计算机研究与发展 DOI:10.7544/issn1000-1239.2015亲率事事 Journal of Computer Research and Developm 卷(期)起止页年 合成孔径雷达影像变化检测研究进展 公茂果苏临之李豪刘嘉 (智能感知与图像理解教育部重点实验室,智能感知与计算国际联合研究中心,西安电子科技大学,陕西西安710071) (gong @ieee. org) A survey on change detection in synthetic aperture radar imagery Gong Maoguo, Su Linzhi, Li Hao and Liu Jia (Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Xidian University, Xi'an, Shaanxi Province 710071) Abstract Change detection in remote sensing imagery is a significant issue to detect the changes happening between different times at the same area. The change detection task based on synthetic aperture radar(SAR) imagery widely concerned in recent years due to their independence on time or weather condition. This paper first gives out a brief introduction to the classical steps along with some traditional methods, and then puts its emphasis on the summary of the burgeoning methods proposed recently. By improving the traditional methods, these state-of-the-art gorithms aim at generating a difference image and to analyze it by using the threshold, clustering, graph cut and level set methods, obtaining some satisfactory results and making a contribution to an accurate detection. The algorithms are introduced from the elementary to the profound, and their performances are compared theoretically To demonstrate their effectiveness, two datasets are tested on every of these algorithms and an objective comparison is made to show the different properties of these algorithms. Finally, several meaningful viewpoints based on the practical problems for the future research of change detection are proposed, throwing light upon some further research directions Key words change detection; synthetic aperture radar; remote sensing imagery; clustering; graph cut; level set 摘要遥感影像变化检测技术用于检測同一地点在一段时间内所发生的变化情况,具有重要的应用价值。而基 于合成孔径雷达( Synthetic Aperture Radar,SAR)影像的变化检测由于其传感器具有不受时段、天气条件影响 等优良特性而在近年内受到了广泛的关注。针对SAR影像变化检测这一核心任务,首先对其经典步骤以及毎 一步的传统方法进行介绍,然后对在近年来的诸多新兴热点算法加以归纳总结。这些热点算法对差异图的生成 以及阈值、聚类、图切和水平集四种常用的差异图分析方法进行了不同程度的研究,将传统方法针对变化检测 任务进行了相应改善,取得了良好的效果。在由浅入深地介绍了这些算法同时也进行了理论上的分析对比。为 了验证这些方法的有效性,使用了两组数据集对这些方法进行了測试,定量比较了一些方法的性能。最后针对 目前SAR影像变化检测技术中需要进一步研究的内容做了展望。 关键词变化检测;合成孔径雷达;遥感影像;聚类;图切;水平集 中图法分类号TP751.1 收稿日期:yy-mm-dd修回日期:yy-mm-d 基金项目:国家自然科学基金优秀青年科学基金项目(6142209)资助计 算 机 研 究 与 发 展 DOI:10.7544/issn1000-1239.2015.******** Journal of Computer Research and Development 卷(期):起止页,年 收稿日期：yyyy-mm-dd 修回日期：yyyy-mm-dd 基金项目：国家自然科学基金优秀青年科学基金项目(61422209)资助 合成孔径雷达影像变化检测研究进展 公茂果 苏临之 李豪 刘嘉 （智能感知与图像理解教育部重点实验室，智能感知与计算国际联合研究中心，西安电子科技大学，陕西西安 710071） (gong@ieee.org) A survey on change detection in synthetic aperture radar imagery Gong Maoguo, Su Linzhi, Li Hao and Liu Jia (Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Xidian University, Xi’an, Shaanxi Province 710071) Abstract Change detection in remote sensing imagery is a significant issue to detect the changes happening between different times at the same area. The change detection task based on synthetic aperture radar (SAR) imagery is widely concerned in recent years due to their independence on time or weather condition. This paper first gives out a brief introduction to the classical steps along with some traditional methods, and then puts its emphasis on the summary of the burgeoning methods proposed recently. By improving the traditional methods, these state-of-the-art algorithms aim at generating a difference image and to analyze it by using the threshold, clustering, graph cut and level set methods, obtaining some satisfactory results and making a contribution to an accurate detection. The algorithms are introduced from the elementary to the profound, and their performances are compared theoretically. To demonstrate their effectiveness, two datasets are tested on every of these algorithms and an objective comparison is made to show the different properties of these algorithms. Finally, several meaningful viewpoints based on the practical problems for the future research of change detection are proposed, throwing light upon some further research directions. Key words change detection; synthetic aperture radar; remote sensing imagery; clustering; graph cut; level set 摘要 遥感影像变化检测技术用于检测同一地点在一段时间内所发生的变化情况，具有重要的应用价值。而基 于合成孔径雷达(Synthetic Aperture Radar，SAR) 影像的变化检测由于其传感器具有不受时段、天气条件影响 等优良特性而在近年内受到了广泛的关注。针对 SAR 影像变化检测这一核心任务，首先对其经典步骤以及每 一步的传统方法进行介绍，然后对在近年来的诸多新兴热点算法加以归纳总结。这些热点算法对差异图的生成 以及阈值、聚类、图切和水平集四种常用的差异图分析方法进行了不同程度的研究，将传统方法针对变化检测 任务进行了相应改善，取得了良好的效果。在由浅入深地介绍了这些算法同时也进行了理论上的分析对比。为 了验证这些方法的有效性，使用了两组数据集对这些方法进行了测试，定量比较了一些方法的性能。最后针对 目前 SAR 影像变化检测技术中需要进一步研究的内容做了展望。 关键词 变化检测；合成孔径雷达；遥感影像；聚类；图切；水平集 中图法分类号 TP751.1