Unsupervised classification using polarimetric decomposition and the complex Wishart classifier

In this paper, we propose a new method for unsupervised classification of t errain types and man-made objects using polarimetric synthetic aperture rad ar (SAR) data. This technique is a combination of the unsupervised classifi cation based on polarimetric target decomposition [9] and the maximum likel ihood classifier based on the complex Wishart distribution for the polarime tric covariance matrix [15]. We use Cloude and Pottier's method to initiall y classify the polarimetric SAR image. The initial classification map defin es training sets for classification based on the Wishart distribution. The classified results are then used to define training sets for the next itera tion. Significant improvement has been observed in iteration. The iteration ends when the number of pixels switching classes becomes smaller than a pr edetermined number or when other criteria are met. We observed that the cla ss centers in the entropy-alpha plane are shifted by each iteration, The fi nal class centers in the entropy-alpha plane are useful for class identific ation by the scattering mechanism associated with each zone. The advantages of this method are the automated classification, and the interpretation of each class based on scattering mechanism. The effectiveness of this algori thm is demonstrated using a JPL/AIRSAR polarimetric SAR image.