PolSAR image classification based on deorientation theory

The randomly distributed target orientation causes confusion in classification of the polarimetric scattering target. In this paper, we proposed an unsupervised classification method to the fully polarimetric SAR (PolSAR) image to solve this problem. Firstly, we make a certain angle rotation of this part along the sight line to minimize the cross-polarized scattering; then we make an initial classification using the scattering mechanism described by the parameters; finally, using the initial classification result, the PolSAR image is classified by the modified C-mean algorithm. Experiment is performed on the real measured data; the result shows the proposed method is effective.