Polarimetric SAR image classification using Multiple-Component Scattering Model and Support Vector Machine

The classification of polarimetric SAR image based on Multiple-Component Scattering Model (MCSM) and Support Vector Machine (SVM) is presented in this paper. MCSM is a potential decomposition method for a general condition. SVM is a popular tool for machine learning tasks involving classification, recognition or detection. The scattering powers of single-bounce, double-bounce, volume, helix, and wire scattering components are extracted from full polarimetric SAR images. Combined with the scattering power and the texture feature, SVM is used for the polarimetric classification. We generate a validity test for the method using EMISAR L-band full polarized data of Foulum Area (DK), Denmark. The preliminary result indicates that this method can classify most of the areas correctly.