Unsupervized classification of full polarimetric SAR data and feature vectors identificat1on using radar target decomposition theorems and entropy analysis

Classification of Earth terrain components within a full polarimetric SAR image is one of the most important applications of radar polarimetry in remote sensing. An unsupervised classification procedure, based around neural networks with competitive architecture, is applied to the full polarimetric SAR images of San Francisco Bay (NASA/JPL 1988) for segmentation and clustering of different Earth terrain components. An identification procedure, based on polarimetric decomposition theorems is presented from which a new approach to the interpretation of different scattering mechanisms is obtained after clustering.