CN116958610A - Beidou-based power transmission line tower point cloud clustering method - Google Patents
Beidou-based power transmission line tower point cloud clustering method Download PDFInfo
- Publication number
- CN116958610A CN116958610A CN202310868589.6A CN202310868589A CN116958610A CN 116958610 A CN116958610 A CN 116958610A CN 202310868589 A CN202310868589 A CN 202310868589A CN 116958610 A CN116958610 A CN 116958610A
- Authority
- CN
- China
- Prior art keywords
- points
- tower
- point
- point cloud
- beidou
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000005540 biological transmission Effects 0.000 title claims abstract description 40
- 230000011218 segmentation Effects 0.000 claims abstract description 11
- 238000005070 sampling Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 4
- 238000012512 characterization method Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000036544 posture Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Graphics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a Beidou-based power transmission line tower point cloud clustering method, which comprises the following steps: step 1, installing laser radar equipment with Beidou positioning on a transmission tower, positioning the transmission tower by using a Beidou satellite positioning system, acquiring coordinate information of the equipment, acquiring a transmission line channel point cloud by using a laser radar, and correcting a point cloud model according to Beidou parameters; removing ground points by using a random sampling consistency segmentation algorithm, and firstly extracting electric power facility points by using an European clustering algorithm; step 2, calculating a central point of the tower in the electric power facility point; step 3, finely extracting tower points; the method solves the technical problems of low semantic segmentation accuracy and the like of the power transmission line pole and tower point cloud data.
Description
Technical Field
The invention belongs to the technical field of power transmission line point cloud data processing, and particularly relates to a Beidou-based power transmission line tower point cloud clustering method.
Background
Because the traditional manual inspection method has the defects of large workload, multiple potential safety hazards, doubtful accuracy of measured data and the like, more and more transmission line operation and maintenance units begin to apply the laser scanning technology to the transmission line inspection work.
In the inspection operation and maintenance work of the power transmission line, towers, wires and environments are mainly used, so that the point cloud data of the power transmission line are divided into three types of ground feature points, tower points and power line points, which are basic requirements for subsequent data processing. At present, the point cloud classification method based on the inherent characteristics of the power transmission engineering has extremely high requirements on the characteristics selected by the user, needs to construct various constraint conditions and parameter thresholds, has a small application range, and can generate the situation that the classification effect difference is large when the same set of algorithm is used for different lines; for the data processing of the laser radar power line inspection work, the most critical is to separate a pole tower and a power line from original point cloud data so as to facilitate the development of later dangerous point detection and data modeling work, a great deal of work is developed in the aspects of research on power line and pole tower extraction algorithms at home and abroad at present, and the main idea is to segment spatial characteristics according to context of each category in a power transmission corridor scene, and then accurately identify and extract the power line or pole tower point cloud by utilizing a characteristic fitting method; most methods only pay attention to the extraction of the power line, and the position determination of the tower and the accurate extraction of the tower point are not involved; aiming at the problem of low semantic segmentation accuracy of the point cloud data of the power transmission line.
Disclosure of Invention
The invention aims to solve the technical problems that: the utility model provides a transmission line tower point cloud clustering method based on big dipper to solve the lower technical problem of the semantic segmentation precision of transmission line tower point cloud data.
The technical scheme of the invention is as follows:
a Beidou-based power transmission line tower point cloud clustering method, comprising:
step 1, installing laser radar equipment with Beidou positioning on a transmission tower, positioning the transmission tower by using a Beidou satellite positioning system, acquiring coordinate information of the equipment, acquiring a transmission line channel point cloud by using a laser radar, and correcting a point cloud model according to Beidou parameters; removing ground points by using a random sampling consistency segmentation algorithm, and firstly extracting electric power facility points by using an European clustering algorithm;
step 2, calculating a central point of the tower in the electric power facility point;
and 3, finely extracting the tower points.
The method for correcting the point cloud model according to the Beidou parameters comprises the following steps:
step 1.1, acquiring Beidou navigation system parameters of the current position of laser equipment, wherein the Beidou navigation system parameters comprise position coordinates, pitch angle, course angle and roll angle and time information;
step 1.2, matching the Beidou parameters with the time stamps of the point cloud data, and simultaneously, corresponding the Beidou parameters with the point cloud data according to the geometric relation of the installation position of the equipment to ensure that all the parameters have the same time and space coordinate system;
and 1.3, calculating a rigid body transformation matrix according to the position and posture parameters of the equipment, translating and rotating the point cloud data by utilizing the matrix, so that the point cloud data is converted from an equipment coordinate system to a world coordinate system, is consistent with Beidou positioning coordinates, and improves the longitude of the point cloud coordinates.
