions (DeltaX, deltaY, deltaZ) are defined;
2) Computing point cloud boundaries
Obtaining maximum values (maxX, maxY, maxZ) and minimum values (minX, minY, minZ) of length, width and height by traversing the whole point cloud data, and accumulating the sizes (delta X, delta Y, delta Z) of the voxels along the X-axis, the Y-axis and the Z-axis respectively by taking the minimum values (minX, minY, minZ) as starting points until the accumulated result of each direction meets a formula (1); taking the accumulation result in each direction as a new maximum value;
wherein n is x 、n y 、n z The number of voxels in the X-axis, Y-axis and Z-axis directions is represented respectively;
3) Acquiring voxel information
Constructing n in the range of minima and maxima x *n y *n z And traversing all voxels in sequence by using a multithreading technology, detecting whether each voxel contains the point cloud, and marking the voxel as empty if the voxel does not contain the point cloud, wherein the multithreading technology is the prior art and is not described herein.
As shown in fig. 2, the purpose of step S2 is to extract point cloud data corresponding to a static target (e.g., ground, building) and a dynamic target (e.g., power line, vegetation) from the preprocessed point cloud data, respectively.
Specifically, the method comprises the following steps:
1) Ground point cloud data extraction
And (3) extracting each column of voxels along the Z-axis direction (height direction) in the preprocessed point cloud data according to the voxel information acquired in the step (S1), taking the first non-empty voxel from bottom to top of each column of extracted voxels as ground candidate voxels, extracting ground points from all the ground candidate voxels by using the prior art such as a cloth simulation algorithm and the like as a final ground point cloud data extraction result, and removing the ground point cloud data from the preprocessed point cloud data to obtain non-ground point cloud data.
2) Power transmission line point cloud data extraction
The non-ground point cloud data is used as input data, the vertical axis represents the Z coordinate range of the voxels, the horizontal axis represents the number of point clouds contained in the voxels to construct a two-dimensional histogram of each column of voxels, and as the transmission line is suspended, voxels higher than a preset suspension height H are selected from the two-dimensional histogram of each column of voxels to serve as transmission line candidate voxels, wherein the transmission line erection height is selected by H, 20m is taken in the embodiment, and secondly, as the transmission line point clouds are distributed densely locally, voxels with the number of point clouds larger than T are selected from the transmission line candidate voxels to serve as transmission line candidate point clouds, wherein the calculation method of T is shown in formula (2):
wherein N represents the number of point clouds in the range from the suspension height H to maxZ in each column of voxels; Δh represents the number of voxels in each column of voxels ranging from the suspended height H to maxZ, wherein maxZ represents the Z-axis maximum value of the voxel accumulation result during preprocessing, namely the maximum value in the Z-axis direction determined during preprocessing, namely the maximum value finally determined in the Z-axis direction;
carrying out neighborhood search on all the power transmission line candidate point clouds, and then carrying out principal component analysis on each point according to formulas (3) - (5) to obtain the characteristic value of each power transmission line candidate point cloud:
wherein X is i Representing the X-coordinate of the point cloud,represents the average value of X coordinates in a neighborhood range, Y i Representing the Y coordinate of the point cloud,/->Representing the average of the Y-coordinates in the neighborhood, n representing the number of points in each non-ground point neighborhood, cov (X, Y) representing the covariance of the X-dimension and Y-dimension coordinates;
wherein C represents covariance matrix, cov represents covariance, Q represents eigenvectors, λ 1 、λ 2 、λ 3 Representing characteristic values, wherein X, Y and Z represent coordinates of X dimension, Y dimension and Z dimension in the neighborhood search result;
because the local position of the power transmission line can be approximately a straight line, the point cloud data meeting the formula (6) in the candidate point cloud data of the power transmission line is used as the power transmission line point cloud data according to the characteristic value relation, and the power transmission line point cloud data is removed from the non-ground point cloud data to obtain the non-power transmission line point cloud data.
