An Unsupervised Classification Method Using Wishart H/a/SPAN Algorithm
Conference: EUSAR 2006 - 6th European Conference on Synthetic Aperture Radar
05/16/2006 - 05/18/2006 at Dresden, Germany
Proceedings: EUSAR 2006
Pages: 4Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Fang, Cao; Wen, Hong; Yirong, Wu (National Key Lab. of Microwave Imaging Technology, the Institute of Electronics, Chinese Academy of Sciences, P. R. China)
Fang, Cao (The Graduate School of Chinese Academy of Sciences, P.R. China)
Abstract:
In this paper, an unsupervised classification method is proposed for full polarimetric SAR data. The Wishart segmentation algorithm is used to perform the segmentation. The backscatter mechanism power SPAN combined with the entropy H and the α angle is used to initialize this segmentation. The experiments show that though the performance of this H/α/SPAN classification is only slightly better than the one provided by the Wishart H/α/A method in general areas, it is greatly improved compared with the H/α/A in the farm areas.