Electric power inspection image defect identification method and system, and electric power inspection unmanned aerial vehicle

Abstract

The invention discloses an electric power inspection image defect identification method. The method comprises the following steps: creating and cascading a target detection network and a plurality ofclassification networks; obtaining a plurality of frames of inspection image samples, labeling targets in the inspection image samples, and generating a training sample set; adopting a training sampleset to train a cascade network, wherein the quantization parameter of each network layer is related to the quantization stage number and the quantization range of the network layer where the networklayer is located; and identifying defects in the newly acquired inspection image by adopting the trained cascade network. According to the invention, an effective FPGA airborne identification system is provided for operation and maintenance of a power grid tower and an overhead line, and a corresponding quantization function can ensure that different channels of different network layers can be properly quantified, so that the precision of the network is reserved to the maximum extent; through cascading the target detection network and the classification network, the defect detection accuracy is greatly improved, and the unmanned aerial vehicle routing inspection of the power grid truly realizes automatic identification.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method and system for identifying defects in electric power inspection images, and an electric power inspection drone. Background technique [0002] The transmission lines built by the State Grid are several million kilometers long. The operation and maintenance of such long-distance distribution network overhead lines must fully rely on the comprehensive inspection of drones. Commonly used UAV platforms are equipped with high-speed image modules, infrared and ultraviolet imaging sensing modules, UHF partial discharge, ultrasonic partial discharge sensing modules and other equipment to complete comprehensive inspection operations. Among them, the high-speed image module is mainly to realize the video image acquisition function of visible light under flight conditions. The visible light image captured by the drone equipped with a high-resolution visible l...

AI Technical Summary

Problems solved by technology

[0004] However, the existing technology can only detect one or a limited number of defects. In fact, a patrol inspection task usually needs to detect most or all parts of the entire transmission line. There are many types of transmission line components and defects. , if the targeted recognition system is replaced each time, the inspection task will become quite heavy, and if you want to create a recognition system that can detect multiple targets, there are the following two problems: 1. The structure of the recognition system is complex , it is difficult to create; 2. For the recognition system that detects multiple defects at the same time, due to the different parameters used in the recognition methods of different targets, and even parameters such as abnormal weights, the calculation of the entire recognition system is large, and the actual detection accuracy and accuracy Low

Images