Polarimetric SAR images segmentation incorporating texture features

Many polarimetric classification algorithms have been proposed in the literature. It has been shown that the use of spatial information provides better sensitivity for class separation such as forests. In this paper, we wish to address this issue, testing and comparing two polarimetric SAR (Synthetic Aperture Radar) segmentation approaches incorporating contextual information. The first approach is contextual fuzzy clustering based on the use of bias correction defined by a texture feature, while the second one is a Markovian segmentation based on non parametric textural modeling. These approaches have been tested on Oberpfaffenhofen area in Munich and the PolSAR images are acquired in the P band. In both cases, texture considering allowed to improve greatly the rates of good identification.