Abstract: A synthetic aperture radar (SAR) ship detection algorithm with improved RTMDet (real-time models for object detection) is proposed to address the problem of low detection accuracy in small target ships and complex backgrounds in SAR images. Firstly, the basic building blocks in backbone network structure are optimized, and the global attention mechanism SimAM (simple, parameter-free attention module) is introduced, which improves the ability of the model to extract key feature information without adding additional parameters. In order to reduce the loss of small target feature information and increase its share in shallow feature map during feature fusion, a new lightweight feature fusion module SPD-RPAFPN (space to depth reverse path aggregation feature pyramid network) is constructed. Finally, the regression loss function is replaced with KFIoU (Kalman filter based intersection over union) in the prediction module to improve the detection capability of the model for small target ships. Experimental comparisons are conducted on the publicly available dataset RSDD. Compared with RTMDet, the improved model improves the inshore AP value by 14.6 percentage points and the total AP value by 2.7 percentage points to 90.7%, while the number of model parameters and computational effort are decreased by 4.5% and 10.8%. Compared with the current mainstream algorithm, the SAR ship detection accuracy is also significantly improved, which proves the effectiveness of the improved RTMDet algorithm.

Key words: SAR images, ship detection, RTMDet, SimAM, SPD-RPAFPN, KFIoU

摘要： 针对合成孔径雷达（synthetic aperture radar，SAR）图像中小目标舰船和复杂背景下舰船检测精度低的问题，提出一种改进RTMDet（real-time models for object detection）的SAR舰船检测算法。优化主干网络结构中的基本构建单元，并引入全局注意力机制SimAM（simple，parameter-free attention module），在不增加额外参数的情况下提高模型对关键特征信息的提取能力；为了在特征融合过程中减少小目标特征信息流失和增加其在浅层特征图中的融合占比，构建新的轻量级特征融合模块SPD-RPAFPN（space to depth reverse path aggregation feature pyramid network）；在预测模块中将回归损失函数替换为KFIoU（Kalman filter based intersection over union），提高模型对小目标舰船的检测能力。在公开数据集RSDD上进行了实验对比，改进后的算法相比RTMDet，模型参数量和计算量分别下降4.5%和10.8%，同时近岸AP提高14.6个百分点，总AP提高2.7个百分点，达到90.7%。与目前的主流算法对比，SAR舰船检测精度也明显提升，证明了改进RTMDet算法的有效性。

关键词: SAR图像, 舰船检测, RTMDet, SimAM, SPD-RPAFPN, KFIoU