Classification of Polarimetric SAR Images Based on the Riemannian Manifold

Abstract

Classification is one of the core components in the interpretation of Polarimetric Synthetic Aperture Radar (PolSAR) images. A new PolSAR image classification approach employs the structural properties of the Riemannian manifold formed by PolSAR covariance matrices. In this paper, we first review the Riemannian manifold metrics generally used in PolSAR image analysis. Then, we describe a sparse coding method for the covariance matrices in the Riemannian manifold. For supervised classification, we propose a PolSAR image classification method that considers spatial information based on kernel space sparse coding. As for unsupervised PolSAR image classification, a method that takes advantage of Riemannian sparse induced similarity is proposed. Experimental results on EMISAR and AIRSAR data demonstrate the effectiveness of the proposed methods.

Journal

Title: Journal of Radars

Publisher: Chinese Academy of Sciences

Publication date (Electronic): 01 October 2017

Volume: 6

Issue: 5

Pages: 433-441

Affiliations

[1 ] (School of Electronic Information, Wuhan University, Wuhan 430072, China)

Article

Doaj ID: 8bf38685500e4648a74a076c328a9a52

DOI: 10.12000/JR17031

License:

This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

Product

Self URI: http://radars.ie.ac.cn/fileup/HTML/R17031.htm

Self URI (journal page): http://radars.ie.ac.cn/EN/volumn/home.shtml

Categories

Subject: Technology (General)

Subject: T1-995