An Optimization Method for Hyperspectral Endmember Extraction Based on K-SVD

被引：1

作者：

Feng, Xiaoxiao ^{[1
]}

He, Luxiao ^{[1
]}

Zhang, Ya ^{[1
]}

Tang, Yun ^{[2
]}

机构：

[1] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, 129 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China

[2] Wuhan Univ, Sch Remote Sensing & Informat Engn, 129 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China

来源：

PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING | 2019年 / 85卷 / 12期

基金：

中国国家自然科学基金;

关键词：

NONNEGATIVE MATRIX FACTORIZATION; COMPONENT ANALYSIS; ALGORITHM;

D O I：

10.14358/PERS.85.12.879

中图分类号：

P9 [自然地理学];

学科分类号：

0705 ; 070501 ;

摘要：

Mixed pixels are common in hyperspectral imagery (HSI). Due to the complexity of the ground object distribution, some endmember extraction methods cannot obtain good results and the processes are complex. Therefore, this paper proposes an optimization method for HSI endmember extraction, which improves the accuracy of the results based on K-singular value decomposition (K-SVD). The proposed method comprises three core steps. (1) Based on the contribution value of initial endmembers, partially observed data selected according to the appropriate confidence participate in the calculation. (2) Construction of the error model to eliminate the background noise. (3) Using the K-SVD to perform column-by-column iteration on the endmembers to achieve the overall optimality. Experiments with three real images are applied, demonstrating the proposed method can improve the overall endmember accuracy by 15.1%-55.7% compared with the original methods.

引用

页码：879 / 887

页数：9

共 25 条

[1] The importance of scale in object-based mapping of vegetation parameters with hyperspectral imagery [J].

Addink, Elisabeth A. ;

de Jong, Steven M. ;

Pebesma, Edzer J. .

PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2007, 73 (08) :905-912

[2] K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation [J].

Aharon, Michal ;

Elad, Michael ;

Bruckstein, Alfred .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2006, 54 (11) :4311-4322

[3] For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution [J].

Donoho, DL .

COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS, 2006, 59 (06) :797-829

[4]

Hong DF, 2017, IEEE IMAGE PROC, P235, DOI 10.1109/ICIP.2017.8296278

[5] Spectral unmixing [J].

Keshava, N ;

Mustard, JF .

IEEE SIGNAL PROCESSING MAGAZINE, 2002, 19 (01) :44-57

[6]

Li H, 2017, IEEE C EVOL COMPUTAT, P458, DOI 10.1109/CEC.2017.7969347

[7]

Li J., 2008, P IEEE INT GEOSC REM, P250, DOI DOI 10.1109/IGARSS.2008.4779330

[8] An Approach Based on Constrained Nonnegative Matrix Factorization to Unmix Hyperspectral Data [J].

Liu, Xuesong ;

Xia, Wei ;

Wang, Bin ;

Zhang, Liming .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (02) :757-772

[9] Sparse Dictionary Learning for Blind Hyperspectral Unmixing [J].

Liu, Yang ;

Guo, Yi ;

Li, Feng ;

Xin, Lei ;

Huang, Puming .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2019, 16 (04) :578-582

[10] Double Constrained NMF for Hyperspectral Unmixing [J].

Lu, Xiaoqiang ;

Wu, Hao ;

Yuan, Yuan .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (05) :2746-2758

← 1 2 3 →