Bidirection-Fusion-YOLOv3: An Improved Method for Insulator Defect Detection Using UAV Image

Abstract

With advances in the continuous improvement and development of the power system, insulators have gradually become one of the most important components. At present, unmanned aerial vehicles(UAV) have been widely used to inspect insulators, and insulators in pictures are accurately and efficiently identified by convolutional neural networks and this method has been extensively applied. These existing methods have been widely used to identify insulators in pictures, with high accuracy and efficiency. However, they are based on Faster R-CNN and you only look once(YOLO) either require more identification time due to the complex network structure, or do not have sufficient accuracy for insulator defects. More identification time is required due to the complexity of the network structure, or there is not enough accuracy for insulator defects. Based on the YOLOv3 network, this paper proposes a new type of convolutional neural network(CNN) for target detection, which can improve enhance the efficiency while ensuring the detection speed. In addition, this paper applies the latest EIoU and loss functions to YOLOv3, which significantly improves the coincidence of the prediction frame and the annotation frame and accelerates the convergence speed. The experimental results show that the detection model proposed in this paper has an average precision(AP) of 0.94 for insulators and 0.89 for insulator defects, and its detection speed can reach 93.5ms/image. Finally, after experimental verification, the detection model proposed in this paper meets the requirements of power inspection and has good engineering application prospects.