An Unsupervised Classification Method for Polarimetric SAR Images Based on Inhomogeneous Markov Random Field and Graph Cuts

摘要：

A new unsupervised classification method is proposed for polarimetric SAR images to keep the spatial coherence of pixels and edges of different kinds of targets simultaneously. We consider the label scale variability of images by combining Inhomogeneous Markov Random Field (MRF) and Bayes theorem. After minimizing an energy function using an expansion algorithm based on Graph Cuts, we can obtain classification results that are discontinuity preserving. Using a NASA/JPL AIRSAR image, we demonstrate the effectiveness of the proposed method.

作者: Xing Rong Jian Yang Weijie Zhang Wen Hong Fang Cao

作者单位: Dept.of Electronic Eng.,Tsinghua University,Beijing 100084,China National Key Lab of Microwave Imaging Technology Institute of Electronics,CAS,Beijing 100080,China

会议类型: 国际会议

会议名称: Progress in Electromagnetics Research Symposium 2008(2008年电磁学研究新进展学术研讨会)(PIERS 2008)

会议地点: 杭州

会议语种:英文

页码: 1-5

在线出版日期: 2008-03-24（万方平台首次上网日期，不代表论文的发表时间）