Unmanned aerial vehicle power transmission line inspection method based on deep learning image recognition

Abstract

The invention belongs to the technical field of power transmission line automatic inspection, and particularly relates to an unmanned aerial vehicle power transmission line inspection method based on deep learning image recognition. According to the method, firstly, image recognition is carried out according to an image shot by holder equipment carried by an unmanned aerial vehicle, a target point in the image is extracted, then frame selection is carried out on the target point in the image, the frame selection position of the target point is compared with a standard position, and the position and angle of a power transmission line of a power tower relative to the unmanned aerial vehicle are judged. the least square fitting is carried out on the normalized coordinates of the power transmission line image and the weighted pixel coordinates of the power transmission line so as to judge the direction of the power transmission line, adjusting the unmanned aerial vehicle, enabling the unmanned aerial vehicle to be parallel to the power transmission line, and starting routing inspection along the power transmission line. The unmanned aerial vehicle can be controlled to move along the power transmission line between the power towers by analyzing the images collected by the unmanned aerial vehicle, so that the purposes of unmanned aerial vehicle cruising and power transmission line anomaly detection are achieved.

Description

technical field [0001] The invention belongs to the technical field of automatic inspection of power transmission lines, and in particular relates to a UAV transmission line inspection method based on deep learning image recognition for autonomous inspection of transmission lines connected to power poles and towers. Background technique [0002] With the development of drone technology, there are more and more industries that use drones to replace manual inspection operations, and power inspection is one of them. The high mobility, versatility, and portability of drones all play an important role in power inspections. However, the efficiency of traditional drone inspection operations is low, and often requires a professional team of two or more to operate. Although drones are highly mobile, they cannot be fully utilized due to the limitation of remote sensing distance, especially in mountainous deserts. The impact is more significant in areas where the operator has difficul...

AI Technical Summary

Problems solved by technology

However, the efficiency of traditional drone inspection operations is low, and often requires a professional team of two or more to operate. Although drones are highly mobile, they cannot be fully utilized due to the limitation of remote sensing distance, especially in mountainous deserts. The impact is more significant in areas where the operator has difficulty moving

[0003] In order to get rid of the shackles of manual operation, in the field of UAV autonomous cruising, although laser point cloud data can be used to model the transmission corridor to realize the function of UAV automatic cruising, but the laser equipment is expensive, high in quality and functional. Serious power consumption, not suitable for drones to work for a long time

Images