Method for detecting insulator string breakage defect based on sparse representation

Abstract

The invention relates to a method for detecting an insulator string breakage defect based on sparse representation. The method comprises the steps of firstly performing image segmentation on a shot original image containing an insulator string by using an image segmentation algorithm, removing background interferences such as accumulated snow and transmission lines, and segmenting the image into a plurality of regions which are not mutually connected; then performing ASIFT (Affine Scale-Invariant Feature Transform) matching on the regions which are not mutually connected and insulators in an insulator string library, wherein regions with the number of matching points being higher than a preset threshold are insulator string regions; then performing insulator single-disc segmentation on the recognized insulator string regions to acquire a plurality of insulator small discs; and finally, performing classified labeling on each insulator small disc by using a sparse representation classifier, recognizing whether each single small disc has a string breakage defect or not, and performing positioning and labeling in the original image. Compared with other methods, the method has higher recognition accuracy and is accurate in defect positioning.

Description

technical field [0001] The invention relates to the technical field of transmission line spare parts detection, in particular to a method for detecting insulator string drop defects based on sparse representation. Background technique [0002] Insulators are special insulation controls that can play an important role in overhead transmission lines. In the early years, insulators were mostly used on utility poles, and gradually developed into a high-voltage wire connection tower with many disc-shaped insulators hanging on one end. It is used to increase the creepage distance, usually made of glass or ceramics, and is called an insulator. Insulators should not fail due to various electromechanical stresses caused by changes in the environment and electrical load conditions, otherwise the insulator will not have a significant effect. The service life and operating life of the line. Regular insulator defect detection and timely replacement according to the detection results ca...

AI Technical Summary

Problems solved by technology

In the past, the detection and maintenance of insulators required a lot of manpower to detect along the transmission line, which cost a lot of time and money. With the development of electronic image processing, image processing technology is used to analyze and process insulators, and then realize automatic detection of insulator defects. It can effectively reduce the burden on the staff and has practical significance for automatic inspection of transmission lines, but the existing detection technology has problems of low precision and inaccurate defect location

Images