Insulation terminal defect recognition method based on patrol robot

Abstract

The invention provides an insulation terminal defect recognition method based on a patrol robot. The method of the invention is mainly divided into five steps of (1) training the SVM multi-classifierby using the insulation terminal image data set collected in advance; 2) enabling the patrol robot to arrive at the designate patrol point, obtaining the field insulation terminal image and reading itin the form of a gray scale image; (3) coarse positioning and precise positioning of the target area to be detected, and screening the target candidate area to obtain the insulation terminal image; (4) preprocessing the obtained field insulation terminal image; (5) extracting the HOG feature from the sliding window, and sending the HOG feature operator to the SVM multi-classifier to get the recognition result. The machine learn is utilized, the insulation terminal detection and identification task can be effectively completed under different illumination and posture conditions, the automationlevel and the accuracy rate of the image identification under the complex environment are improved, and the problem of missing detection and false detection are reduced to the utmost extent.

Description

Technical field [0001] The present invention relates to target detection and recognition technology, in particular to a method for recognizing defects of insulated terminals based on inspection robots. Background technique [0002] The power industry is closely related to people's lives. The insulated terminal of the substation is the most basic device in the power industry, and it is very important for power supply. In recent years, the inadequate detection and identification of insulated terminals has led to the inability to transmit electricity from time to time, causing huge economic losses to people's lives and industrial production. [0003] At present, there are mainly two types of inspection methods for insulated terminals. The first is a manual inspection method. However, since most of the insulated terminals of substations exist in the field, workers are generally far away, and when defects occur, they generally cannot be solved in time, resulting in the failure of the p...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a method for identifying defects in insulating terminals based on inspection robots, which solves the problems of irregular robot positions, large changes in target scale and angle, and large impact of light on targets in the existing insulated terminal detection and identification technologies. Problems that lead to inaccurate detection and identification

Images