神经网络在SAR图像目标识别中的研究综述  

Research Summary of Convolutional Neural Network in SAR Image Target Recognition

作　　者：冯博迪 杨海涛 李高源 王晋宇 张长弓 FENG Bodi;YANG Haitao;LI Gaoyuan;WANG Jinyu;ZHANG Changgong(Graduate School,Space Engineering University,Beijing 101416,China;School of Space Information,Space Engineering University,Beijing 101416,China)

机构地区：[1]航天工程大学研究生院,北京101416 [2]航天工程大学航天信息学院,北京101416

出　　处：《兵器装备工程学报》2021年第10期15-22,共8页Journal of Ordnance Equipment Engineering

摘　　要：传统的SAR图像目标识别方法都存在局限性,而利用深度学习自学习的特点,使得SAR图像目标识别能够克服人为选择目标特征的困难。论述了卷积神经网络在SAR图像目标识别分类领域的研究进展,介绍了SAR自动目标识别的基本概念以及传统的识别方法及其优缺点,以及卷积神经网络的基本组成,在光学领域的发展现状,分析了卷积神经网络在SAR图像相干斑噪声抑制和SAR图像目标识别中的经典研究方法和研究现状,给出了卷积神经网络在该领域应用中的不足,展望了未来研究方法。SAR image target recognition technology has an important influence on the wide application of SAR.Traditional methods of SAR image target recognition have some limitations,but the self-learning ability of deep learning can help solving the problem of selecting target features manually.This paper summarized the research progress of convolutional neural networks in the field of SAR image target recognition and classification.The basic concepts of SAR ATR was introduced,as well as traditional recognition methods and their advantages and disadvantages.The basic components of convolutional neural networks and the status quo of its development in the optical field was introduced as well,in which the classical research methods and current research status of convolutional neural network in speckle suppression and SAR target recognition were mainly introduced.Further more,the shortcoming of the application of convolutional neural networks in this field was given,and areas need further research were discussed.

关 键 词：合成孔径雷达 目标识别 卷积神经网络 相干斑噪声抑制 

分 类 号：TN959[电子电信—信号与信息处理]