Neighborhood preserving Nonnegative Matrix Factorization for spectral mixture analysis

Shaohui Mei; Mingyi He; Zhiming Shen; Baassou Belkacem

doi:10.1109/IGARSS.2013.6723348

Neighborhood preserving Nonnegative Matrix Factorization for spectral mixture analysis

Shaohui Mei, Mingyi He, Zhiming Shen, Baassou Belkacem

School of Electronics and Information

Northwestern Polytechnical University Xian

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

7 Scopus citations

Abstract

Nonnegative Matrix Factorization (NMF) has been successfully employed to address the mixed-pixel problem of hyperspectral remote sensing images. However, minimizing the representation error by NMF is not sufficient for SMA since the unmixing results of NMF are not unique. Therefore, in this paper, a neighborhood preserving regularization, which preserves the local structure of the hyperspectral data on a low-dimensional manifold, is proposed to constrain NMF for unique solution in SMA. As a result, a Neighborhood Preserving constrained NMF (NP-NMF) algorithm is proposed for SMA of highly mixed hyperspectral data. Finally, experimental results on AVIRIS data demonstrate the effectiveness of our proposed NP-NMF algorithm for SMA applications.

Original language	English
Title of host publication	2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings
Pages	2573-2576
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2013.6723348
State	Published - 2013
Event	2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Melbourne, VIC, Australia Duration: 21 Jul 2013 → 26 Jul 2013

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference	2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013
Country/Territory	Australia
City	Melbourne, VIC
Period	21/07/13 → 26/07/13

Keywords

hyperspectral images
Nonnegative Matrix Factorization
Spectral Mixture Analysis

Access to Document

10.1109/IGARSS.2013.6723348

Cite this

Mei, S., He, M., Shen, Z., & Belkacem, B. (2013). Neighborhood preserving Nonnegative Matrix Factorization for spectral mixture analysis. In 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings (pp. 2573-2576). Article 6723348 (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.2013.6723348

@inproceedings{22916923f55c41ed82c7d0a869967ef9,

title = "Neighborhood preserving Nonnegative Matrix Factorization for spectral mixture analysis",

abstract = "Nonnegative Matrix Factorization (NMF) has been successfully employed to address the mixed-pixel problem of hyperspectral remote sensing images. However, minimizing the representation error by NMF is not sufficient for SMA since the unmixing results of NMF are not unique. Therefore, in this paper, a neighborhood preserving regularization, which preserves the local structure of the hyperspectral data on a low-dimensional manifold, is proposed to constrain NMF for unique solution in SMA. As a result, a Neighborhood Preserving constrained NMF (NP-NMF) algorithm is proposed for SMA of highly mixed hyperspectral data. Finally, experimental results on AVIRIS data demonstrate the effectiveness of our proposed NP-NMF algorithm for SMA applications.",

keywords = "hyperspectral images, Nonnegative Matrix Factorization, Spectral Mixture Analysis",

author = "Shaohui Mei and Mingyi He and Zhiming Shen and Baassou Belkacem",

year = "2013",

doi = "10.1109/IGARSS.2013.6723348",

language = "英语",

isbn = "9781479911141",

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

pages = "2573--2576",

booktitle = "2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings",

note = "2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 ; Conference date: 21-07-2013 Through 26-07-2013",

}

Mei, S, He, M, Shen, Z & Belkacem, B 2013, Neighborhood preserving Nonnegative Matrix Factorization for spectral mixture analysis. in 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings., 6723348, International Geoscience and Remote Sensing Symposium (IGARSS), pp. 2573-2576, 2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013, Melbourne, VIC, Australia, 21/07/13. https://doi.org/10.1109/IGARSS.2013.6723348

Neighborhood preserving Nonnegative Matrix Factorization for spectral mixture analysis. / Mei, Shaohui; He, Mingyi; Shen, Zhiming et al.
2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings. 2013. p. 2573-2576 6723348 (International Geoscience and Remote Sensing Symposium (IGARSS)).

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

TY - GEN

T1 - Neighborhood preserving Nonnegative Matrix Factorization for spectral mixture analysis

AU - Mei, Shaohui

AU - He, Mingyi

AU - Shen, Zhiming

AU - Belkacem, Baassou

PY - 2013

Y1 - 2013

N2 - Nonnegative Matrix Factorization (NMF) has been successfully employed to address the mixed-pixel problem of hyperspectral remote sensing images. However, minimizing the representation error by NMF is not sufficient for SMA since the unmixing results of NMF are not unique. Therefore, in this paper, a neighborhood preserving regularization, which preserves the local structure of the hyperspectral data on a low-dimensional manifold, is proposed to constrain NMF for unique solution in SMA. As a result, a Neighborhood Preserving constrained NMF (NP-NMF) algorithm is proposed for SMA of highly mixed hyperspectral data. Finally, experimental results on AVIRIS data demonstrate the effectiveness of our proposed NP-NMF algorithm for SMA applications.

AB - Nonnegative Matrix Factorization (NMF) has been successfully employed to address the mixed-pixel problem of hyperspectral remote sensing images. However, minimizing the representation error by NMF is not sufficient for SMA since the unmixing results of NMF are not unique. Therefore, in this paper, a neighborhood preserving regularization, which preserves the local structure of the hyperspectral data on a low-dimensional manifold, is proposed to constrain NMF for unique solution in SMA. As a result, a Neighborhood Preserving constrained NMF (NP-NMF) algorithm is proposed for SMA of highly mixed hyperspectral data. Finally, experimental results on AVIRIS data demonstrate the effectiveness of our proposed NP-NMF algorithm for SMA applications.

KW - hyperspectral images

KW - Nonnegative Matrix Factorization

KW - Spectral Mixture Analysis

UR - http://www.scopus.com/inward/record.url?scp=84894238367&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2013.6723348

DO - 10.1109/IGARSS.2013.6723348

M3 - 会议稿件

AN - SCOPUS:84894238367

SN - 9781479911141

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2573

EP - 2576

BT - 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings

T2 - 2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013

Y2 - 21 July 2013 through 26 July 2013

ER -

Neighborhood preserving Nonnegative Matrix Factorization for spectral mixture analysis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this