DBW-YOLO: A High-Precision SAR Ship Detection Method for Complex Environments

Synthetic aperture radar (SAR) is widely used for ship target detection with the application of deep learning techniques. However, in certain complex environments such as near shore or with small ships, the problem of false alarms and missed detections still exists. To address these issues, a high-precision ship target detection method named DBW-YOLO, which builds upon YOLOv7-tiny as its foundational network, is proposed in this paper. The proposed method consists of the following main steps. Firstly, a feature extraction enhancement network based on deformable convolution network (DCNet) is introduced to obtain more comprehensive feature representations across various ship types. Secondly, an adaptive feature recognition method based on BiFormer attention mechanism is proposed to strengthen detection accuracy, which is more beneficial to capture near shore ships and small ships. Thirdly, a Wise Intersection-over-Union (Wise IoU) based on dynamic non-monotonic focusing mechanism is proposed to generate the loss function, which improves the convergence speed and generalization ability. Consequently, the DBW-YOLO method trains a more robust model that better utilizes samples from near shore and small ships. To verify the effectiveness of this method, two SAR datasets, HRSID and SSDD, are employed for performance evaluation. Compared to other widely-used methods, the mAP value of DBW-YOLO reachs 88.84% and 99.18% on the HRSID and SSDD datasets, respectively. The findings indicate that DBW-YOLO method outperforms other representative SAR ship detection methods in both accuracy and overall performance.