YOLO-DFT: An object detection method based on cloud data fusion and transfer learning for power system equipment maintenance

Abstract

Object detection techniques have been widely used in power system equipment maintenance. However, in power systems, the accuracy of object detection is limited by the scarcity of publicly available datasets and the lack of scene pertinence. In order to solve these problems, an object detection method based on cloud data fusion and transfer learning (YOLO-DFT) for power system equipment maintenance is proposed. Illustratively, YOLO-DFT focuses on the object detection task involving birds and humans, generating a substantial and resilient human-bird dataset through cloud-based data fusion to compensate for the dearth of public datasets in the power system domain. By seamlessly integrating the YOLOv5 algorithm with a transfer learning strategy, a targeted detection mechanism for specific locations is meticulously formulated. The experimental results demonstrate that YOLO-DFT effectively addresses object detection challenges in power systems, achieving a Mean Average Precision (MAP) measure of 0.925 across all classes, thereby providing a valuable reference for the maintenance of power system equipment.