Unmanned aerial vehicle inspection track automatic generation method based on electric power tower point cloud

Through the automatic generation method of drone patrol trajectory based on power pole tower point cloud, clustering, classification and corrosion algorithms are used to identify power lines and insulators, and combined with ACO and RRT* algorithms to generate drone patrol trajectory, the problem of insufficient artificial dependence and intelligence in the existing technology is solved, and the efficiency and automation of drone patrol are improved.

CN119723377AActive Publication Date: 2025-03-28STATE GRID HUBEI ELECTRIC POWER RES INST +1
5 Cites 3 Cited by

Patent Information

Application Number
CN202411662214.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-20
Publication Date
2025-03-28
Estimated Expiration
2044-11-20

AI Technical Summary

Technical Problem

In the prior art, power inspection operations rely on manual operations, resulting in low data processing efficiency, inaccurate settings of aerial photography points, and insufficient intelligence of drone route planning software, which limits the promotion and application of drone inspection.

Method used

The automatic generation method of drone patrol trajectory based on power pole tower point cloud is adopted, point cloud data is collected through lidar, DBSCAN algorithm is used for clustering, PointNet classification algorithm judges point cloud cluster type, corrosion algorithm recognizes power lines and insulators, and combines ACO and RRT* path planning algorithms to generate the optimal drone patrol trajectory.

Benefits of technology

It reduces the labor cost of drone inspection trajectory planning operations, improves the efficiency of drone inspection operations, and realizes automated processing of complex power tower environments and intelligent planning of drone routes.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an unmanned aerial vehicle inspection track automatic generation method based on electric power tower point cloud. The method comprises the steps of obtaining space coordinates of the top end of a target inspection tower; extracting an edge point cloud of an area within a certain range of the space coordinates, and performing spatial clustering by using a DBSCAN clustering algorithm to obtain a point cloud cluster; identifying and classifying each point cloud cluster based on a PointNet algorithm, and screening out point clouds with power line features; a corrosion algorithm is applied, the outermost edge point, away from a tower, on the point cloud of the power line serves as a starting point, corrosion is conducted in the line direction, and insulators are recognized and extracted from line branches; according to a shooting rule of unmanned aerial vehicle inspection and an inclination angle of a tower connecting power line, generating a to-be-shot point position on the equipment, and calculating a corresponding unmanned aerial vehicle flight path point; and generating and exporting an unmanned aerial vehicle inspection route file. The method reduces the labor cost of unmanned aerial vehicle route planning, and is widely applied to point cloud processing of various electric tower devices and unmanned aerial vehicle routing inspection route planning scenes.
Need to check novelty before this filing date? Find Prior Art