The method for eliminating the ground points by using the random sampling consistency segmentation algorithm comprises the following steps:
step 1.4, randomly selecting 3 points in the point cloud data set after Beidou correction, fitting a plane equation according to coordinates of the 3 points, setting thresholds in positive and negative directions of the plane, carrying the point cloud into the fitted plane equation for verification, if a point is in a given threshold range, namely the ground point, continuously and iteratively updating the random 3 points until the number of points in the threshold range is maximum, judging that the equation created by the 3 points at the moment is an optimal model, and finally removing the ground point.
The method for firstly extracting the electric power facility points by using the European clustering algorithm comprises the following steps:
step 1.5, extracting characteristics of non-ground points after the ground points are removed, and extracting attributes capable of describing characteristics of the points of the electric power facilities, wherein the attributes comprise colors, normal vectors, curvatures and densities of the points;
step 1.6, calculating Euclidean distance between points by using an Euclidean clustering algorithm, setting a distance threshold, and marking the points with the distance smaller than the threshold as the same category, thereby gathering the points with the distance smaller than the distance threshold in a feature space;
and 1.7, extracting the cluster belonging to the electric power facility point according to the clustering result of the European clustering algorithm.
The method for calculating the central point of the pole tower in the electric power facility point comprises the following steps:
step 2.1, grid dividing the electric power facility points to form a grid set { G } i I=1, 2, 3.. } and calculate the centroid point { P } for each grid i ,i＝1、2、3...}，P i Characterization grid G i Characteristics of all points within;
step 2.2, creating a point cloud traversal model;
step 2.3, traversing the tower points; until all points meeting the model requirement are traversed, namely the tower points;
and 2.4, calculating the central coordinates of the pole tower.
The method for creating the point cloud traversal model comprises the following steps: with any grid centroid point P i The cross arm width w is the diameter, and the h-cent is the height, so as to create a cylinder model Cy-cent; taking the top surface of Cy-cent as the bottom, h-top is high, creating a cylinder model Cy-top; a cylinder model Cy-bottom was created with the bottom of Cy-cent as the top and h-bottom as the high.
The method for traversing the tower points comprises the following steps: continuously and iteratively updating P according to a point cloud traversal model i Creating a new cylinder model, inquiring whether Cy-top and Cy-bottom contain other points, if so, P epsilon pole tower points, otherwise P epsilon wire points, traversing in sequence until all points meeting the model requirement are traversed, namely pole tower points.
The method for finely extracting the pole tower points comprises the following steps: the central coordinate of the tower is assumed to be O, the O is taken as the center of a circle, the width w of the cross arm is taken as the diameter, a circle C on a horizontal plane is created, if the projection of any point in the horizontal direction falls in the circle C, the point is judged to be a tower point, otherwise, the point is judged to be a power line point
Step 2.4.1, layering tower point clouds and calculating mass center points of each layer; according to the obtained tower points, the distribution of the tower point clouds is mainly in the Z-axis direction, the tower point clouds are layered by taking L as step length in the Z-axis direction, and the mass center S of each layer is calculated i ,i＝1,2,3...；
Step 2.4.2, calculating the horizontal distance between two adjacent layers of centroid points and the included angle between the connecting line of the two centroid points and the Z axis: sequentially calculating mass centers S of two adjacent layers i And S is i+1 Distance d (S) i ～S i+1 ) At the same time calculate S i And S is i+1 An included angle theta between the connecting line and the Z axis;
step 2.4.3, query d (S i ～S i+1 ) If d is the maximum value of max If the mass center is less than or equal to 0.5, taking the average value of all mass centers as the center of the tower; if d max > 0.5, respectively calculating adjacent S i 、S i+1 And S is equal to i+2 The angle in the vertical direction is denoted as θ i～i+1 And theta i+1～i+2 If theta i～i+1 >θ i+1～i+2 Give S to i Record 1 minute, if θ i～i+1 ≤θ i+1～i+2 Give S to i+1 Recording 1 score, deleting the point with the highest score and the related distance d and angle theta, namely deleting the centroid point with larger deviation, and repeatedly executing the step 2.4.2; up to d max And (3) keeping the average value of the mass center points as the central coordinates of the tower, wherein the average value is less than or equal to 0.5.
