Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF

Zihan Zhang; Qi Wang; Yuan Yuan

doi:10.1109/IGARSS.2019.8898427

Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF

Zihan Zhang, Qi Wang, Yuan Yuan

School of Artificial Intelligence, OPtics and Electronics

Northwestern Polytechnical University Xian

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

7 Scopus citations

Abstract

Hyperspectral unmixing, by extracting the fractional abundances of endmembers from the hyperspectral image (HSI), has raised wide attention in recent years. In last decade, nonnegative matrix factorization (NMF) have been intensively studied for solving spectral unmixing problem. In this paper, we extend the multilayer NMF method by incorporating the L_1/4 sparsity constraint, named L_1/4-MLNMF. The L_1/4 regularizer induces sparsity effectively. We propose an iterative estimation algorithm for L_1/4-MLNMF, which provides sparser and more accurate results than MLNMF. Experiments on a synthetic dataset and a real dataset show that the prposed method outperforms the similar competitors.

Original language	English
Title of host publication	2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2143-2146
Number of pages	4
ISBN (Electronic)	9781538691540
DOIs	https://doi.org/10.1109/IGARSS.2019.8898427
State	Published - Jul 2019
Event	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan Duration: 28 Jul 2019 → 2 Aug 2019

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Country/Territory	Japan
City	Yokohama
Period	28/07/19 → 2/08/19

Keywords

hyperspectral image
Hyperspectral unmixing
nonnegative matrix factorization

Access to Document

10.1109/IGARSS.2019.8898427

Cite this

Zhang, Z., Wang, Q., & Yuan, Y. (2019). Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings (pp. 2143-2146). Article 8898427 (International Geoscience and Remote Sensing Symposium (IGARSS)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2019.8898427

@inproceedings{567f8804fed5437cabb0b0991062c0cd,

title = "Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF",

abstract = "Hyperspectral unmixing, by extracting the fractional abundances of endmembers from the hyperspectral image (HSI), has raised wide attention in recent years. In last decade, nonnegative matrix factorization (NMF) have been intensively studied for solving spectral unmixing problem. In this paper, we extend the multilayer NMF method by incorporating the L1/4 sparsity constraint, named L1/4-MLNMF. The L1/4 regularizer induces sparsity effectively. We propose an iterative estimation algorithm for L1/4-MLNMF, which provides sparser and more accurate results than MLNMF. Experiments on a synthetic dataset and a real dataset show that the prposed method outperforms the similar competitors.",

keywords = "hyperspectral image, Hyperspectral unmixing, nonnegative matrix factorization",

author = "Zihan Zhang and Qi Wang and Yuan Yuan",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2019",

month = jul,

doi = "10.1109/IGARSS.2019.8898427",

language = "英语",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2143--2146",

booktitle = "2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings",

}

Zhang, Z, Wang, Q & Yuan, Y 2019, Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF. in 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings., 8898427, International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., pp. 2143-2146, 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 28/07/19. https://doi.org/10.1109/IGARSS.2019.8898427

Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF. / Zhang, Zihan; Wang, Qi ; Yuan, Yuan.
2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2143-2146 8898427 (International Geoscience and Remote Sensing Symposium (IGARSS)).

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

TY - GEN

T1 - Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF

AU - Zhang, Zihan

AU - Wang, Qi

AU - Yuan, Yuan

PY - 2019/7

Y1 - 2019/7

N2 - Hyperspectral unmixing, by extracting the fractional abundances of endmembers from the hyperspectral image (HSI), has raised wide attention in recent years. In last decade, nonnegative matrix factorization (NMF) have been intensively studied for solving spectral unmixing problem. In this paper, we extend the multilayer NMF method by incorporating the L1/4 sparsity constraint, named L1/4-MLNMF. The L1/4 regularizer induces sparsity effectively. We propose an iterative estimation algorithm for L1/4-MLNMF, which provides sparser and more accurate results than MLNMF. Experiments on a synthetic dataset and a real dataset show that the prposed method outperforms the similar competitors.

AB - Hyperspectral unmixing, by extracting the fractional abundances of endmembers from the hyperspectral image (HSI), has raised wide attention in recent years. In last decade, nonnegative matrix factorization (NMF) have been intensively studied for solving spectral unmixing problem. In this paper, we extend the multilayer NMF method by incorporating the L1/4 sparsity constraint, named L1/4-MLNMF. The L1/4 regularizer induces sparsity effectively. We propose an iterative estimation algorithm for L1/4-MLNMF, which provides sparser and more accurate results than MLNMF. Experiments on a synthetic dataset and a real dataset show that the prposed method outperforms the similar competitors.

KW - hyperspectral image

KW - Hyperspectral unmixing

KW - nonnegative matrix factorization

UR - http://www.scopus.com/inward/record.url?scp=85077718376&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2019.8898427

DO - 10.1109/IGARSS.2019.8898427

M3 - 会议稿件

AN - SCOPUS:85077718376

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2143

EP - 2146

BT - 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Zhang Z, Wang Q , Yuan Y. Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2143-2146. 8898427. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2019.8898427

Hyperspectral Unmixing VIA L1/4 Sparsity-Constrained Multilayer NMF

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this