Unsupervised classification of PolSAR data using Freeman decomposition and fuzzy clustering

An unsupervised classification method using Freeman decomposition and fuzzy clustering is proposed to solve the ambiguity problem among surface, volume and double-bounce scattering dominated region. A fuzzy clustering method of PolSAR data making use of scattering power entropy and anisotropy parameters is proposed to partition different scattering mechanisms dominated region. The proposed method is applied to full polarimetric synthetic aperture radar data of Oberpfaffenhofen acquired by ESAR. Experiment result confirms the validity of this method.