The central coordinate of the tower is assumed to be O, the O is taken as the center of a circle, the width w of the cross arm is taken as the diameter, a circle C on a horizontal plane is created, if the projection of any point in the horizontal direction falls in the circle C, the point is judged to be a tower point, and otherwise, the point is judged to be a power line point.
The invention has the beneficial effects that:
according to the invention, ground points are firstly removed from the point cloud data set, then, electric facility points are roughly extracted from non-ground points by using an European clustering method, the obtained electric facility points are relatively rough, so that a tower point is precisely extracted from the electric facility points by using a traversing model created in the text, the positions of the traversing model are continuously and iteratively updated, the obtained tower points are repeatedly searched, layering is carried out in the obtained tower points, the mass centers of all layers are iteratively calculated, finally, relatively precise tower center point coordinates are obtained, then, the traversing model is created by taking the center point coordinates as a reference, and then, the tower points are searched again by using the traversing model, and the precise tower points and the tower center point coordinates are obtained by continuously and repeatedly searching through continuously dropping the updating, so that the precision of the tower point cloud clustering is improved.
The method solves the technical problems of low semantic segmentation accuracy and the like of the power transmission line pole and tower point cloud data.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is a schematic diagram of a cylinder model according to an embodiment of the present invention;
FIG. 3 is a schematic view of the horizontal distance between two adjacent centroid points and the angle between the connecting line of the two centroid points and the Z axis;
FIG. 4 is adjacent S i 、S i+1 And S is equal to i+2 Schematic diagram of the included angle in the vertical direction.
Detailed Description
A Beidou-based power transmission line tower point cloud clustering method specifically comprises the following steps:
step 1: and installing laser radar equipment with Beidou positioning on the transmission tower, positioning the transmission line tower by using a Beidou satellite positioning system, acquiring coordinate information of the equipment, acquiring a transmission line channel point cloud by using a laser radar, and correcting a point cloud model according to Beidou parameters. The precision of the point cloud data corrected by the Beidou parameters reaches the centimeter level due to the adoption of centimeter-level Beidou positioning, and the power transmission line is monitored by utilizing centimeter-level high-precision point cloud data, so that the monitoring precision is improved. And removing ground points by using a random sampling consistency segmentation algorithm, and firstly extracting electric power facility points by using an European clustering algorithm.
(1) The method for correcting the point cloud model to obtain the high-precision point cloud data according to the Beidou parameters comprises the following steps:
1) Acquiring Beidou navigation system parameters: and acquiring Beidou navigation system parameters of the current position of the laser equipment, wherein the Beidou navigation system parameters comprise position coordinates, postures (pitch angle, course angle and roll angle) and time information.
2) Establishing association of the point cloud and Beidou parameters: and matching the Beidou parameters with the time stamps of the point cloud data, and simultaneously, corresponding the Beidou parameters with the point cloud data according to the geometric relationship of the installation position of the equipment, so as to ensure that all the parameters have the same time and space coordinate system.
3) Rigid body transformation: and calculating a rigid body transformation matrix according to the position and posture parameters of the equipment, translating and rotating the point cloud data by utilizing the matrix, so that the point cloud data is converted into a world coordinate system from the equipment coordinate system, is consistent with the Beidou positioning coordinate, and improves the longitude of the point cloud coordinate. (2) The method for eliminating the ground points by using the random sampling consistency segmentation algorithm comprises the following steps:
3 points in the point cloud data set after Beidou correction are randomly selected from the point cloud data set, an equation of the plane is fitted according to coordinates of the 3 points, a threshold value is set in the positive direction and the negative direction of the plane, the point cloud is brought into the fitted equation of the plane for verification, if a large number of points are in a given threshold value range, the points falling in the threshold value range are ground points, the random 3 points are continuously and iteratively updated until the number of the points falling in the threshold value range is maximum, the equation created by the 3 points at the moment is judged to be an optimal model, and finally the ground points are removed.
(3) The method for firstly extracting the electric power facility points by using the European clustering algorithm comprises the following steps:
1) And extracting the characteristics of the non-ground points after the ground points are removed, and extracting the attributes capable of describing the characteristics of the points of the electric power facilities, including the colors, normal vectors, curvatures, densities and the like of the points.
2) And calculating Euclidean distances between points by using an Euclidean clustering algorithm, setting a distance threshold value, and marking the points with the distances smaller than the threshold value as the same category, thereby gathering the points with the closer distances in the feature space.
3) And extracting the cluster belonging to the electric power facility point according to the clustering result of the European clustering algorithm.
Step 2: in the power utility point, a tower center point is calculated.