λ 1 ＞＞λ 2 ≈λ 3 (6)
3) Tower point cloud data extraction
Since the tower has continuity in Z-axis distribution, the point cloud data (i.e., non-power line data) of the ground and the power line is removed as input data, the number of voxels containing input data in each column of voxels (the number of voxels containing input data in each column of voxels of the point cloud data after the statistical preprocessing) is counted from the voxel segmentation result in step S1 by using the multithreading technology, and if there are other columns in the counted result that contain significantly more (for example, 1.5 times or more) continuous non-power line point cloud voxels than that in the neighborhood, the column of voxels is considered as candidate tower data.
Because the transmission line must exist around the tower, the multi-threading technology is utilized to perform spatial analysis on all the candidate tower data and transmission line results, namely: and if the transmission line voxels exist in the neighborhood of the alternative tower voxel, the alternative tower voxel is considered to be a tower, otherwise, the alternative tower voxel is considered to be non-tower data.
4) Building and vegetation point cloud data extraction
Because modern buildings are mostly formed by planes, point cloud data of the ground, the transmission lines and the towers (namely non-tower point cloud data) are removed to serve as input point clouds, and a random sampling consistency algorithm is used for extracting the planes from the input point clouds to serve as potential building plane point clouds; because the building is close to the ground and the connection relation exists between the building planes, the plane close to the ground is extracted from the potential building point clouds to serve as a building point cloud, and then a recursion method is adopted to extract the plane which has the adjacent relation with the existing building point clouds from the rest potential building plane point clouds to serve as a new building point cloud; and repeating the detection of the adjacent relation of the building point clouds until the building point clouds do not exist in the potential building plane point clouds. The specific algorithm flow is as follows:
step 1: taking point clouds (namely non-tower point cloud data) with ground, transmission lines and towers removed as input data, carrying out principal component analysis according to formulas (3) - (5), and taking a feature vector corresponding to a minimum feature value of each point as a normal vector for plane extraction in the step (2);
step 2: extracting a planar point cloud set p= { P from input data 1 ,p 2 …p i …,p n And } wherein,n represents the number of planar point clouds in the extraction result, for example, a random sampling consistency algorithm is adopted to realize the extraction of the planar point cloud set, and whether the normal vectors of adjacent points in the input data are the same or not is specifically judged, if yes, the points are considered to belong to the planar point set; then calculate each planar point cloud P in P i For example, calculating by adopting an Alpha Shapes algorithm;
step 3: sequential detection of p i Whether or not there is a ground point cloud within a radius r for each point in the boundary contour point cloud of (a), if so, p i Take out from P and add to the building point cloud set b= { B 1 ,b 2 …b i …,b m }, wherein b i Representing house point clouds, m represents the number of house point clouds, and r is 2-3 times of the average interval of the point clouds in input data;
step 4: detecting whether a cloud Ping Miandian still exists in the P, if so, continuing to execute the step 5, and if not, ending the algorithm;
step 5: record member number n of collection B b Sequentially selecting house point clouds B from B i Detection b i Whether p exists for each point in the boundary contour point cloud within a radius r i If present, will p i Taking out from the P and adding the building point cloud set B;
step 6: checking whether the number of members of the current set B is still equal to the number of members n recorded in step 5 b If the building point cloud set B is equal to the building point cloud set B, the algorithm is ended, otherwise, the step 4 is continuously executed, and the finally obtained building point cloud set B is the required building point cloud data.
And finally, removing the building point cloud from the non-tower point cloud, and taking the rest point cloud as vegetation point cloud data.
As shown in fig. 3, after extracting point cloud data corresponding to the static target and the dynamic target, risk assessment is performed based on the point cloud data, that is, step S3 is performed, specifically, the method includes the following steps:
1) Cylindrical bounding box constructed based on power transmission line point cloud data
Due to spatial division of overhead line transmission linesThe distribution is in a sagged shape, so that the power transmission line point cloud is divided into a plurality of sub power transmission line point clouds, the sub power transmission line point cloud data can be approximately in a straight line, and the multi-threading technology is utilized to take the straight line direction as a central axis for the plurality of sub power transmission line point clouds, so that the safety distance r is ensured s Constructing a cylindrical bounding box for a radius, where r s Depending on the overhead line type and the span distance, 50cm is typically taken.
