基于改进YOLOv7的SAR图像舰船目标检测方法  

A Ship Target Detection Method for SAR images Based on Improved YOLOv7 Algorithm

作　　者：陈文翰 朱正为[1] 宋昌隆 CHEN Wenhan;ZHU Zhengwei;SONG Changlong(School of Information Engineering,Southwest University of Science and Technology,Mianyang 621000,China;China Ordnance Equipment Group Automation Research Institute Co.Ltd.,Mianyang 621000,China)

机构地区：[1]西南科技大学信息工程学院,四川绵阳621000 [2]中国兵器装备集团自动化研究所有限公司,四川绵阳621000

出　　处：《电光与控制》2024年第12期19-26,112,共9页Electronics Optics & Control

基　　金：国家自然科学基金(62071399);西南科技大学博士基金(17zx7159)。

摘　　要：为了解决SAR图像舰船目标检测的现有主流算法中图像模糊、缺乏纹理特征而导致的目标检测精度低和小目标检测难度大等问题,同时考虑不引入过多参数量以免影响网络实时性,提出了一种基于坐标注意力机制和NWD度量的改进YOLOv7的SAR图像舰船目标检测方法。首先,该方法在坐标注意力机制中引入了最大池化和残差结构,以提高模型特征提取能力;其次,将密集连接和轻量化卷积相结合,设计了SPPCSPC-P模块,以增强特征间的融合;另外,在主干网络中增加了小目标检测层,以改善模型对小目标检测精度低的问题;最后,利用NWD度量和CIoU损失设计了加权定位损失函数,进一步提高了模型检测精度。利用SSDD数据集进行实验,实验结果表明,所提方法的平均精度达到了98.38%,高于YOLOv7网络2.09个百分点。In order to solve the problems of low target detection accuracy and difficulty in small target detection caused by blurred images and lack of texture features in the existing mainstream algorithms for ship target detection in SAR images,and considering that the real-time performance of the network will be affected by introducing too many parameters,an improved YOLOv7 ship target detection method based on coordinate attention mechanism and Normalized Wasserstein Distance(NWD)metric is proposed.Firstly,the maximum pooling and residual structure are introduced into the coordinate attention mechanism to improve the model feature extraction ability.Secondly,combining dense connection with lightweight convolution,SPPCSPC-P is designed to enhance the fusion between features.In addition,a small target detection layer is added to the backbone network to improve the low detection accuracy of the model for small targets.Finally,the weighted positioning loss function is designed by using NWD metric and CIoU loss,which further improves the model detection accuracy.Experiments are carried out on SSDD dataset,and the experimental results show that the average accuracy of this method reaches 98.38%,which is 2.09 percentage points higher than that of YOLOv7 network.

关 键 词：合成孔径雷达 舰船目标检测 YOLOv7 坐标注意力机制 NWD度量 

分 类 号：TN957.52[电子电信—信号与信息处理] TP751[电子电信—信息与通信工程] U675.74[自动化与计算机技术—检测技术与自动化装置]