(4) Dividing grids:
grid dividing the electric power facility points to form a grid set { G } i I=1, 2, 3.. } and calculate the centroid point { P } for each grid i ,i＝1、2、3...}，P i Characterization grid G i Characteristics of all points within;
(5) Creating a point cloud traversal model:
with any grid centroid point P i The cross arm width w is the diameter, and the h-cent is the height, so as to create a cylinder model Cy-cent; taking the top surface of the Cy-cent as the bottom, taking the h-top as the high, and creating a cylinder model Cy-top; with the bottom of Cy-cent as the top and h-bottom as the high, a cylinder model Cy-bottom was created as shown in the following figure:
(6) Traversing tower points:
according to the cylinder model of the upper graph, continuously and iteratively updating P i Creating a new cylinder model, inquiring whether Cy-top and Cy-bottom contain other points, if so, P epsilon pole tower points, otherwise P epsilon wire points, traversing in sequence until traversing to meet the modelAll points required are pole tower points;
(7) Calculating the central coordinates of the pole tower:
1) Layering tower point clouds and calculating mass center points of each layer:
the tower points are obtained through the steps, at the moment, the distribution of the tower point clouds is mainly in the Z-axis direction, the tower point clouds are layered by taking L as step length in the Z-axis direction, and the mass center S of each layer is calculated i ,i＝1,2,3...；
2) Calculating the horizontal distance between two adjacent layers of centroid points and the included angle between the connecting line of the two centroid points and the Z axis:
sequentially calculating mass centers S of two adjacent layers i And S is i+1 Distance d (S) i ～S i+1 ) At the same time calculate S i And S is i+1 An included angle theta between the connecting line and the Z axis;
3) Removing mass center points with larger deviation, and keeping the average value of the mass center points as the central coordinates of the tower:
query d (S) i ～S i+1 ) If d is the maximum value of max If the mass center is less than or equal to 0.5, taking the average value of all mass centers as the center of the tower; if d max > 0.5, respectively calculating adjacent S i 、S i+1 And S is equal to i+2 The angle in the vertical direction is denoted as θ i～i+1 And theta i+1～i+2 If theta i～i+1 >θ i+1～i+2 Give S to i Record 1 minute, if θ i～i+1 ≤θ i+1～i+2 Give S to i+1 Recording 1 score, deleting the point with the highest score and the related distance d and angle theta, namely deleting the centroid point with larger deviation, repeating the step 2) again until d max And (3) keeping the average value of the mass center points as the central coordinates of the tower, wherein the average value is less than or equal to 0.5.
Step 3: refined extraction pole tower point
And 2, calculating to obtain a central coordinate of the tower, assuming O as a center of a circle, taking the width w of the cross arm as a diameter, creating a circle C on a horizontal plane, judging the point as a tower point if the projection of any point in the horizontal direction falls in the circle C, and judging as a power line point if the projection of any point in the horizontal direction falls in the circle C.
Claims (9)
1. A power transmission line tower point cloud clustering method based on Beidou is characterized by comprising the following steps of: the method comprises the following steps:
step 1, installing laser radar equipment with Beidou positioning on a transmission tower, positioning the transmission tower by using a Beidou satellite positioning system, acquiring coordinate information of the equipment, acquiring a transmission line channel point cloud by using a laser radar, and correcting a point cloud model according to Beidou parameters; removing ground points by using a random sampling consistency segmentation algorithm, and firstly extracting electric power facility points by using an European clustering algorithm;
step 2, calculating a central point of the tower in the electric power facility point;
and 3, finely extracting the tower points.
2. The Beidou-based power transmission line tower point cloud clustering method of claim 1 is characterized by comprising the following steps: the method for correcting the point cloud model according to the Beidou parameters comprises the following steps:
step 1.1, acquiring Beidou navigation system parameters of the current position of laser equipment, wherein the Beidou navigation system parameters comprise position coordinates, pitch angle, course angle and roll angle and time information;
step 1.2, matching the Beidou parameters with the time stamps of the point cloud data, and simultaneously, corresponding the Beidou parameters with the point cloud data according to the geometric relation of the installation position of the equipment to ensure that all the parameters have the same time and space coordinate system;
and 1.3, calculating a rigid body transformation matrix according to the position and posture parameters of the equipment, translating and rotating the point cloud data by utilizing the matrix, so that the point cloud data is converted from an equipment coordinate system to a world coordinate system, is consistent with Beidou positioning coordinates, and improves the longitude of the point cloud coordinates.
