Real-Time Detection of Insulators and Drop Fuses Based on Improved YOLOv4

Abstract

During the power grid system maintenance and overhaul, real-time detection of the insulators and drop fuses is important for the live working robots in the distribution network to plan motion. The visual system of the robot needs object detection algorithms with high detection precision, fast speed, and robustness to image brightness changes. In this paper, the improved YOLOv4 is proposed for detecting the insulators and drop fuses based on the YOLOv4. The improved YOLOv4 extracts features of power components through convolutional neural networks (CNN) and then performs feature fusion. After feature extraction and fusion, the algorithm generates prediction boxes based on anchor boxes that are clustered by fuzzy C-means algorithm (FCM) instead of K-means algorithm to detect the objects. Finally, the nonmaximum suppression algorithm (NMS) is used to obtain the final prediction results. In order to detect small targets, the improved YOLOv4 is added to a larger detection layer. For enhancing the robustness of the algorithm, data augmentation methods are carried out to enrich the data set. Combining the improvements, the test results show that the improved YOLOv4 gets higher accuracy and faster detection speed compared with the other detection algorithms based on deep learning. The mean average precision is 97.0%, and the average detection time is 0.012 s. Therefore, the improved YOLOv4 is suitable for the live working robots in the distribution network to detect the insulators and drop fuses fast and accurately.

YOLOX++ for Transmission Line Abnormal Target Detection

“…Subsequently, Ying et al [31] optimized the width and height of the prediction box and the class imbalance loss function to improve the recognition accuracy of the YOLOv3 algorithm for the bird's nest target. To detect defective insulators, Yang et al [32] added a new feature layer to the YOLOv4 model to enrich the feature information of insulators. In addition, Liu C et al [33] proposed a cross-stage partially dense YOLO model, which improved the detection performance of the network for insulators by improving its clustering algorithm and loss function.…”