The specific algorithm flow is as follows:
step 1: taking the power transmission line point cloud data as input data to obtain an independent power transmission line point cloud set L= { L 1 ,l 2 ,…l i …l n N represents the number of power lines, and specifically, for example, a European cluster is adopted to obtain a point cloud set;
step 2: taking out a power transmission line point cloud L from the power transmission line point cloud set L i From l i Optionally selecting one point as a starting point to execute a depth-first traversal algorithm, and taking a traversal end point as l i Suspension point S of (2) L (x L ,y L ,z L ) The method comprises the steps of carrying out a first treatment on the surface of the By S L As a starting point, executing a depth-first traversal algorithm, and taking a traversal end point as l i Suspension point S at the other end of (2) R (x R ,y R ,z R ) The method comprises the steps of carrying out a first treatment on the surface of the Transmission line l i The minimum point of Z value is taken as the minimum point S D (x D ,y D ,z D )；
Step 3: calculate S according to equation (7) L To S D Number of transmission line segments n L S is calculated according to formula (8) R To S D The number of transmission line segments n R ；
Wherein p is L Represent S L To S D Distance in transmission line of section is defined by S L And S is D Is composed ofThree-dimensional coordinates, p, of the point with the furthest vector R Represent S R To S D Distance in transmission line of section is defined by S R And S is D Three-dimensional coordinates of the point with the furthest vector, r s Representing a safe distance;
step 4: according to S L To S D Segment and S R To S D Number of segment pairs l i Segmentation is performed to obtain a segmentation result C (namely a segmentation set) = { C 1 ,c 2 ,…c i …c n N represents l i Is a number of segments; a segment of segmentation point cloud C is taken out from the segmentation result C i C i The connecting line of the two end points is used as a cylindrical axis vector to input a safe distance r s Constructing a cylindrical bounding box as a radius; build completion c i After the bounding box, checking whether the division point cloud still exists in the C, if so, continuing to take out a section of division point cloud from the bounding box to calculate the bounding box until all the division point clouds in the C are taken out;
step 5: after the bounding boxes of all the division point clouds in the set C are built, checking whether the transmission line point cloud set L still has the transmission line point clouds, if so, continuously taking out one transmission line point cloud from the L, and calculating the bounding boxes according to the steps 2-4 until all the transmission line point clouds in the L are taken out, so that the building of all the bounding boxes is completed.
2) Static target potential risk assessment
The ground and building do not change with time or other common external force factors and are therefore static targets. Calculating the distance d between each ground point and building point and the cylinder axis of the nearest cylinder bounding box according to the formula (9) by utilizing a multithreading technology, if d is less than or equal to r s If the ground point or the building point is considered to be in the cylindrical bounding box, the potential safety hazard exists in the power transmission line, if d>r s And if the ground point or the building point is not in the cylindrical bounding box, the ground point or the building point is considered to be not in the cylindrical bounding box, so that no potential safety hazard exists in the power transmission line.
Wherein d represents a ground point orThe distance of the building point to its nearest cylinder axis, vector c represents the cylinder axis vector, p s Representing ground points or building points.
3) Dynamic target potential risk assessment
The transmission lines and vegetation will change over time or other common external factors and thus serve as dynamic targets. As the transmission lines swing under the influence of wind, there may be a touch between different transmission lines and between the transmission lines and vegetation. After obtaining the maximum horizontal swing distance of the power transmission lines and the vegetation affected by wind power according to the on-site measurement or simulation calculation, calculating the nearest distances between different power transmission lines or the power transmission lines and the vegetation according to a formula (10), calculating the safe distances between the different power transmission lines at local positions according to a formula (11), calculating the safe distances between the vegetation and the power transmission lines according to a formula (12), and if the nearest distances between the power transmission lines or the power transmission lines and the vegetation are larger than the corresponding safe distances, indicating that the power transmission lines have no potential safety hazards, and if not, indicating that the power transmission lines have the potential safety hazards.
l h ＝H ab -S a -S b (10)
Wherein l h Represents the nearest distance, H ab Representing the horizontal distance between object a and object b, e.g. the horizontal distance between two power lines, or the horizontal distance between a power line and vegetation, S a Representing the maximum horizontal swing distance (pre-determined) of the target a, S b The maximum horizontal swing distance (predetermined) of the target b is shown.
