YOLO-based multi-class target detection for SAR images

The current SAR image target detection mainly focuses on single category target detection problem in single task scenario, and no research has been conducted on multi-category target detection in different scenarios. YOLO is widely used in target detection tasks because of its speed and accuracy. In this paper, the YOLOv3, YOLOv5 and YOLOv8 algorithms, which have better detection performance and are more widely used, are used to perform target detection on the SAR image multi-category target detection dataset MSAR-1.0, and the detection results are analyzed from both the SAR image multi-category target detection dataset and the YOLO algorithm.