Endmember extraction by L2,0 constrained sparse dictionary selection

Shaohui Mei; Qian Du; Mingyi He; Yihang Wang

doi:10.1109/WHISPERS.2015.8075404

Endmember extraction by L_2,0 constrained sparse dictionary selection

Shaohui Mei, Qian Du, Mingyi He, Yihang Wang

School of Electronics and Information

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Endmembers play an important role in many hyperspectral remote sensing applications, such as classification and Spectral Mixture Unmixing (SMU). In this paper, by considering endmembers as a small subset of pixels in a hyperspectral image, a sparse Linear Mixture Model (sLMM) is constructed to model the mixed pixels. As a result, an L_2,0 based sparse dictionary selection model is proposed for endmember extraction (EE) of hyperspectral images. Moreover, a Simultaneous Orthogonal Matching Pursuit (SOMP) based algorithm is adopted to extract endmembers efficiently. Experimental results on both synthetic and real hyperspectral data demonstrate our proposed EE algorithm outperforms several popular pure-pixel EE algorithms.

Original language	English
Title of host publication	2015 7th Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publication	Evolution in Remote Sensing, WHISPERS 2015
Publisher	IEEE Computer Society
ISBN (Electronic)	9781467390156
DOIs	https://doi.org/10.1109/WHISPERS.2015.8075404
State	Published - 2 Jul 2015
Event	7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015 - Tokyo, Japan Duration: 2 Jun 2015 → 5 Jun 2015

Publication series

Name	Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
Volume	2015-June
ISSN (Print)	2158-6276

Conference

Conference	7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015
Country/Territory	Japan
City	Tokyo
Period	2/06/15 → 5/06/15

Keywords

Endmember Extraction
Simultaneous Orthogonal Matching Pursuit
Sparse Dictionary
Spectral Mixture Unmixing

Access to Document

10.1109/WHISPERS.2015.8075404

Cite this

Mei, S., Du, Q., He, M., & Wang, Y. (2015). Endmember extraction by L_2,0 constrained sparse dictionary selection. In 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015 Article 8075404 (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing; Vol. 2015-June). IEEE Computer Society. https://doi.org/10.1109/WHISPERS.2015.8075404

@inproceedings{6fa6c37c30f7480e89b003e98b1e7093,

title = "Endmember extraction by L2,0 constrained sparse dictionary selection",

abstract = "Endmembers play an important role in many hyperspectral remote sensing applications, such as classification and Spectral Mixture Unmixing (SMU). In this paper, by considering endmembers as a small subset of pixels in a hyperspectral image, a sparse Linear Mixture Model (sLMM) is constructed to model the mixed pixels. As a result, an L2,0 based sparse dictionary selection model is proposed for endmember extraction (EE) of hyperspectral images. Moreover, a Simultaneous Orthogonal Matching Pursuit (SOMP) based algorithm is adopted to extract endmembers efficiently. Experimental results on both synthetic and real hyperspectral data demonstrate our proposed EE algorithm outperforms several popular pure-pixel EE algorithms.",

keywords = "Endmember Extraction, Simultaneous Orthogonal Matching Pursuit, Sparse Dictionary, Spectral Mixture Unmixing",

author = "Shaohui Mei and Qian Du and Mingyi He and Yihang Wang",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015 ; Conference date: 02-06-2015 Through 05-06-2015",

year = "2015",

month = jul,

day = "2",

doi = "10.1109/WHISPERS.2015.8075404",

language = "英语",

series = "Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing",

publisher = "IEEE Computer Society",

booktitle = "2015 7th Workshop on Hyperspectral Image and Signal Processing",

}

Mei, S, Du, Q, He, M & Wang, Y 2015, Endmember extraction by L_2,0 constrained sparse dictionary selection. in 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015., 8075404, Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing, vol. 2015-June, IEEE Computer Society, 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015, Tokyo, Japan, 2/06/15. https://doi.org/10.1109/WHISPERS.2015.8075404

Endmember extraction by L_2,0 constrained sparse dictionary selection. / Mei, Shaohui; Du, Qian; He, Mingyi et al.
2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015. IEEE Computer Society, 2015. 8075404 (Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing; Vol. 2015-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Endmember extraction by L2,0 constrained sparse dictionary selection

AU - Mei, Shaohui

AU - Du, Qian

AU - He, Mingyi

AU - Wang, Yihang

PY - 2015/7/2

Y1 - 2015/7/2

N2 - Endmembers play an important role in many hyperspectral remote sensing applications, such as classification and Spectral Mixture Unmixing (SMU). In this paper, by considering endmembers as a small subset of pixels in a hyperspectral image, a sparse Linear Mixture Model (sLMM) is constructed to model the mixed pixels. As a result, an L2,0 based sparse dictionary selection model is proposed for endmember extraction (EE) of hyperspectral images. Moreover, a Simultaneous Orthogonal Matching Pursuit (SOMP) based algorithm is adopted to extract endmembers efficiently. Experimental results on both synthetic and real hyperspectral data demonstrate our proposed EE algorithm outperforms several popular pure-pixel EE algorithms.

AB - Endmembers play an important role in many hyperspectral remote sensing applications, such as classification and Spectral Mixture Unmixing (SMU). In this paper, by considering endmembers as a small subset of pixels in a hyperspectral image, a sparse Linear Mixture Model (sLMM) is constructed to model the mixed pixels. As a result, an L2,0 based sparse dictionary selection model is proposed for endmember extraction (EE) of hyperspectral images. Moreover, a Simultaneous Orthogonal Matching Pursuit (SOMP) based algorithm is adopted to extract endmembers efficiently. Experimental results on both synthetic and real hyperspectral data demonstrate our proposed EE algorithm outperforms several popular pure-pixel EE algorithms.

KW - Endmember Extraction

KW - Simultaneous Orthogonal Matching Pursuit

KW - Sparse Dictionary

KW - Spectral Mixture Unmixing

UR - http://www.scopus.com/inward/record.url?scp=85039170726&partnerID=8YFLogxK

U2 - 10.1109/WHISPERS.2015.8075404

DO - 10.1109/WHISPERS.2015.8075404

M3 - 会议稿件

AN - SCOPUS:85039170726

T3 - Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing

BT - 2015 7th Workshop on Hyperspectral Image and Signal Processing

PB - IEEE Computer Society

T2 - 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015

Y2 - 2 June 2015 through 5 June 2015

ER -