Defect identification method and device of power equipment, computer equipment and storage medium

Abstract

The invention relates to a defect identification method and device of power equipment, computer equipment and a storage medium. The method comprises the steps of receiving a to-be-recognized image sent by a machine nest, and obtaining the to-be-recognized image by shooting power equipment through an unmanned aerial vehicle configured in the machine nest; obtaining a reference feature vector library corresponding to the to-be-recognized image , determining a to-be-recognized feature vector set based on the to-be-recognized image, wherein the reference feature vector library comprises a reference feature vector set of a plurality of reference images, and the reference images are images when the power equipment lacks parts; and determining an identification result based on the reference feature vector library and the to-be-identified feature vector set, and sending the identification result to the cloud server. According to the method, the defect identification efficiency is improved, and real-time identification of the defects of the power equipment can be realized.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a defect identification method, device, computer equipment and storage medium of electric equipment. Background technique [0002] The application of multi-rotor UAV technology in the inspection of power transmission lines in the power industry has matured. The current multi-rotor UAV inspection mode is mainly to control the UAV to automatically inspect the power line according to the three-dimensional route planned in advance by the flight control application APP of the mobile terminal. Since the flight time supported by the battery power of the multi-rotor UAV is not much, the inspection of the entire line cannot be completed at one time. The latest technology to solve this problem is to use the "nest-drone" method for line inspection, that is, Install drone nests according to the line section, each nest is fixed with a drone, the drone can be charged in the...

AI Technical Summary

Problems solved by technology

However, there are usually a large number of images to be identified on the inspection line of sight. The existing defect identification method is complex and requires high computing power and memory of the server. It takes a long time to perform a defect identification, resulting in the image The efficiency of defect identification is low, and it is impossible to realize real-time identification of electrical equipment defects

Images