Xu Yubin, Pan Haiyan, Wang Lingqun, Zou Ran
School of Information Science, Shanghai Ocean University, Shanghai 201306, China.
Sensors (Basel). 2025 May 7;25(9):2940. doi: 10.3390/s25092940.
Synthetic aperture radar (SAR) ship detection holds significant application value in maritime monitoring, marine traffic management, and safety maintenance. Despite remarkable advances in deep-learning-based detection methods, performance remains constrained by the vast size differences between ships, limited feature information of small targets, and complex environmental interference in SAR imagery. Although many studies have separately tackled small target identification and multi-scale detection in SAR imagery, integrated approaches that jointly address both challenges within a unified framework for SAR ship detection are still relatively scarce. This study presents MC-ASFF-ShipYOLO (Monte Carlo Attention-Adaptively Spatial Feature Fusion-ShipYOLO), a novel framework addressing both small target recognition and multi-scale ship detection challenges. Two key innovations distinguish our approach: (1) We introduce a Monte Carlo Attention (MCAttn) module into the backbone network that employs random sampling pooling operations to generate attention maps for feature map weighting, enhancing focus on small targets and improving their detection performance. (2) We add Adaptively Spatial Feature Fusion (ASFF) modules to the detection head that adaptively learn spatial fusion weights across feature layers and perform dynamic feature fusion, ensuring consistent ship representations across scales and mitigating feature conflicts, thereby enhancing multi-scale detection capability. Experiments are conducted on a newly constructed dataset combining HRSID and SSDD. Ablation experiment results demonstrate that, compared to the baseline, MC-ASFF-ShipYOLO achieves improvements of 1.39% in precision, 2.63% in recall, 2.28% in AP50, and 3.04% in AP, indicating a significant enhancement in overall detection performance. Furthermore, comparative experiments show that our method outperforms mainstream models. Even under high-confidence thresholds, MC-ASFF-ShipYOLO is capable of predicting more high-quality detection boxes, offering a valuable solution for advancing SAR ship detection technology.
合成孔径雷达（SAR）舰船检测在海上监测、海上交通管理和安全维护中具有重要的应用价值。尽管基于深度学习的检测方法取得了显著进展，但性能仍受到舰船尺寸差异巨大、小目标特征信息有限以及SAR图像中复杂环境干扰的限制。虽然许多研究分别解决了SAR图像中的小目标识别和多尺度检测问题，但在统一框架内联合应对这两个挑战的综合方法仍然相对较少。本研究提出了MC - ASFF - ShipYOLO（蒙特卡洛注意力 - 自适应空间特征融合 - ShipYOLO），这是一种解决小目标识别和多尺度舰船检测挑战的新型框架。我们的方法有两个关键创新点：（1）我们将蒙特卡洛注意力（MCAttn）模块引入主干网络，该模块采用随机采样池化操作生成注意力图用于特征图加权，增强对小目标的关注并提高其检测性能。（2）我们在检测头中添加了自适应空间特征融合（ASFF）模块，该模块自适应学习跨特征层的空间融合权重并进行动态特征融合，确保跨尺度的舰船表示一致并减轻特征冲突，从而增强多尺度检测能力。在结合HRSID和SSDD构建的新数据集上进行了实验。消融实验结果表明，与基线相比，MC - ASFF - ShipYOLO在精度上提高了1.39%，召回率提高了2.63%，AP50提高了2.28%，AP提高了3.04%，表明整体检测性能有显著提升。此外，对比实验表明我们的方法优于主流模型。即使在高置信度阈值下，MC - ASFF - ShipYOLO也能够预测更多高质量的检测框，为推进SAR舰船检测技术提供了有价值的解决方案。
