Method for identifying GIS sleeve of specified equipment in infrared image and storage medium

Abstract

The invention discloses a method for identifying a GIS sleeve of specified equipment in an infrared image and a storage medium, and the method specifically comprises the following steps: S101, carrying out the image preprocessing of an initial training sample set in advance, labeling an infrared spectrum, carrying out the amplification processing of the total number of the infrared spectrum through the rotation and overturning of the infrared spectrum, and obtaining a training sample set to train a neural network model to obtain a target recognition model; S102, obtaining a to-be-processed infrared image containing the target GIS sleeve; S103, inputting the to-be-processed infrared image into the target recognition model to obtain an infrared image containing the target GIS bushing mask labeled by using the data labeling format and the equipment detection frame to which the target GIS bushing mask belongs. According to the method, the GIS sleeve in the infrared image can be effectively marked in real time by using the target recognition model obtained based on the training sample set through deep learning, and the detection position of the GIS sleeve in the infrared image and the accuracy of real target GIS sleeve detection are improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and specifically relates to a method and a storage medium for identifying a GIS casing of a designated device in an infrared image. Background technique [0002] With the wide application of infrared equipment in live detection, power supply companies have accumulated a large amount of infrared image data for operation and maintenance. Currently, they manually screen whether there are GIS casings in the infrared images, and manually mark the GIS casing in the infrared image. The location in the image for later storage and statistics. [0003] However, the efficiency of manual detection is low, the outdoor environment is complex, and the detection results cannot be given in real time. In addition, the format of manual annotation is not standardized, and the image data after annotation will not help to improve the detection efficiency and recognition rate in the future, which makes the use...

AI Technical Summary

Problems solved by technology

[0003] However, the efficiency of manual detection is low, the outdoor environment is complex, and the detection results cannot be given in real time. In addition, the format of manual annotation is not standardized, and the image data after annotation will not help to improve the detection efficiency and recognition rate in the future, which makes the use of historical data analysis. The efficiency is low, and it cannot be a powerful help for future inspection and identification work

[0004] In order to solve the problems of manual detection and labeling, related technologies are screened by image recognition technology. However, due to the problem of the shooting angle of infrared pictures, a large-scale picture is required as a training sample set, and the recognition results are often not according to the GIS casing in the picture. Angle is marked, and most of the useless background information exists in the marked area

Images