基于结构特征的高分辨率TerraSAR-X船舶识别 - 中国图象图形学报.DOCVIP

基于结构特征的高分辨率TerraSAR-X图像船舶识别方法研究 殷雄1,2 王超1* 张红1 吴樊1 中国科学院对地观测与数字地球科学中心数字地球重点实验室，北京，100094 中国科学院研究生院， 北京， 100049） 摘 要：针对高分辨率TerraSAR-X船舶图像，提出了一种基于结构特征的两阶段船舶识别方法。所识别船舶包括油船和货船两大类，根据船舶结构的不同将油船分为显示油管油船和不显示油管油船，货船分为闭合货船和不闭合货船。识别第一阶段根据船体内是否有孔洞将闭合货船与显示油管油船分为一类，不闭合货船和不显示油管分为另一类；识别第二阶段根据船体内最长直线是否在船体中部将有闭合货船与显示油管油船分开，根据船体内是否可以截断直线将不闭合货船和不显示油管油船分开。实验结果表明，采用本文方法进行船舶识别能够得到较好的识别结果。 关键字：高分辨率；TerraSAR-X；船舶识别；结构特征 中图法分类号：TP391 A Study on Vessel Recognition with High Resolution TerraSAR-X Image based on Structure Feature( YIN Xiong, WANG Chao, ZHANG Hong, WU Fan Key Laboratory of Digital Earth, Center for Earth Observation and Digital Earth, CAS, Beijing 100094, China Graduate University of the Chinese Academy of Sciences， CAS， Beijing， 100049， China） Abstract: This paper presents a two-stage vessel recognition method based on structure feature of high resolution TerraSAR-X image. The vessel contains two categories, tanker and cargo ship. The tanker includes tube showing tanker and no tube showing tanker. The cargo ship includes closed rail cargo ship and open rail cargo ship. The first recognition phase distinguished closed rail cargo ship and tube showing tanker as one class from no tube showing tanker and open rail cargo ship as the other class based on whether the ship body possessed holes, and the second phase discriminates discriminated closed rail cargo ship from tube showing tanker based on the longest lines of the ship whether existing on the middle region of the vessel and discriminates open rail cargo ship from no tube showing tanker based on whether the ship body could cut off line. The experiment obtained good result based on the method. Key words: high resolution; TerraSAR-X; vessel recognition; structure feature 0 引言 对海洋船舶进行监测与识别是每个沿海国家的重要任务，在海洋资源保护、渔船监测与管理、打击走私偷渡等方面均起到了重要作用。由于星载SAR具有覆盖范围广、平台稳定、可连续观测等突出优势，因此近年来利用星载SAR数据对海洋船舶目标进行监测与识别技术得到广泛的研究与应用。目前在美国、加拿大和欧盟，利用星载SAR技术进行船舶监测已经形成了一套完整的体系和工作流程，但是在船舶识别研究方面限于SAR数据分辨率的原因，发展不及船舶监测技术成熟，但随着新一代SAR传感器，如TerraSAR-X和Cosmo-SkyMed传