Electric power equipment defect identification method and device based on electric power image and storage medium

Abstract

The invention discloses an electric power equipment defect identification method and device based on an electric power image and a storage medium. The method comprises the steps: collecting an electric power image, and constructing an electric power image database containing multi-scale electric power image blocks; performing amplification processing on the electric power image blocks in the electric power image database to obtain an amplified electric power image database; acquiring an electric power image block in the amplification electric power image database and an image feature vector ofthe electric power image to be detected; according to the image feature vector and the feature vector of the to-be-detected image, calculating the similarity between the electric power image block and the to-be-detected electric power image; sorting the electric power image blocks according to the similarity to obtain an electric power image block sorting list with gradually reduced similarity; and constructing a similarity distribution map according to the electric power image block sorting list, and identifying the electric power image containing the same electric power equipment defect asthe to-be-detected electric power image. The method can accurately and timely identify the defects of the power equipment in the power image, and ensures the safe operation of a power system.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a method, device and storage medium for identifying defects of electric power equipment based on electric power images. Background technique [0002] In recent years, with the rapid construction of the Southern Power Grid, line inspection to ensure the safe operation of the power grid has become increasingly important. With the development of intelligent inspection, from a large number of inspection power images collected by aerial photography or robots, quickly and automatically identifying images with electrical equipment defects is of great importance for timely fault repair. [0003] Since electrical equipment defects are insignificant targets in the entire image, it is impossible to realize defect recognition through conventional target detection. Although the existing technology can use classification to determine whether there are defects in the image, it...

AI Technical Summary

Problems solved by technology

[0003] Since electrical equipment defects are insignificant targets in the entire image, it is impossible to realize defect recognition through conventional target detection. Although the existing technology can use classification to determine whether there are defects in the image, it is not universal, and generally requires The image is preprocessed to convert the non-salient target in the image into a salient target. This preprocessing is a specific processing process for a specific image, not for a general target. Therefore, this classification method cannot solve the power equipment defects of the power image. classification problem

Images