Wherein c 1 And c 2 Representing the axial quantity of a cylindrical bounding box selected on two different power transmission lines, o 1 And o 2 Representing the cylindrical axis c 1 And c 2 The points above, |·| represent norms, i.e., modulo lengths.
Wherein d represents the distance from the ground point or building point to the nearest cylinder axis, and vector c represents the axis vector of the cylinder, p T Representing vegetation points.
In addition, as vegetation grows with time, the vegetation growth rate G is obtained according to field observation, the time that the vegetation reaches the safety range of the power transmission line is calculated by using a formula (13), and early warning is carried out in advance, namely.
Wherein T represents the time when the vegetation reaches the safe range of the power transmission line, H represents the vertical height from the top end of the vegetation to the cylindrical bounding box of the power transmission line right above the vegetation, and G represents the growth rate.
The invention is described below in connection with specific application scenarios:
in this embodiment, taking a certain power transmission line scenario as an example, the method for comprehensively evaluating the potential risk of the overhead line is described:
1) Point cloud data processing
Acquiring point cloud data of a power transmission line by using an unmanned aerial vehicle, setting the size of a voxel, wherein the size of the voxel is 0.2 m, the width of the voxel is 0.2 m, and the height of the voxel is 0.2 m, and performing voxel segmentation on the point cloud data of the power transmission line based on the step S1 of the invention, wherein a region without the point cloud data does not display the voxel, and the data containing the point cloud displays the voxel, as shown in fig. 4;
2) Point cloud classification
According to the conventional erection height of the overhead line, the preset suspension height H is 20 meters, and the point cloud data are classified based on the step S2 of the invention to obtain the point cloud data of the ground, the transmission line, the pole tower, the building and the vegetation, as shown in fig. 5;
3) Risk assessment
After the maximum horizontal swing distance and the vegetation growth rate are measured, calculating the area with potential safety hazards according to the point cloud classification data based on the step S3 of the invention, and prompting the vegetation to grow into a time node of the safe area. The result of the potential risk analysis on the power transmission line scene is shown in fig. 6, wherein the left bounding box selection area in the figure represents the area with potential threat to the vegetation growth influence in the next year in the dynamic analysis, and the right deep color point cloud represents the area with threat to the vegetation influence in the power transmission line. By developing a test in a certain power transmission line scene, the method successfully completes the point cloud classification of the power transmission line, and realizes the comprehensive risk assessment of the static target and the dynamic target of the potential risk.
