Comparative Analysis of ICA Based Incoherent Target Decompositions for Polsar Data

The Independent Component Analysis (ICA) has been re-cently introduced as a reliable alternative to identify canon-ical scattering mechanisms within PolSAR images. This paper addresses an overview of the most important aspects for applying such methods on real data. A new geometric classification algorithm is introduced by applying the polar decomposition and by adjusting the conventional k-means mean and distance with their counterpart on the Riemannian manifold. This method is illustrated using P-band airborne PolSAR data acquired for the ESA campaign TropiSAR cam-paign.