SDGSAT-1卫星微光影像的夜间渔船识别  

Fishing Vessel Identification by Low-light Images of SDGSAT-1 Satellites

作　　者：常昊 胡昌苗 陆俊南 闫冬梅 唐娉 CHANG Hao;HU Changmiao;LU Junnan;YAN Dongmei;TANG Ping(Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China;School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China;School of Navigation,Wuhan University of Technology,Wuhan 430070,China)

机构地区：[1]中国科学院空天信息创新研究院,北京100094 [2]中国科学院大学电子电气与通信工程学院,北京100049 [3]武汉理工大学航运学院,湖北武汉430070

出　　处：《无线电工程》2023年第11期2691-2698,共8页Radio Engineering

基　　金：国家自然科学基金(42192584);中国科学院战略性先导科技专项(A类)资助“地球大数据支撑海洋可持续发展目标研究”(XDA19090123)。

摘　　要：现代渔民常利用鱼类的趋光特性来捕鱼,在夜晚出海时在船身安装集鱼灯,使用强烈的灯光照明来吸引鱼群,从而可以捕获大量的鱼类。开启集鱼灯的渔船在夜间微光影像上具有明显的灯光辐射特征和几何特征。可持续发展科学卫星1号(The Sustainable Development Science Satellite 1,SDGSAT-1)的微光成像仪具有10 m的空间分辨率,可以轻易地探测到夜间开启集鱼灯的渔船。使用传统的形态学方法可以检测到夜间渔船的灯光。使用SDGSAT-1卫星的微光遥感影像数据,进行夜间渔船的动态监测。分析了渔船夜间灯光在影像上的辐射特征和几何特征,构建不同渔船大小和船只种类的船只识别模型。结合自动识别系统(Automatic Identification System,AIS)数据对识别的船只目标进行匹配验证,实现了影像灯光与船只的匹配。对中国南部的某渔场开展研究。实验使用了2022年3—9月的34景微光影像及对应AIS数据,研究区域的影像覆盖率达到100%。基于船只识别技术,对不同灯组数量的渔船、货船等船只实现了检测与匹配。在禁渔期的影像中检测到疑似存在非法捕鱼的渔船灯光,为微光遥感影像服务渔业检测,以及打击禁渔期非法捕捞行为提供了有效的技术手段。Modern fishermen often take advantage of the phototropic property of fish to catch fish and install fish collection lights on the hull of their vessels when they go to sea at night,using intense lighting to attract fish so that they can catch a large number of fish.Fishing vessels with fish collection lights on have apparent light radiation features and geometric features on the nighttime microlight images.The microlight imager of The Sustainable Development Science Satellite 1(SDGSAT-1)has a spatial resolution of 10 m,which can easily detect fishing vessels with fish collection lights on at night.The lights of fishing vessels at night can be detected using traditional morphological methods.The micro-light remote sensing image data of SDGSAT-1 is used for dynamic monitoring of ocean-going fishing vessels at night.The radiation characteristics and geometric features of fishing vessel lights on images at night are analyzed and vessel identification models are constructed for different fishing vessel sizes and types.Then the Automatic Identification System(AIS)data is combined to match and verify the identified vessel targets and realize the matching of image lights and vessels.Fish farms in southern China are used to conduct the research.The experiments use 34 scenes of micro-light images and the corresponding AIS data from March to September 2022.The image coverage of the study area reaches 100%.Based on the vessel identification technology,the detection and matching of fishing vessels,cargo ships,and other vessels with a different number of light sets are realized.The lights of fishing vessels suspected of illegal fishing are detected in the images of the closed fishing season,which provides an effective technical means for microlight remote sensing images to serve pelagic fishery detection and combat illegal fishing during the closed season.

关 键 词：夜间渔船识别 微光影像 可持续发展科学卫星1号 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]