In a word, the invention processes the whole point cloud scene based on voxel segmentation, thereby facilitating the rapid retrieval of point cloud data and the processing of a multithreading technology, and extracting the ground point; then, classifying the non-ground point cloud into a power transmission line, a pole tower, a building and vegetation according to a statistical result and local geometric characteristics of the voxels in the Z-axis direction so as to ensure that the point cloud data can be accurately analyzed in the subsequent steps; and finally, corresponding risk assessment is realized according to different targets, and the method is specifically divided into static targets (ground, towers and houses) and dynamic targets (vegetation and power lines), wherein the static targets analyze and assess potential risks through calculating Euclidean distance. The dynamic target determines the spatial variation of the dynamic target through the swing distance of the input power line and the vegetation and the growth rate of the vegetation, and evaluates and predicts the potential risk according to space-time analysis. According to the method, the analysis of dynamic swing and vegetation growth of the power transmission line is realized while the analysis of the safety distance of the static target is ensured, and experiments prove that the method can complete data processing along the power transmission line in a short time, and realize comprehensive risk assessment of the semi-automatic power transmission line.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The comprehensive evaluation method for the potential risk of the overhead line is characterized by comprising the following steps of:
s1, acquiring point cloud data of an overhead line and preprocessing the point cloud data;
s2, dividing the preprocessed point cloud data into ground point cloud data and non-ground point cloud data; extracting power line point cloud data from non-ground point cloud data, and taking the rest point cloud data as non-power line point cloud data; dividing non-transmission line point cloud data into tower point cloud data and non-tower point cloud data; extracting building point cloud data from non-tower point cloud data, and taking the rest data as vegetation point cloud data;
and S3, constructing a cylindrical bounding box according to the power transmission line point cloud data, evaluating potential risks of the static target ground and the building to the overhead line based on the cylindrical bounding box, the ground point cloud data and the building point cloud data, and evaluating potential risks of the dynamic target power transmission line and the vegetation to the overhead line based on preset power transmission line and vegetation swing data, the power transmission line point cloud data and the vegetation point cloud data, so that comprehensive evaluation of the potential risks of the overhead line is realized.
2. The method for comprehensively evaluating the potential risk of the overhead line according to claim 1, wherein the preprocessing is specifically voxel segmentation of point cloud data based on a preset voxel size.
3. The method for comprehensively evaluating the potential risk of the overhead line according to claim 1, wherein the division of the point cloud data into the ground point cloud data and the non-ground point cloud data is specifically as follows: firstly, extracting each column of voxels of the preprocessed point cloud data along the Z-axis direction, then taking the first non-empty voxel from bottom to top of each column of voxels as a ground candidate voxel, finally extracting ground points from all the ground candidate voxels as final ground point cloud data, and taking the rest point cloud data as non-ground point cloud data.
4. The method for comprehensively evaluating the potential risk of the overhead line according to claim 1, wherein the following method is adopted to extract the cloud data of the transmission line points:
(1) Taking non-ground point cloud data as input data, using a vertical axis to represent a Z coordinate range of the voxels, and using a horizontal axis to represent the number of point clouds contained in the voxels to construct a two-dimensional histogram of each column of voxels;
(2) Extracting voxels higher than a preset suspension height H from the two-dimensional histogram of each column of voxels as power transmission line candidate voxels;
(3) Extracting voxels with the number of point clouds larger than T from the transmission line candidate voxels as the transmission line candidate point clouds, wherein the calculation formula of T is as follows:
wherein N represents the number of point clouds in the range from a preset suspension height H to maxZ in each column of voxels; Δh represents the number of voxels ranging from a preset suspension height H to maxZ in each column of voxels, and maxZ represents the maximum value of the Z axis direction determined during preprocessing;
(4) And carrying out neighborhood search on all the power transmission line candidate point clouds, carrying out principal component analysis on each point, obtaining the characteristic value of each power transmission line candidate point cloud, and screening out point cloud data meeting the conditions based on the characteristic value to serve as power transmission line point cloud data.
5. The method for comprehensively evaluating the potential risk of the overhead line according to claim 1, wherein the division of the non-transmission line point cloud data into the tower point cloud data and the non-tower point cloud data is specifically as follows:
(1) Taking non-power line point cloud data as input data, counting the number of voxels containing the input data in each column of voxels of the point cloud data after preprocessing, and taking the column of voxels with the number greater than that of other columns in a neighborhood range as alternative tower data;
(2) And analyzing all the alternative tower data, and considering the alternative tower voxels as tower data if the transmission line voxels exist in the neighborhood of the alternative tower voxels, or else, judging the alternative tower voxels as non-tower data.
6. The method for comprehensively evaluating the potential risk of the overhead line according to claim 1, wherein the building point cloud data is extracted by adopting the following method: and extracting a plane with adjacent relation to the building point cloud from the rest of the potential building plane point clouds by adopting a recursion method as a new building point cloud until the building point cloud does not exist in the potential building plane point clouds, thereby completing the extraction of the building point cloud data.
