Multi-Frequency Polarimetric SAR Classification Based on Riemannian Manifold and Simultaneous Sparse Representation

被引:25
作者
Yang, Fan [1 ]
Gao, Wei [1 ]
Xu, Bin [1 ]
Yang, Jian [1 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China
关键词
STATISTICAL-ANALYSIS; DECOMPOSITION; SEGMENTATION; REGRESSION; SELECTION; MODEL;
D O I
10.3390/rs70708469
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Normally, polarimetric SAR classification is a high-dimensional nonlinear mapping problem. In the realm of pattern recognition, sparse representation is a very efficacious and powerful approach. As classical descriptors of polarimetric SAR, covariance and coherency matrices are Hermitian semidefinite and form a Riemannian manifold. Conventional Euclidean metrics are not suitable for a Riemannian manifold, and hence, normal sparse representation classification cannot be applied to polarimetric SAR directly. This paper proposes a new land cover classification approach for polarimetric SAR. There are two principal novelties in this paper. First, a Stein kernel on a Riemannian manifold instead of Euclidean metrics, combined with sparse representation, is employed for polarimetric SAR land cover classification. This approach is named Stein-sparse representation-based classification (SRC). Second, using simultaneous sparse representation and reasonable assumptions of the correlation of representation among different frequency bands, Stein-SRC is generalized to simultaneous Stein-SRC for multi-frequency polarimetric SAR classification. These classifiers are assessed using polarimetric SAR images from the Airborne Synthetic Aperture Radar (AIRSAR) sensor of the Jet Propulsion Laboratory (JPL) and the Electromagnetics Institute Synthetic Aperture Radar (EMISAR) sensor of the Technical University of Denmark (DTU). Experiments on single-band and multi-band data both show that these approaches acquire more accurate classification results in comparison to many conventional and advanced classifiers.
引用
收藏
页码:8469 / 8488
页数:20
相关论文
共 31 条
[1]  
[Anonymous], ARXIV11101773
[2]  
[Anonymous], P 2 INT WORKSH POLIN
[3]   Log-euclidean metrics for fast and simple calculus on diffusion tensors [J].
Arsigny, Vincent ;
Fillard, Pierre ;
Pennec, Xavier ;
Ayache, Nicholas .
MAGNETIC RESONANCE IN MEDICINE, 2006, 56 (02) :411-421
[4]   Hierarchical Segmentation of Polarimetric SAR Images Using Heterogeneous Clutter Models [J].
Bombrun, Lionel ;
Vasile, Gabriel ;
Gay, Michel ;
Totir, Felix .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (02) :726-737
[5]  
Chen SSB, 2001, SIAM REV, V43, P129, DOI [10.1137/S003614450037906X, 10.1137/S1064827596304010]
[6]   Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices [J].
Cherian, Anoop ;
Sra, Suvrit ;
Banerjee, Arindam ;
Papanikolopoulos, Nikolaos .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (09) :2161-2174
[7]   A test statistic in the complex Wishart distribution and its application to change detection in polarimetric SAR data [J].
Conradsen, K ;
Nielsen, AA ;
Sehou, J ;
Skriver, H .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (01) :4-19
[8]   Segmentation and classification of vegetated areas using polarimetric SAR image data [J].
Dong, Y ;
Milne, AK ;
Forster, BC .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (02) :321-329
[9]   Classification With a Non-Gaussian Model for PolSAR Data [J].
Doulgeris, Anthony P. ;
Anfinsen, Stian Normann ;
Eltoft, Torbjorn .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2008, 46 (10) :2999-3009
[10]   Automated Non-Gaussian Clustering of Polarimetric Synthetic Aperture Radar Images [J].
Doulgeris, Anthony P. ;
Anfinsen, Stian Normann ;
Eltoft, Torbjorn .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (10) :3665-3676