Sparse Spectral Unmixing of Hyperspectral Images using Expectation-Propagation

Zeng Li; Yoann Altmann; Jie Chen; Stephen McLaughlin; Susanto Rahardja

doi:10.1109/VCIP49819.2020.9301819

Sparse Spectral Unmixing of Hyperspectral Images using Expectation-Propagation

Zeng Li, Yoann Altmann, Jie Chen, Stephen McLaughlin, Susanto Rahardja

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

1 Citation (Scopus)

Abstract

The aim of spectral unmixing of hyperspectral images is to determine the component materials and their associated abundances from mixed pixels. In this paper, we present sparse linear unmixing via an Expectation-Propagation method based on the classical linear mixing model and a spike-and-slab prior promoting abundance sparsity. The proposed method, which allows approximate uncertainty quantification (UQ), is compared to existing sparse unmixing methods, including Monte Carlo strategies traditionally considered for UQ. Experimental results on synthetic data and real hyperspectral data illustrate the benefits of the proposed algorithm over state-of-art linear unmixing methods.

Original language	English
Title of host publication	2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020
Publisher	IEEE
Pages	197-200
Number of pages	4
ISBN (Electronic)	978-1-7281-8067-0, 978-1-7281-8068-7
DOIs	https://doi.org/10.1109/VCIP49819.2020.9301819
Publication status	Published - 29 Dec 2020
Event	2020 IEEE International Conference on Visual Communications and Image Processing - Virtual, Macau, China Duration: 1 Dec 2020 → 4 Dec 2020

Conference

Conference	2020 IEEE International Conference on Visual Communications and Image Processing
Abbreviated title	VCIP 2020
Country/Territory	China
City	Virtual, Macau
Period	1/12/20 → 4/12/20

Keywords

Approximate Bayesian method
Expectation-Propagation
Spectral unmixing

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Media Technology

Access to Document

10.1109/VCIP49819.2020.9301819

Cite this

@inproceedings{403ecd05564647b58bd067cad91f74dd,

title = "Sparse Spectral Unmixing of Hyperspectral Images using Expectation-Propagation",

abstract = "The aim of spectral unmixing of hyperspectral images is to determine the component materials and their associated abundances from mixed pixels. In this paper, we present sparse linear unmixing via an Expectation-Propagation method based on the classical linear mixing model and a spike-and-slab prior promoting abundance sparsity. The proposed method, which allows approximate uncertainty quantification (UQ), is compared to existing sparse unmixing methods, including Monte Carlo strategies traditionally considered for UQ. Experimental results on synthetic data and real hyperspectral data illustrate the benefits of the proposed algorithm over state-of-art linear unmixing methods.",

keywords = "Approximate Bayesian method, Expectation-Propagation, Spectral unmixing",

author = "Zeng Li and Yoann Altmann and Jie Chen and Stephen McLaughlin and Susanto Rahardja",

note = "Funding Information: Y.A. is supported by the Royal Academy of Engineering under the Research Fellowship scheme RF201617/16/31. Z.L. is supported by the China Scholarship Council. J.C. is supported by 111 project B18041. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020 ; Conference date: 01-12-2020 Through 04-12-2020",

year = "2020",

month = dec,

day = "29",

doi = "10.1109/VCIP49819.2020.9301819",

language = "English",

pages = "197--200",

booktitle = "2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020",

publisher = "IEEE",

address = "United States",

}

Li, Z, Altmann, Y, Chen, J, McLaughlin, S & Rahardja, S 2020, Sparse Spectral Unmixing of Hyperspectral Images using Expectation-Propagation. in 2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020., 9301819, IEEE, pp. 197-200, 2020 IEEE International Conference on Visual Communications and Image Processing, Virtual, Macau, China, 1/12/20. https://doi.org/10.1109/VCIP49819.2020.9301819

TY - GEN

T1 - Sparse Spectral Unmixing of Hyperspectral Images using Expectation-Propagation

AU - Li, Zeng

AU - Altmann, Yoann

AU - Chen, Jie

AU - McLaughlin, Stephen

AU - Rahardja, Susanto

N1 - Funding Information: Y.A. is supported by the Royal Academy of Engineering under the Research Fellowship scheme RF201617/16/31. Z.L. is supported by the China Scholarship Council. J.C. is supported by 111 project B18041. Publisher Copyright: © 2020 IEEE.

PY - 2020/12/29

Y1 - 2020/12/29

N2 - The aim of spectral unmixing of hyperspectral images is to determine the component materials and their associated abundances from mixed pixels. In this paper, we present sparse linear unmixing via an Expectation-Propagation method based on the classical linear mixing model and a spike-and-slab prior promoting abundance sparsity. The proposed method, which allows approximate uncertainty quantification (UQ), is compared to existing sparse unmixing methods, including Monte Carlo strategies traditionally considered for UQ. Experimental results on synthetic data and real hyperspectral data illustrate the benefits of the proposed algorithm over state-of-art linear unmixing methods.

AB - The aim of spectral unmixing of hyperspectral images is to determine the component materials and their associated abundances from mixed pixels. In this paper, we present sparse linear unmixing via an Expectation-Propagation method based on the classical linear mixing model and a spike-and-slab prior promoting abundance sparsity. The proposed method, which allows approximate uncertainty quantification (UQ), is compared to existing sparse unmixing methods, including Monte Carlo strategies traditionally considered for UQ. Experimental results on synthetic data and real hyperspectral data illustrate the benefits of the proposed algorithm over state-of-art linear unmixing methods.

KW - Approximate Bayesian method

KW - Expectation-Propagation

KW - Spectral unmixing

UR - http://www.scopus.com/inward/record.url?scp=85099433248&partnerID=8YFLogxK

U2 - 10.1109/VCIP49819.2020.9301819

DO - 10.1109/VCIP49819.2020.9301819

M3 - Conference contribution

AN - SCOPUS:85099433248

SP - 197

EP - 200

BT - 2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020

PB - IEEE

T2 - 2020 IEEE International Conference on Visual Communications and Image Processing

Y2 - 1 December 2020 through 4 December 2020

ER -

Sparse Spectral Unmixing of Hyperspectral Images using Expectation-Propagation

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this