A supervised classification approach for PolSAR images based on covariance matrix sparse coding

Authors:

Abstract
To achieve the aim of classification for Polarimetrie synthetic aperture radar (PolSAR) images, the supervised classification approach based on sparse coding of covariance matrix is proposed in this paper. Being different from traditional classification methods which are based on polarization features extraction or statistical distribution models, our method research the sparse coding algorithm for covariance matrices under the circumstances of Riemannian manifold. The proposed method first obtains the coding dictionary by using k-means clustering. Then, each covariance matrix is decomposed into the sparse linear combination of those atoms in the coding dictionary via Riemannian sparse coding approach. Finally, the sparse coding coefficients are used as the feature vectors to obtain the final classification results with support vector machine (SVM) classifier. The experimental results of different real PolSAR images demonstrate that our method is effectiveness.

This publication has 12 references indexed in Scilit: