Nonlinear Estimation of Material Abundances in Hyperspectral Images With l1-Norm Spatial Regularization

被引:69
作者
Chen, Jie [1 ]
Richard, Cedric [1 ]
Honeine, Paul [2 ]
机构
[1] Univ Nice Sophia Antipolis, CNRS, Observ Cote Azur, F-06108 Nice, France
[2] Univ Technol Troyes, CNRS, Inst Charles Delaunay, F-10010 Troyes, France
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2014年 / 52卷 / 05期
关键词
Hyperspectral imaging; l(1)-norm regularization; nonlinear spectral unmixing; spatial regularization; SPECTRAL MIXTURE ANALYSIS; SIGNAL-DEPENDENT NOISE; CLASSIFICATION; EXTRACTION; ALGORITHM;
D O I
10.1109/TGRS.2013.2264392
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Integrating spatial information into hyperspectral unmixing procedures has been shown to have a positive effect on the estimation of fractional abundances due to the inherent spatial-spectral duality in hyperspectral scenes. However, current research works that take spatial information into account are mainly focused on the linear mixing model. In this paper, we investigate how to incorporate spatial correlation into a nonlinear abundance estimation process. A nonlinear unmixing algorithm operating in reproducing kernel Hilbert spaces, coupled with a l(1)-type spatial regularization, is derived. Experiment results, with both synthetic and real hyperspectral images, illustrate the effectiveness of the proposed scheme.
引用
收藏
页码:2654 / 2665
页数:12
相关论文
共 44 条
[31]   Spectral-Spatial Hyperspectral Image Segmentation Using Subspace Multinomial Logistic Regression and Markov Random Fields [J].
Li, Jun ;
Bioucas-Dias, Jose M. ;
Plaza, Antonio .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2012, 50 (03) :809-823
[32]   Region-Based Spatial Preprocessing for Endmember Extraction and Spectral Unmixing [J].
Martin, Gabriel ;
Plaza, Antonio .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2011, 8 (04) :745-749
[33]   Modeling and estimation of signal-dependent noise in hyperspectral imagery [J].
Meola, Joseph ;
Eismann, Michael T. ;
Moses, Randolph L. ;
Ash, Joshua N. .
APPLIED OPTICS, 2011, 50 (21) :3829-3846
[34]   An introduction to kernel-based learning algorithms [J].
Müller, KR ;
Mika, S ;
Rätsch, G ;
Tsuda, K ;
Schölkopf, B .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (02) :181-201
[35]   HYPERSPECTRAL IMAGE UNMIXING USING MANIFOLD LEARNING METHODS DERIVATIONS AND COMPARATIVE TESTS [J].
Nguyen Hoang Nguyen ;
Richard, Cedric ;
Honeine, Paul ;
Theys, Celine .
2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2012, :3086-3089
[36]  
Plaza A, 2011, AUGMENT VIS REAL, V3, P235, DOI 10.1007/978-3-642-14212-3_12
[37]   Recent advances in techniques for hyperspectral image processing [J].
Plaza, Antonio ;
Benediktsson, Jon Atli ;
Boardman, Joseph W. ;
Brazile, Jason ;
Bruzzone, Lorenzo ;
Camps-Valls, Gustavo ;
Chanussot, Jocelyn ;
Fauvel, Mathieu ;
Gamba, Paolo ;
Gualtieri, Anthony ;
Marconcini, Mattia ;
Tilton, James C. ;
Trianni, Giovanna .
REMOTE SENSING OF ENVIRONMENT, 2009, 113 :S110-S122
[38]   Nonlinear Spectral Mixture Analysis for Hyperspectral Imagery in an Unknown Environment [J].
Raksuntorn, Nareenart ;
Du, Qian .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2010, 7 (04) :836-840
[39]   Integration of spatial-spectral information for the improved extraction of endmembers [J].
Rogge, D. M. ;
Rivard, B. ;
Zhang, J. ;
Sanchez, A. ;
Harris, J. ;
Feng, J. .
REMOTE SENSING OF ENVIRONMENT, 2007, 110 (03) :287-303