3. The Beidou-based power transmission line tower point cloud clustering method of claim 1 is characterized by comprising the following steps: the method for eliminating the ground points by using the random sampling consistency segmentation algorithm comprises the following steps:
step 1.4, randomly selecting 3 points in the point cloud data set after Beidou correction, fitting a plane equation according to coordinates of the 3 points, setting thresholds in positive and negative directions of the plane, carrying the point cloud into the fitted plane equation for verification, if a point is in a given threshold range, namely the ground point, continuously and iteratively updating the random 3 points until the number of points in the threshold range is maximum, judging that the equation created by the 3 points at the moment is an optimal model, and finally removing the ground point.
4. The Beidou-based power transmission line tower point cloud clustering method of claim 1 is characterized by comprising the following steps: the method for firstly extracting the electric power facility points by using the European clustering algorithm comprises the following steps:
step 1.5, extracting characteristics of non-ground points after the ground points are removed, and extracting attributes capable of describing characteristics of the points of the electric power facilities, wherein the attributes comprise colors, normal vectors, curvatures and densities of the points;
step 1.6, calculating Euclidean distance between points by using an Euclidean clustering algorithm, setting a distance threshold, and marking the points with the distance smaller than the threshold as the same category, thereby gathering the points with the distance smaller than the distance threshold in a feature space;
and 1.7, extracting the cluster belonging to the electric power facility point according to the clustering result of the European clustering algorithm.
5. The Beidou-based power transmission line tower point cloud clustering method of claim 1 is characterized by comprising the following steps: the method for calculating the central point of the pole tower in the electric power facility point comprises the following steps:
step 2.1, grid dividing the electric power facility points to form a grid set { G } i I=1, 2, 3.. } and calculate the centroid point { P } for each grid i ,i＝1、2、3...}，P i Characterization grid G i Characteristics of all points within;
step 2.2, creating a point cloud traversal model;
step 2.3, traversing the tower points; until all points meeting the model requirement are traversed, namely the tower points;
and 2.4, calculating the central coordinates of the pole tower.
6. The Beidou-based power transmission line tower point cloud clustering method of claim 5 is characterized by comprising the following steps: the method for creating the point cloud traversal model comprises the following steps: with any grid centroid point P i The cross arm width w is the diameter, and the h-cent is the height, so as to create a cylinder model Cy-cent; taking the top surface of the Cy-cent as the bottom, taking the h-top as the high, and creating a cylinder model Cy-top; a cylinder model Cy-bottom was created with the bottom of Cy-cent as the top and h-bottom as the high.
7. The Beidou-based power transmission line tower point cloud clustering method of claim 5 is characterized by comprising the following steps: the method for traversing the tower points comprises the following steps: continuously and iteratively updating P according to a point cloud traversal model i Creating a new cylinder model, inquiring whether Cy-top and Cy-bottom contain other points, if so, P epsilon pole tower points, otherwise P epsilon wire points, traversing in sequence until all points meeting the model requirement are traversed, namely pole tower points.
8. The Beidou-based power transmission line tower point cloud clustering method of claim 1 is characterized by comprising the following steps: the method for finely extracting the pole tower points comprises the following steps: the central coordinate of the tower is assumed to be O, the O is taken as the center of a circle, the width w of the cross arm is taken as the diameter, a circle C on a horizontal plane is created, if the projection of any point in the horizontal direction falls in the circle C, the point is judged to be a tower point, otherwise, the point is judged to be a power line point
Step 2.4.1, layering tower point clouds and calculating mass center points of each layer; according to the obtained tower points, the distribution of the tower point clouds is mainly in the Z-axis direction, the tower point clouds are layered by taking L as step length in the Z-axis direction, and the mass center S of each layer is calculated i ,i＝1,2,3...；
Step 2.4.2, calculating the horizontal distance between two adjacent layers of centroid points and the included angle between the connecting line of the two centroid points and the Z axis: sequentially calculating mass centers S of two adjacent layers i And S is i+1 Distance d (S) i ～S i+1 ) At the same time calculate S i And S is i+1 An included angle theta between the connecting line and the Z axis;
step 2.4.3, query d (S i ～S i+1 ) If d is the maximum value of max If the mass center is less than or equal to 0.5, taking the average value of all mass centers as the center of the tower; if d max > 0.5, respectively calculating adjacent S i 、S i+1 And S is equal to i+2 The angle in the vertical direction is denoted as θ i～i+1 And theta i+1～i+2 If theta i～i+1 >θ i+1～i+2 Give S to i Record 1 minute, if θ i～i+1 ≤θ i+1～i+2 Give S to i+1 Recording 1 score, deleting the point with the highest score and the related distance d and angle theta, namely deleting the centroid point with larger deviation, and repeatedly executing the step 2.4.2; up to d max And (3) keeping the average value of the mass center points as the central coordinates of the tower, wherein the average value is less than or equal to 0.5.
