Riemannian Nearest-Regularized Subspace Classification for Polarimetric SAR images

TL;DR

This paper introduces a Riemannian nearest-regularized subspace (RNRS) classification method for PolSAR images that effectively utilizes the original covariance matrix structure, leading to improved accuracy over existing methods.

Contribution

The paper proposes a novel Riemannian NRS approach that incorporates the Hermitian positive definite matrix structure and a new regularization term, enhancing PolSAR image classification performance.

Findings

Outperforms state-of-the-art algorithms with fewer features

Utilizes only T matrix in the proposed method

Demonstrates superior accuracy in experimental tests

Abstract

As a representation learning method, nearest regularized subspace(NRS) algorithm is an effective tool to obtain both accuracy and speed for PolSAR image classification. However, existing NRS methods use the polarimetric feature vector but the PolSAR original covariance matrix(known as Hermitian positive definite(HPD)matrix) as the input. Without considering the matrix structure, existing NRS-based methods cannot learn correlation among channels. How to utilize the original covariance matrix to NRS method is a key problem. To address this limit, a Riemannian NRS method is proposed, which consider the HPD matrices endow in the Riemannian space. Firstly, to utilize the PolSAR original data, a Riemannian NRS method(RNRS) is proposed by constructing HPD dictionary and HPD distance metric. Secondly, a new Tikhonov regularization term is designed to reduce the differences within the same class. Finally, the optimal method is developed and the first-order derivation is inferred. During the experimental test, only T matrix is used in the proposed method, while multiple of features are utilized for compared methods. Experimental results demonstrate the proposed method can outperform the state-of-art algorithms even using less features.