基于高效聚合特征增强网络的合成孔径雷达船舰检测方法  

Synthetic Aperture Radar Ship Detection Method Based on Highly Efficient Aggregated Feature Enhancement Network

作　　者：单慧琳[1,2] 刘文星 王兴涛 付相为 李长帅 张银胜 Shan Huilin;Liu Wenxing;Wang Xingtao;Fu Xiangwei;Li Changshuai;ZhangYinsheng(School of Electronics&Information Engineering,Nanjing University of Information Science&Technology,Nanjing 210044,Jiangsu,China;School of Electronic&Information Engineering,Wuxi University,Wuxi 214105,Jiangsu,China)

机构地区：[1]南京信息工程大学电子与信息工程学院,江苏南京210044 [2]无锡学院电子信息工程学院,江苏无锡214105

出　　处：《光学学报》2024年第12期309-319,共11页Acta Optica Sinica

基　　金：国家自然科学基金(62071240,62106111);江苏省一流本科课程(2021YLKC005);江苏省产教融合型一流课程(2022-133)。

摘　　要：合成孔径雷达(SAR)由于散射效应以及波长和天线尺寸的分辨率限制,难以获取小尺寸目标的细节和边界信息,因此,检测准确性不高。为了提高SAR船舰检测的准确率以及降低误检率,提出了一种基于高效聚合特征增强网络的SAR船舰检测方法。首先,在主干网络中采用空间通道注意力机制,构建出高效层卷积块作为主要的特征提取模块,以增强模型的特征获取性能,提高模型对船舰目标的识别能力;其次,特征融合部分采用Inception NeXt模块来提高算法效率;最后,在主干网络以及特征提取部分之间构建出一种全局增强特征金字塔分支结构,进一步融合全局特征,避免传输过程中的低维度特征损失,以提升网络的特征融合能力,使其即使对于复杂背景下的小目标仍然能展现出可靠的检测能力。为了证明所提网络的有效性,在SSDD数据集上作了对比实验,实验结果表明,相较于YOLOv7,所提网络的准确率提升了2.5个百分点,召回率提升了9.2个百分点,交并比(IoU)阈值为0.5时的平均精度提升了6.4个百分点,IoU为0.5∶0.95时的平均精度提升了9.9个百分点。实验结果证明,所提网络在提升SAR船舰检测精度、改善误检漏检等方面有显著优势,可作为高精度的检测方法来有效应对SAR船舰检测中存在的问题。Objective Synthetic aperture radar(SAR)is a microwave imaging radar that utilizes the principle of synthetic aperture to achieve high resolution.It has various characteristics such as all day,all weather,high resolution,and wide bandwidth.It is not affected by weather,day,and night and can obtain high-quality,high-resolution,large-scale,and long-distance images.SAR ship target detection technology can provide important technical support in industries such as ocean,oil,port management,marine resource development,and marine scientific research,as it can detect ships and equipments on the sea and detect potential safety risks in advance.At the same time,ship target detection technology has important strategic significance for strengthening maritime monitoring,border patrol,maritime rescue,and safety assurance of maritime channels.We aim to improve the accuracy of SAR ship detection,reduce false positives,and enhance the adaptability of the model.Methods Traditional SAR image target detection methods include texture analysis,polarization characteristics,and constant false alarm rate(CFAR)algorithms.Among them,the most widely used is the CFAR detection algorithm,which has certain advantages in speed,but its drawbacks are high computational complexity and susceptibility to complex backgrounds,resulting in unsatisfactory detection efficiency.In the actual SAR imaging process,the backgrounds of SAR images are mostly ports,islands,reefs,and other buildings.These backgrounds have high grayscale characteristics and strong confusion.Therefore,for the detection of ship targets on the sea,multiple complex backgrounds,various irregular arrangements of ships,similar target misdetection,and other uncertain factors should be considered.The target features of uncertain factors have a certain degree of similarity with ships.Therefore,we propose an efficient aggregation feature enhancement network(EAFENet)to solve the problems of low accuracy,serious false detections,and unstable effects in current SAR ship target detection.The core

关 键 词：深度学习 目标检测 高效聚合特征增强网络 注意力机制 合成孔径雷达船舰检测 

分 类 号：TN959.17[电子电信—信号与信息处理]