Opening and closing state identification method

Abstract

An opening and closing state identification method is characterized by comprising the following steps: step 1, collecting a plurality of opening and closing sample images, and training an SVM multi-classifier by using the sample images; step 2, collecting a to-be-identified opening and closing image, and converting the opening and closing image into a gray level image; step 3, performing coarse positioning in the grayscale image to obtain a coarse positioning candidate region; Performing accurate positioning on the grayscale image to obtain a plurality of accurate positioning candidate regions; Screening out a final target image for identifying the opening and closing states between the coarse positioning candidate area and the plurality of accurate positioning candidate areas; step 4, preprocessing the acquired target image; and step 5, extracting HOG features from the target image, and sending the HOG feature operator obtained through calculation to an SVM multi-classifier to obtaina final identification result. The method can effectively improve the accuracy of target area positioning and opening and closing state identification.

Description

technical field [0001] The invention belongs to the field of image recognition, in particular to a method for recognizing an opening and closing state. Background technique [0002] The power industry is closely related to people's lives. The opening and closing of substations is the most basic device in the power industry, and it is crucial to power supply. In recent years, the detection and identification of opening and closing are not in place, which leads to the phenomenon that the normal transmission of electricity occurs from time to time, causing huge economic losses to people's lives and industrial production. [0003] At present, there are mainly two types of detection methods for opening and closing. The first is the manual inspection method. However, since the opening and closing of substations mostly exist in the field, the staff are generally far away, and when the opening and closing are not in place, they generally cannot be resolved in time, which leads to t...

AI Technical Summary

Problems solved by technology

However, most of the current methods use traditional image processing methods for detection and recognition. In the case of changing lighting conditions, the detection effect is not good. Generally, one lighting condition requires a set of parameters, which requires a more general method. Detection and recognition methods to deal with detection tasks under different lighting and attitude conditions

Images