Automatic extraction method of power tower in random laser point cloud data

A technology for automatic extraction of laser point cloud data, applied to radio wave measurement systems, instruments, etc.

Active Publication Date: 2013-11-27
ELECTRIC POWER RES INST OF GUANGDONG POWER GRID
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The lidar system has been widely used in foreign power grid maintenance, and has been applied in domestic power line design, and it is still in the exploratory stage for power grid maintenance

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic extraction method of power tower in random laser point cloud data
  • Automatic extraction method of power tower in random laser point cloud data
  • Automatic extraction method of power tower in random laser point cloud data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In the method for automatically extracting power towers from disordered laser point cloud data of the present invention, firstly, the laser point cloud data is gridded to generate an elevation image map similar to a digital image. The line segment corresponding to the power line on the elevation value image is generally only a few pixels wide, and the electric tower and potentially dangerous features are clustered point groups. The corrosion operation in mathematical morphology can eliminate the boundary of the object. Therefore, the power line can be eliminated through the corrosion operation first. , and then use the expansion operation to get the connected area, and then use the K-means clustering to get the point group of each connected area, and finally distinguish the electric tower and the potentially dangerous ground object by the size of the area. The specific process is as figure 1 shown.

[0021] The line segment corresponding to the power line on the elevat...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an automatic extraction method of a power tower in random laser point cloud data. The method includes the steps of : (1) an airborne light detection and ranging system is used to take an aerial photo of power line inspection; laser point cloud data of the power line inspection are obtained; the obtained laser point cloud data are meshed; an elevation value image of the power line inspection is generated; the power line inspection comprises inspection of a power tower, a power line and a potentially dangerous object; (2) the elevation value image is binarized; (3) the elevation value image is corroded; (4) the elevation value image is expanded; (5) the elevation value image is then scanned, and all dark spots are processed by a K-means clustering to get clustering of different ground objects, wherein the ground objects include potentially dangerous / non-dangerous ground objects, and the value of K is obtained by visual estimation of a quantity of the power tower and the ground objects and is inputted manually; and (6) the clustering result obtained in step (5) performs statistics of a quantity of image points. If the quantity of the image points is greater than a threshold value, the corresponding image is considered as the power tower; otherwise, the corresponding image is considered as the potentially dangerous object; and accordingly the automatic extraction of the power tower is realized.

Description

technical field [0001] The invention belongs to a method for extracting power equipment in the field of power line inspection, and specifically refers to a method for automatically extracting power towers from disordered laser point cloud data. Background technique [0002] The power tower is an important device for high-voltage power transmission and transformation. It is used to realize the large-scale and long-distance supply of power resources. It is an important basic equipment in the country's economic construction. To ensure efficient power transmission and safe energy supply, it is necessary to grasp and monitor the current status of power tower facilities in real time and accurately, and establish a complete early warning and emergency response mechanism. Therefore, the detection and modeling of power towers becomes an important guarantee to solve this problem. On this basis, carry out scene analysis around power facilities, such as: detection of other types of art...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01S7/48G01S7/491
Inventor 王柯陈驰麦晓明赵刚徐晓刚杨必胜彭向阳
Owner ELECTRIC POWER RES INST OF GUANGDONG POWER GRID
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products