Iteration classification method and experiment study based on unsupervised classification of fully polarimetric SAR image

Based on the theory of eigen-decomposition of fully polarimetric Synthetic Aperture Radar (SAR) and maximum likelihood (ML) classifier, an unsupervised iteration classification method is proposed. It is simple, flexible with high precision. A few schemes of the iteration classification method are given. The characteristic of each scheme is carefully analyzed, according to the properties of eigen-decomposition and ML, and each scheme hold its own merit. Experiments are done on data gotten by NASA/ JPL lab near Tien Mountains, and perfect classification results are obtained. This method is robust and has high adaptability.