摘要
作为人工智能的重要分支,深度学习在近年来飞速发展,已成功应用于多个领域的研究工作中。深度学习算法为解决雷达信号处理领域的瓶颈问题提供了新的突破口,也带来了新的技术难题。文中针对深度学习在低截获与无源雷达波形识别、自动目标识别、干扰杂波信号的识别与抑制以及雷达波形与阵列设计等领域的应用进行了全面梳理总结,重点介绍和分析了近年来提出的基于深度学习的雷达波形识别和合成孔径雷达图像自动目标识别方法,阐明了限制深度学习算法性能的主要因素,旨在为相关领域科研人员开展后续研究提供参考依据。
As of the most important branches of artificial intelligence, deep learning(DL) has developed rapidly in recent years, and has been successfully used in many research fields. Although the DL-based algorithms offer a great opportunity for researchers to finally conquer the bottleneck problems in the field of radar signal processing, they also bring about brand-new technical challenges. In this paper, comprehensive review of the applications of DL methods is proposed, including low probability of interception and passive radar waveform recognition, automatic target recognition, radar jamming/clutter recognition and suppression, and radar waveform and antenna array design. Recently the proposed DL-based radar waveform recognition and SAR automatic target recognition methods are summarized and analyzed in detail. The major factors limiting the performance of the DL algorithms are also examined. This work aims to provide valuable information to the scholars in this promising field of research.
作者
吴迪
徐滢
汪倍宁
耿哲
朱岱寅
WU Di;XU Ying;WANG Beining;GENG Zhe;ZHU Daiyin(Key Laboratory of Radar Imaging and Microwave Photonics,Ministry of Education,Nanjing University of Aeronautics and Astronautics,NI anjing 211106,China)
出处
《现代雷达》
CSCD
北大核心
2022年第12期1-7,共7页
Modern Radar
基金
江苏省自然科学基金青年基金资助项目(BK20200420)
工信部民机专项项目(MJ-2018-S-28)。
关键词
深度学习
波形识别
自动目标识别
低截获概率
deep learning
waveform recognition
automatic target recognition(ATR)
low probability of intercept
