Insulator defect automatic detection algorithm for electric power inspection video

Abstract

The invention discloses an insulator defect automatic detection algorithm for an electric power inspection video. The algorithm comprises the following steps: step 1, classifying and enhancing original electric power tower insulator sample data; step 2, building and generating a convolutional neural network model, and training the network model through the data enhanced in the step 1; step 3, processing the to-be-detected image, extracting HOG features of the image passing through the network model through the established network model, and determining the approximate position of the insulatorin the image; step 4, after the approximate position of the insulator in the picture is determined through the step 3, whether the insulator is defective or not is detected through a CNN / LSTM deep learning method; according to the method disclosed by the invention, the defects of an existing power tower insulator defect detection method are overcome, a deep learning method is used, and the influence of other environmental factors in a sample is avoided. And the image is further processed and analyzed in combination with image features, so that the detection process is more accurate and efficient.

Description

technical field

[0001] The invention belongs to the technical fields of image processing, machine vision and artificial intelligence, and relates to an automatic detection algorithm for insulator defects oriented to electric power inspection video. Background technique

[0002] On the power transmission line, it is very important to ensure the safety and correctness of the power tower and the line. It is very important to detect and deal with the problems of the insulator in the overhead transmission line. Due to the influence of the environment and power changes, the insulator will cause different degrees of dirt and defects. This will seriously damage the service life of the transmission line, and even burn out the equipment and cause a power outage, causing serious accidents in power production. In order to avoid insulator failure, the power production process can only increase the number of inspections, while manual inspection is inefficient, poor reliability, and costly....

Images