Research on Image Recognition of Insulators Based on YOLO Algorithm

Abstract

Insulators are important components of power transmission and transformation equipment in power systems. Insulator identification is a basis work for evaluation of insulation status of insulators in computer vision. With the recent development of big data and cloud computing technologies, terminal-to-terminal picture recognition was accomplished based on deep learning algorithms, making it possible to apply insulator image recognition in power systems. This paper firstly introduced the research background of deep learning: the recent YOLO (You Only Look Once) convolutional neural network algorithm, established insulator image databases for train and test, and preprocessed the images of training insulator images with the TensorFlow platform. With the YOLO algorithm applied, the training of the image database for 5 days was completed, and a good recognition result was achieved. Then the results were compared between the Fast R-CNN algorithm and the YOLO algorithm in identify speed and accuracy. Based on relevant paper, the accuracy of insulator image recognition is defined, and the factors that affect the accuracy of insulator image recognition are discussed: It is concluded that the accuracy of identification increases with the increase in the number of training insulators, which is the next step in the identification of insulators.