Parameters estimation of polarimetric Gp0 distribution with MoLDC method

Gp0 distribution has recently been proposed as a good model for characterizing multilook polarimetric SAR images of different homogeneity. Nevertheless, parameters estimation has always been a problem that hinders its use in practical application. In this paper, we first describe the shortcomings of classical maximum likehood method(ML) and moment based method(MoM), then starting from the second kind statistics and Mellin transform, we derive a new and simple method to estimate parameters. Experiments on real SAR images demonstrate its validity and superiority over the ML and MoM methods.