电子测量与仪器学报

胡欣,马丽军.基于 YOLOv5 的多分支注意力 SAR 图像舰船检测[J].电子测量与仪器学报,2022,36(8):141-149

基于 YOLOv5 的多分支注意力 SAR 图像舰船检测

Multi-branch attention SAR image ship detection based on YOLOv5

DOI：

英文关键词:synthetic aperture radar rotated object detection multi-branch attention circular smooth label

基金项目:国家重点研发计划（2020YFB1600400）、科技部国家重点研发计划（2021YFB1600202）项目资助

作者	单位
胡欣	1.长安大学电子控制与工程学院
马丽军	1.长安大学电子控制与工程学院

Author	Institution
Hu Xin	1.School of Electronics and Control Engineering, Chang′an University
Ma Lijun	1.School of Electronics and Control Engineering, Chang′an University

摘要点击次数: 1106

全文下载次数: 1042

中文摘要:

针对合成孔径雷达图像噪声大,成像特征不明显,尤其在面对海陆边界、港口码头、近岸岩礁等复杂场景,通常的检测算法对 SAR 图像目标特征提取困难,导致检测精度不高,出现误检漏检等问题。在 YOLOv5 的基础上设计了一种旋转的目标检测方法,提出了多分支注意力模块可以跨维度的信息融合,能更好地提取 SAR 图像目标中的位置信息和语义信息,以提高检测精度。此外,由于旋转目标检测会产生边界不连续问题影响边界框的回归,因此,利用了圆形平滑标签的方法将角度参数从回归问题转为分类问题,由此提高了精度。最后在 HRSID、SSDD+数据集上进行了实验,精度分别达到 84. 98%和 90. 13%,比原始的 YOLOv5 算法分别提升了 1. 29%和 2. 57%,实验结果证明所提算法的有效性。

英文摘要:

In view of the high noise of synthetic aperture radar images and inconspicuous imaging features, especially in complex scenes such as sea and land boundaries, ports, and coastal reefs, it is difficult for common detection algorithms to extract target features from SAR images, resulting in low detection accuracy and leak detection, etc. This paper designs a rotating target detection method based on YOLOv5, and proposes that the multi-branch attention module can be used for cross-dimensional information fusion, which can better extract the location information and semantic information in SAR image targets. In addition, the boundary discontinuity will be caused by rotating target detection, which will affect the regression of the bounding box. Therefore, the circular smooth label method is used to transform the angle parameter from regression problem to classification problem, thus improving the accuracy. Finally, experiments are carried out on HRSID and SSDD+ datasets, and the accuracy reaches 84. 98% and 90. 13%, respectively, which is 1. 29% and 2. 57% higher than the original YOLOv5 algorithm, respectively. Experimental results prove the effectiveness of the proposed algorithm.

查看全文查看/发表评论下载PDF阅读器