SAR Images Processing Based On Gibbs-MRF and Connected Clustering

摘要：

This paper proposes a new method of restoration and segmentation of SAR image. The Radar cross-section (RCS) for intensity SAR images is estimated based on Gibbs Markov random fields and simulated annealing. Further, it puts forward to segment SAR image into target and shadow with the theory of connectivity in digital morphology. In this paper, Gibbs Markov random field models and simulated annealing used together for SAR images processing are discussed for the first time; a simple and effective method is presented for SAR images segmentation using the connected cluster model of pixels intensity value relevance in the neighborhood of SAR image pixel space, and obtains good segment results.

作者: Yingying Kong Yan Zhang Jianjiang Zhou

作者单位: College of information science and technology Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

会议类型: 国际会议

会议名称: The Second International Joint Conference on Computational Science and Optimization(CSO 2009)(2009 国际计算科学与优化会议)

会议地点: 三亚

会议语种:英文

页码: 896-898

在线出版日期: 2009-04-24（万方平台首次上网日期，不代表论文的发表时间）