Multi Scale Ship Detection Based on Attention and Weighted Fusion Model for High Resolution SAR Images

Ship detection in SAR images is a challenging problem. CNN-based ship detection method in SAR images has achieved remarkable results. Due to the multi scale of the ships and interference from complex sea conditions or nearshore background in SAR images, many false alarms and missed detections can occur in ship detection. To solve these problems, a multi-scale ship detection network in SAR images based on attention and weighted fusion is proposed in this paper. First, a higher-resolution detect head is added based on the YOLOv5 framework for detecting tiny-scale ships in SAR images. Then, the coordinate attention block is introduced to refine the location features of ship targets and suppress the interference of complex background. Finally, in the feature fusion stage, adaptive weighted feature fusion is used to reduce feature redundancy. Experiments on the SSDD dataset show the effectiveness of the proposed method.