Region-based classification by combining MS segmentation and MRF for POLSAR images

作     者：Bin Zhang Guorui Ma Zhi Zhang Qianqing Qin 

作者机构：School of Electronic InformationWuhan University State Key Laboratory for Information Engineering in SurveyingMapping and Remote SensingWuhan University School of Public AdministrationChina University of Geosciences 

出 版 物：《Journal of Systems Engineering and Electronics》 (系统工程与电子技术（英文版）)

年 卷 期：2013年第24卷第3期

页      面：400-409页

核心收录：

学科分类：080904[工学-电磁场与微波技术] 0810[工学-信息与通信工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 081105[工学-导航、制导与控制] 081001[工学-通信与信息系统] 081002[工学-信号与信息处理] 0825[工学-航空宇航科学与技术] 0811[工学-控制科学与工程] 

基　　金：supported by the National Natural Science Foundation of China(61001187 41001256 40971219) the National High Technology Research and Development Program of China(863 Program)(2013 AA122301) 

主　　题：polarimetric synthetic aperture radar (POLSAR) clas-sification maximum a posteriori (MAP) mean shift (MS) Markov random field (MRF). 

摘      要：Speckle effects on classification results can be sup- pressed to some extent by introducing the contextual information. An unsupervised classification algorithm is proposed for polarimetric synthetic aperture radar （POLSAR） images based on the mean shift （MS） segmentation and Markov random field （MRF）. First, polarimetdc features are exacted by target decomposition for MS segmentation. An initial classification is executed by using the target decomposition and the agglomerative hierarchical clus- tering algorithm. Thereafter, a classification step based on MRF is performed by using the mean coherence matrices obtained for each segment. Under the MRF framework, the smoothness term is defined according to the distance between neighboring areas. By using POLSAR images acquired by the German Aerospace Centre and National Aeronautics and Space Administration/Jet Propulsion Laboratory, the experimental results confirm that the proposed method has higher accuracy and better regional connectivity than other classification methods.