Intrusion detection of foreign objects in high-voltage lines based on YOLOv4

As an important part of the intelligent inspection system of the power grid, the foreign object detection on the transmission line is of great significance to the safe and reliable operation of the power system. At present, high-voltage overhead transmission lines are mostly bare wires, insulated by air. Therefore, hanging foreign objects such as kites, balloons and plastic films can easily cause short circuits, and lead to shutdown accidents. In order to provide early warning of the danger of foreign body intrusion around the transmission line, this paper proposes a high-voltage line foreign object intrusion detection model based on Yolov4. We mainly add k-means clustering and DIoU-NMS method to optimize the original Yolov4. In the experimental evaluation, the results shows that the average accuracy of our proposed method is improved by 8.39% compared with the original YOLOv4. And the proposed method is very competitive with existing related architectures.