An improved Cloude-Pottier decomposition using H/α/SPAN and complex Wishart classifier for polarimetric SAR classification

An improvement is proposed for the Cloude-Pottier decomposition using Wa/SPAN and IHSL transform. Based on this decomposition, ar. unsupervised classification with SPAN is also given in this paper. The main advantages of this decomposition are that it uses SPAN to maintain the space information for further polarimetric analysis and provides a straight way to present the result. Our experiments show that this decomposition method provides better results than the general Cloude-Pottier method and the corresponding Wishart H/a/SPAN classification also achieves better performance than the current Wishart H/a/A method.