基于深度学习的遥感图像舰船目标检测算法综述  

Review of deep learning-based algorithms for ship target detection from remote sensing images

作　　者：黄泽贤 吴凡路 傅瑶[1] 张雨 姜肖楠[1] HUANG Zexian;WU Fanlu;FU Yao;ZHANG Yu;JIANG Xiaonan(Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院长春光学精密机械与物理研究所,吉林长春130033 [2]中国科学院大学,北京100049

出　　处：《光学精密工程》2023年第15期2295-2318,共24页Optics and Precision Engineering

基　　金：国家自然科学基金青年科学基金资助项目(No.42001345)。

摘　　要：海面舰船目标检测是遥感图像处理和模式识别领域备受关注的重点研究方向,对舰船目标的自动检测在民用和军用方面都具有重大意义。梳理和分析了典型基于深度学习的目标检测算法的优缺点,并进行了对比和总结;归纳了基于深度学习的舰船目标检测的技术现状,并从多尺度检测、多角度检测、小目标检测、模型轻量化和大幅宽遥感图像舰船目标检测等方面对技术现状进行了详细的介绍。最后,介绍了舰船目标识别算法常用的评价标准和现有的舰船图像数据集,探讨了遥感图像舰船目标检测算法现在所面临的问题和未来的发展趋势。The detection of naval targets is a key area of research interest in the field of remote sensing im⁃age processing and pattern recognition.Moreover,the automatic detection of naval targets is crucial to both civil and military applications.In this study,we discuss and analyze the advantages and disadvantages of typical deep-learning-based target-detection algorithms,compare and summarize them,and summarize state-of-the-art deep-learning-based ship target detection methods.We also provide a detailed introduction to five aspects of state-of-the-art ship target detection methods,including multi-scale detection,multi-an⁃gle detection,small target detection,model light-weighting,and large-format wide remote sensing imag⁃ing.We also introduce the common evaluation criteria of ship target recognition algorithms and existing ship image datasets,and discuss the current problems faced by ship target detection algorithms using re⁃mote sensing images and future development trends in the field.

关 键 词：遥感图像 舰船目标检测 卷积神经网络 图像数据集 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]