SAR Image Change Detection Using Watershed and Spectral Clustering

摘要：

A new method of change detection in SAR images based on spectral clustering is presented in this paper. Spectral clustering is employed to extract change information from a pair images acquired on the same geographical area at different time.. Watershed transform is applied to initially segment the big image into non-overlapped local regions, leading to reduce the complexity. Experiments results and system analysis confirm the effectiveness of the proposed algorithm.

关键词： Change detection SAR images Spectral clustering Watershed transform.

作者: Ruican Niu LC Jiao Guiting Wang Jie Feng

作者单位: Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education ofChina, X Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China,

会议类型: 国际会议

会议名称: 第七届多光谱图象处理与模式识别国际学术会议

会议地点: 桂林

会议语种:英文

页码: 1-8

在线出版日期: 2011-11-01（万方平台首次上网日期，不代表论文的发表时间）