Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation

Xin Ru Feng; Heng Chao Li; Rui Wang

doi:10.1109/IGARSS.2019.8898680

Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation

Xin Ru Feng, Heng Chao Li, Rui Wang

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

3 Scopus citations

Abstract

Hyperspectral unmixing is a critical processing step for many remote sensing applications. Nonnegative matrix factorization (NMF) has drawn extensive attention in hyperspectral image analysis recently. Considering that the abundance matrix is generally sparse and smooth, we propose a sparsity-constrained NMF with adaptive total variation (SNMF-ATV) algorithm for hyperspectral unmixing. Specifically, the ATV could promote the smoothness of the estimated abundances while avoid the staircase effect caused by TV model. The comparison with other unmixing methods on both synthetic and real data sets demonstrates the effectiveness and superiority of the proposed SNMF-ATV algorithm with regard to the other considered methods.

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	2139-2142
Number of pages	4
ISBN (Electronic)	9781538691540
DOIs	https://doi.org/10.1109/IGARSS.2019.8898680
State	Published - Jul 2019
Externally published	Yes
Event	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan Duration: Jul 28 2019 → Aug 2 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	07/28/19 → 08/2/19

Keywords

Hyperspectral unmixing
adaptive total variation
nonnegative matrix factorization

Access to Document

10.1109/IGARSS.2019.8898680

Cite this

Feng, X. R., Li, H. C., & Wang, R. (2019). Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings (pp. 2139-2142). Article 8898680 (International Geoscience and Remote Sensing Symposium (IGARSS)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2019.8898680

Feng, Xin Ru ; Li, Heng Chao ; Wang, Rui. / Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation. 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 2139-2142 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{7011515ad969409f8f97b1d96a11937e,

title = "Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation",

abstract = "Hyperspectral unmixing is a critical processing step for many remote sensing applications. Nonnegative matrix factorization (NMF) has drawn extensive attention in hyperspectral image analysis recently. Considering that the abundance matrix is generally sparse and smooth, we propose a sparsity-constrained NMF with adaptive total variation (SNMF-ATV) algorithm for hyperspectral unmixing. Specifically, the ATV could promote the smoothness of the estimated abundances while avoid the staircase effect caused by TV model. The comparison with other unmixing methods on both synthetic and real data sets demonstrates the effectiveness and superiority of the proposed SNMF-ATV algorithm with regard to the other considered methods.",

keywords = "Hyperspectral unmixing, adaptive total variation, nonnegative matrix factorization",

author = "Feng, {Xin Ru} and Li, {Heng Chao} and Rui Wang",

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.2019.8898680",

language = "English",

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

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

pages = "2139--2142",

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

}

Feng, XR, Li, HC & Wang, R 2019, Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation. in 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings., 8898680, International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., pp. 2139-2142, 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 07/28/19. https://doi.org/10.1109/IGARSS.2019.8898680

Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation. / Feng, Xin Ru; Li, Heng Chao; Wang, Rui.
2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2139-2142 8898680 (International Geoscience and Remote Sensing Symposium (IGARSS)).

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

TY - GEN

T1 - Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation

AU - Feng, Xin Ru

AU - Li, Heng Chao

AU - Wang, Rui

PY - 2019/7

Y1 - 2019/7

N2 - Hyperspectral unmixing is a critical processing step for many remote sensing applications. Nonnegative matrix factorization (NMF) has drawn extensive attention in hyperspectral image analysis recently. Considering that the abundance matrix is generally sparse and smooth, we propose a sparsity-constrained NMF with adaptive total variation (SNMF-ATV) algorithm for hyperspectral unmixing. Specifically, the ATV could promote the smoothness of the estimated abundances while avoid the staircase effect caused by TV model. The comparison with other unmixing methods on both synthetic and real data sets demonstrates the effectiveness and superiority of the proposed SNMF-ATV algorithm with regard to the other considered methods.

AB - Hyperspectral unmixing is a critical processing step for many remote sensing applications. Nonnegative matrix factorization (NMF) has drawn extensive attention in hyperspectral image analysis recently. Considering that the abundance matrix is generally sparse and smooth, we propose a sparsity-constrained NMF with adaptive total variation (SNMF-ATV) algorithm for hyperspectral unmixing. Specifically, the ATV could promote the smoothness of the estimated abundances while avoid the staircase effect caused by TV model. The comparison with other unmixing methods on both synthetic and real data sets demonstrates the effectiveness and superiority of the proposed SNMF-ATV algorithm with regard to the other considered methods.

KW - Hyperspectral unmixing

KW - adaptive total variation

KW - nonnegative matrix factorization

UR - http://www.scopus.com/inward/record.url?scp=85077674087&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2019.8898680

DO - 10.1109/IGARSS.2019.8898680

M3 - Conference contribution

AN - SCOPUS:85077674087

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2139

EP - 2142

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 -

Feng XR, Li HC, Wang R. Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2139-2142. 8898680. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2019.8898680

Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this