7. The method for comprehensively evaluating potential risks of overhead lines according to claim 1, wherein the step S3 includes the following sub-steps:
s31, constructing a cylindrical bounding box based on the power transmission line point cloud data;
s32, static target potential risk assessment:
s321 calculates the distance d of each ground point and building point to the nearest cylindrical bounding box according to the following equation:
wherein vector c represents the axial vector of the cylinder, p a Representing ground points or building points;
s322 determining whether the distance d is within a preset safe distance r a Inner: if d is less than or equal to r a The ground points or the building points are considered to be in the cylindrical bounding box, so that potential safety hazards of the overhead line are indicated; if d>r s And if the ground point or the building point is not in the cylindrical bounding box, the overhead line is considered to have no potential safety hazard.
S33, dynamic target potential risk assessment:
s331, calculating the nearest distances between different power lines or between the power lines and vegetation by adopting the following formula:
l h ＝H ab -S a -S b
wherein l h Represents the nearest distance, H ab Represents the horizontal distance between object a and object b, S a And S is b Horizontal pendulum representing object a and object bA web distance;
s332 calculates a safe distance d between transmission lines using the following formula:
wherein c 1 And c 2 Axial quantity of cylindrical bounding box representing different power lines, o 1 And o 2 Representing points on the cylinder axis, |·| representing norms;
calculating the safety distance d between vegetation and a power transmission line by adopting the following steps:
wherein vector c represents the axial amount of the cylindrical bounding box, p T Representing vegetation points;
s333, judging whether the nearest distance between different power transmission lines or between the power transmission lines and vegetation is larger than the corresponding safety distance, if so, indicating that the overhead line has no safety hidden trouble, and if not, indicating that the overhead line has the safety hidden trouble.
8. The method for comprehensively evaluating potential risks of an overhead line according to claim 7, further comprising the sub-steps of:
s334, calculating time T for vegetation to reach the safety range of the power transmission line by adopting the following formula, and performing early warning in advance:
wherein H represents the vertical height from the top of the vegetation to the cylindrical bounding box of the transmission line right above the vegetation, and G represents the growth rate.
9. The method for comprehensively evaluating potential risk of an overhead line according to claim 7, wherein the step S31 includes the sub-steps of:
s311, taking the power transmission line point cloud data as input data, and acquiring an independent power transmission line point cloud set L= { L 1 ,l 2 ,…l i …l n N represents the number of power lines;
s312, taking out a power transmission line point cloud L from the power transmission line point cloud set L i From l i Any point is selected as a starting point to carry out depth-first traversal, and a traversal end point is used as l i Suspension point S of (2) L In S form L Depth-first traversal is performed with the traversal end point as l i Suspension point S at the other end of (2) R The power transmission line l i The minimum point of Z value is taken as the minimum point S D ；
S313 calculation S L To S D Number of transmission line segments n L Calculate S R To S D The number of transmission line segments n R According to the number n of segments L And n R Pair l i Dividing to obtain a divided segment set C= { C 1 ,c 2 ,…c i …c n N represents the sum of the values of l i Is a number of segments;
s314, a segment of the segmentation point cloud C is taken out of the segmentation segment set C i C i The connecting line of the two end points is used as a cylinder axis vector and a preset safety distance r is used as a connecting line of the two end points s Constructing a cylindrical bounding box as a radius;
s315, repeating the step S314 until the construction of the cylindrical bounding boxes of all the partitioned point cloud segments in the partitioned segment set C is completed;
s316, repeating the steps S312-S315 until the construction of the cylindrical bounding boxes of all the power transmission line point clouds in the power transmission line point cloud set L is completed.
