摘要
SAR图像目标识别在民用和军事领域都具有重要的理论价值和应用前景,是当前目标识别及遥感信息处理研究领域中的一个热点问题。论文对SAR图像目标识别的国内外研究现状进行了综述,分析了各方法的优缺点。其中,深度学习方法具有自动提取层次化特征的优点,提高了目标识别率,在目标识别领域取得了许多优异的成果。最后介绍了SAR图像目标识别技术存在的问题以及发展趋势。
SAR image target recognition has important theoretical value and application prospects in both civil and military fields. It is a hot research topic in the field of target recognition and remote sensing information processing. This review paper was the research status of SAR image target recognition, and analyzed the advantages and disadvantages of each method. Among them, the deep learning method has the advantages of automatically extracting hierarchical features, improves the target recognition rate, and has achieved many excellent results in the field of target recognition. Finally, the problems and development trends of SAR image target recognition technology were summarized.
作者
范欣妍
朱卫纲
冉小辉
FAN Xinyan;ZHU Weigang;RAN Xiaohui(Department of Graduate Management, Space Engineering University, Beijing 101416, China;Department of Electronic and Optical Engineering, Space Engineering University, Beijing 101416, China)
出处
《兵器装备工程学报》
CAS
北大核心
2019年第A01期183-188,共6页
Journal of Ordnance Equipment Engineering
关键词
SAR
目标识别
深度学习
卷积神经网络
综述
SAR
target recognition
deep learning
convolution neural network
review
