Accurate positioning method for power transmission line unmanned aerial vehicle inspection image detection defects

Abstract

The invention provides an accurate positioning method for power transmission line unmanned aerial vehicle inspection image detection defects. The accurate positioning method comprises the steps of (1)constructing a point cloud space electrical component distribution vector; (2) acquiring defect image orientation elements; (3) establishing mapping; and (4) carrying out accurate positioning. According to the invention, high-precision POS information (shooting center space coordinates, a holder angle, a camera focal length and the like) of a defect image shooting instantaneous camera is obtainedthrough inertial navigation in combination with a GNSS rear difference technology; a photographing center and an imaging plane are simulated in the point cloud space; and the three-dimensional pointsof the electrical components in the laser LiDAR point cloud space are projected onto the two-dimensional image plane of the simulated unmanned aerial vehicle image by using an aerial survey collinearequation and a central projection imaging principle, and a mapping relationship between inspection image pixels and the three-dimensional points of the point cloud is established so as to realize three-dimensional positioning of defect pixels in the point cloud space.

Description

technical field [0001] The invention relates to a precise positioning method for detecting defects in a power transmission line UAV inspection image, which belongs to the power transmission line UAV inspection data processing technology. Background technique [0002] With the continuous development of UAV technology, UAVs have been widely used in the inspection of overhead transmission lines. UAV inspection technology takes pictures of transmission lines as a means to obtain high-definition image data of electrical equipment such as towers, insulators, wires, line corridors, fittings, etc., to realize defects such as broken lines, insulators falling off, and foreign objects hanging on lines. rapid detection. UAV inspection data processing generally adopts image recognition to automatically identify defects contained in inspection images. With the continuous development of intelligent identification technologies and means, the accuracy of automatic defect identification cont...

AI Technical Summary

Problems solved by technology

However, due to the lack of precise location information of detected defects in the inspection images of UAVs, it is only possible to roughly locate the detected defects to a certain tower or a certain location by relying on the instantaneous coordinates when the UAV is shot in the POS information stored in the UAV. In the first gear, it is impossible to specify the specific defective electrical components for the maintenance personnel, and the maintenance personnel still need to go to the tower to check on the spot

At present, there is no automatic processing method for the precise positioning of image detection defects, which requires maintenance personnel to visually identify inspection images, and even some inspection images with large focal lengths and lack of overall information on towers cannot be visually identified manually Field defect location

Images