10. The method for comprehensively evaluating potential risk of overhead line according to claim 9, wherein the number of transmission line segments n L The following formula is adopted for calculation:
wherein p is L Represent S L To S D Distance in transmission line of section is defined by S L And S is D Three-dimensional coordinates, x, of the point with the furthest vector D ,y D ,z D Is S D Coordinate value of x L ,y L ,z L Is S D Coordinate values of (2);
the number of the transmission line segments n R The following formula is adopted for calculation:
wherein p is R Represent S R To S D Distance in transmission line of section is defined by S R And S is D Three-dimensional coordinates, x, of the point with the furthest vector D ,y D ,z D Is S D Coordinate value of x R ,y R ,z R Is S R Is set in the coordinate value of (a).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311755143.9A CN117808287A (en) | 2023-12-19 | 2023-12-19 | Comprehensive evaluation method for potential risk of overhead line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311755143.9A CN117808287A (en) | 2023-12-19 | 2023-12-19 | Comprehensive evaluation method for potential risk of overhead line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117808287A true CN117808287A (en) | 2024-04-02 |
Family
ID=90428976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311755143.9A Pending CN117808287A (en) | 2023-12-19 | 2023-12-19 | Comprehensive evaluation method for potential risk of overhead line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808287A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118113055A (en) * | 2024-04-30 | 2024-05-31 | 山东字节信息科技有限公司 | Unmanned aerial vehicle control system and control method thereof |
-
2023
- 2023-12-19 CN CN202311755143.9A patent/CN117808287A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118113055A (en) * | 2024-04-30 | 2024-05-31 | 山东字节信息科技有限公司 | Unmanned aerial vehicle control system and control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037133B (en) | Intelligent electric power equipment defect identification method and system based on unmanned aerial vehicle inspection image | |
| CN106022381B (en) | Automatic extraction method of street lamp pole based on vehicle-mounted laser scanning point cloud | |
| CN105260737B (en) | A kind of laser scanning data physical plane automatization extracting method of fusion Analysis On Multi-scale Features | |
| CN109493119B (en) | POI data-based urban business center identification method and system | |
| CN105225227B (en) | The method and system of remote sensing image change detection | |
| CN110794413B (en) | Method and system for detecting power line of point cloud data of laser radar segmented by linear voxels | |
| CN103390169A (en) | Sorting method of vehicle-mounted laser scanning point cloud data of urban ground objects | |
| CN112529044B (en) | Method for extracting and classifying railway contact network based on vehicle-mounted LiDAR | |
| CN113255677B (en) | Method, equipment and medium for rapidly extracting rock mass structural plane and occurrence information | |
| CN110084169A (en) | A kind of architecture against regulations object recognition methods based on K-Means cluster and profile topological constraints | |
| CN117808287A (en) | Comprehensive evaluation method for potential risk of overhead line | |
| CN113592324A (en) | Cable terminal tower live-line work risk assessment method based on hierarchical analysis | |
| Wang et al. | Segmentation of the communication tower and its accessory equipment based on geometrical shape context from 3D point cloud | |
| Shen et al. | An automatic framework for pylon detection by a hierarchical coarse-to-fine segmentation of powerline corridors from UAV LiDAR point clouds | |
| CN115239625A (en) | Method, device and equipment for detecting defects of top cover welding point cloud and storage medium | |
| CN106023178B (en) | Method for detecting single tree in remote sensing data based on gradient direction clustering | |
| Zhu et al. | Research on deep learning individual tree segmentation method coupling RetinaNet and point cloud clustering | |
| CN111881964A (en) | Linear building mode identification method and system based on Delaunay triangulation network | |
| Wu et al. | Investigator accuracy: A center-weighted metric for evaluating the location accuracy of image segments in land cover classification | |
| CN117218063A (en) | Bridge construction progress monitoring method based on spatial position change of hanging basket in construction stage | |
| CN117036971A (en) | Method for extracting airborne LiDAR data building under self-adaptive local spatial spectrum consistency | |
| CN112284287B (en) | Stereoscopic vision three-dimensional displacement measurement method based on structural surface gray scale characteristics | |
| CN116805357A (en) | Point cloud-based high-voltage transmission line three-dimensional model construction method | |
| CN117994549B (en) | Ultra-high pressure maintenance safety control method, device, equipment and storage medium | |
| Wang et al. | Automatic cross section extraction and cross slope measurement for curved ramps using light detection and ranging point clouds |
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 |