Equivalent-Sparse Unmixing Through Spatial and Spectral Constrained Endmember Selection From an Image-Derived Spectral Library

被引:19
作者
Mei, Shaohui [1 ]
Du, Qian [2 ]
He, Mingyi [1 ]
机构
[1] Northwestern Polytech Univ, Sch Elect & Informat, Xian 710129, Peoples R China
[2] Mississippi State Univ, Geosyst Res Inst, Dept Elect & Comp Engn, Starkville, MS 39762 USA
基金
中国国家自然科学基金;
关键词
Hyperspectral image; in-field spectral variation; mixed pixel; sparse unmixing; spectral unmixing; SELF-ORGANIZING MAP; HYPERSPECTRAL IMAGERY; MIXTURE ANALYSIS; EXTRACTION; ALGORITHM; DECOMPOSITION;
D O I
10.1109/JSTARS.2015.2403254
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Spectral variation, which is inevitably present in hyperspectral data due to nonuniformity and inconsistency of illumination, may result in considerable difficulty in spectral unmixing. In this paper, a field endmember library is constructed to accommodate spectral variation by representing each endmember class by a batch of image-derived spectra. In order to perform unmixing by such a field endmember library, a novel spatial and spectral endmember selection (SSES) algorithm is designed to search for a spatial and spectral constrained endmember subset per pixel for abundance estimation (AE). The net effect is to achieve sparse unmixing equivalently, considering the fact that only a few endmembers in the large library have nonzero abundances. Thus, the resulting algorithm is called spatial and spectral constrained sparse unmixing (SSCSU). Experimental results using both synthetic and real hyperspectral images demonstrate that the proposed SSCSU algorithm not only improves the performance of traditional AE algorithms by considering spectral variation, but also outperforms the existing sparse unmixing approaches.
引用
收藏
页码:2665 / 2675
页数:11
相关论文
共 42 条
[11]   Hierarchical Multiple Endmember Spectral Mixture Analysis (MESMA) of hyperspectral imagery for urban environments [J].
Franke, Jonas ;
Roberts, Dar A. ;
Halligan, Kerry ;
Menz, Gunter .
REMOTE SENSING OF ENVIRONMENT, 2009, 113 (08) :1712-1723
[12]   Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery [J].
Heinz, DC ;
Chang, CI .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (03) :529-545
[13]   A New Minimum-Volume Enclosing Algorithm for Endmember Identification and Abundance Estimation in Hyperspectral Data [J].
Hendrix, Eligius M. T. ;
Garcia, Inmaculada ;
Plaza, Javier ;
Martin, Gabriel ;
Plaza, Antonio .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2012, 50 (07) :2744-2757
[14]   Minimum Dispersion Constrained Nonnegative Matrix Factorization to Unmix Hyperspectral Data [J].
Huck, Alexis ;
Guillaume, Mireille ;
Blanc-Talon, Jacques .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2010, 48 (06) :2590-2602
[15]   Sparse Unmixing of Hyperspectral Data [J].
Iordache, Marian-Daniel ;
Bioucas-Dias, Jose M. ;
Plaza, Antonio .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (06) :2014-2039
[16]   Collaborative Sparse Regression for Hyperspectral Unmixing [J].
Iordache, Marian-Daniel ;
Bioucas-Dias, Jose M. ;
Plaza, Antonio .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (01) :341-354
[17]   Total Variation Spatial Regularization for Sparse Hyperspectral Unmixing [J].
Iordache, Marian-Daniel ;
Bioucas-Dias, Jose M. ;
Plaza, Antonio .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2012, 50 (11) :4484-4502
[18]   Spectral unmixing [J].
Keshava, N ;
Mustard, JF .
IEEE SIGNAL PROCESSING MAGAZINE, 2002, 19 (01) :44-57
[19]  
KITAMOTO A, 1995, INT GEOSCI REMOTE SE, P121, DOI 10.1109/IGARSS.1995.519666
[20]   Decomposition of mixed pixels based on bayesian self-organizing map and Gaussian mixture model [J].
Liu, Lifan ;
Wang, Bin ;
Zhang, Liming .
PATTERN RECOGNITION LETTERS, 2009, 30 (09) :820-826