9. The Beidou-based power transmission line tower point cloud clustering method of claim 1 is characterized by comprising the following steps: the central coordinate of the tower is assumed to be O, the O is taken as the center of a circle, the width w of the cross arm is taken as the diameter, a circle C on a horizontal plane is created, if the projection of any point in the horizontal direction falls in the circle C, the point is judged to be a tower point, and otherwise, the point is judged to be a power line point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310868589.6A CN116958610A (en) | 2023-07-14 | 2023-07-14 | Beidou-based power transmission line tower point cloud clustering method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310868589.6A CN116958610A (en) | 2023-07-14 | 2023-07-14 | Beidou-based power transmission line tower point cloud clustering method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116958610A true CN116958610A (en) | 2023-10-27 |
Family
ID=88461371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310868589.6A Pending CN116958610A (en) | 2023-07-14 | 2023-07-14 | Beidou-based power transmission line tower point cloud clustering method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116958610A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117830676A (en) * | 2024-03-06 | 2024-04-05 | 国网湖北省电力有限公司 | Unmanned aerial vehicle-based power transmission line construction risk identification method and system |
-
2023
- 2023-07-14 CN CN202310868589.6A patent/CN116958610A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117830676A (en) * | 2024-03-06 | 2024-04-05 | 国网湖北省电力有限公司 | Unmanned aerial vehicle-based power transmission line construction risk identification method and system |
| CN117830676B (en) * | 2024-03-06 | 2024-06-04 | 国网湖北省电力有限公司 | Unmanned aerial vehicle-based power transmission line construction risk identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898662B (en) | Point cloud data-based pipeline facility BIM (building information modeling) model automatic reconstruction method | |
| CN107610223B (en) | Three-dimensional reconstruction method for power tower based on LiDAR point cloud | |
| CN108733755B (en) | Intelligent inspection method and system based on three-dimensional information of power transmission line | |
| CN106529469B (en) | Unmanned aerial vehicle-mounted LiDAR point cloud filtering method based on self-adaptive gradient | |
| CN112883878B (en) | Automatic point cloud classification method under transformer substation scene based on three-dimensional grid | |
| CN111553292B (en) | Rock mass structural plane identification and occurrence classification method based on point cloud data | |
| CN109919237B (en) | Point cloud processing method and device | |
| CN111044041B (en) | Gravity-assisted inertial navigation adaptive area selection method based on gravity field three-dimensional characteristics | |
| CN113554595B (en) | Unmanned aerial vehicle laser radar point cloud tower head deformation detection device and method | |
| CN107958486A (en) | A kind of generation method and device of conducting wire vector model | |
| CN116958610A (en) | Beidou-based power transmission line tower point cloud clustering method | |
| CN116993928B (en) | Urban engineering mapping method and system based on unmanned aerial vehicle remote sensing technology | |
| CN109002048A (en) | A kind of scale centralization photovoltaic plant image data acquiring method based on multi-rotor unmanned aerial vehicle | |
| CN110794413A (en) | Method and system for detecting power line of point cloud data of laser radar segmented by linear voxels | |
| CN114117702A (en) | Point cloud-based automatic reverse modeling method for power transmission line | |
| CN112084871B (en) | High-resolution remote sensing target boundary extraction method based on weak supervised learning | |
| CN111382715A (en) | Method for extracting surface feature elements in topographic map | |
| CN109872384B (en) | Automatic tower modeling method based on airborne LIDAR point cloud data | |
| CN110807832B (en) | Automatic power line extraction method based on ground three-dimensional scanner | |
| CN117649489A (en) | Visual modeling method for transmission line pole tower based on holographic data | |
| CN117437631A (en) | Overhead line point cloud detection method based on catenary face hough transformation | |
| CN117115390A (en) | Three-dimensional model layout method of power transformation equipment in transformer substation | |
| CN117058348A (en) | Three-dimensional point cloud electric tower segmentation method based on geometric feature and registration joint optimization | |
| CN111985691A (en) | Site selection method for wind power plant booster station | |
| CN116520881A (en) | Unmanned plane continuous tower foundation three-dimensional inspection path planning method based on laser point cloud |
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 |