Double reweighted sparse regression for hyperspectral unmixing

Rui Wang, Hengchao Li, Wenzhi Liao, Aleksandra Pizurica, Ji WU, Yaqiu JIN, Jiancheng SHI

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

Spectral unmixing is an important technology in hyperspectral image applications. Recently, sparse regression is widely used in hyperspectral unmixing. This paper proposes a double reweighted sparse regression method for hyperspectral unmixing. The proposed method enhances the sparsity of abundance fraction in both spectral and spatial domains through double weights, in which one is used to enhance the sparsity of endmembers in the spectral library, and the other to improve the sparseness of abundance fraction of every material. Experimental results on both synthetic and real hyperspectral data sets demonstrate effectiveness of the proposed method both visually and quantitatively.

Conference

Conference2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Abbreviated titleIGARSS 2016
CountryChina
CityBeijing
Period10/07/1615/07/16

Fingerprint

regression analysis

Keywords

  • hyperspectral unmixing
  • double weights
  • sparse regression
  • geophysical image processing
  • hyperspectral imaging

Cite this

Wang, R., Li, H., Liao, W., Pizurica, A., WU, J., JIN, Y., & SHI, J. (2016). Double reweighted sparse regression for hyperspectral unmixing. 6986-6989. Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China. https://doi.org/10.1109/IGARSS.2016.7730822
Wang, Rui ; Li, Hengchao ; Liao, Wenzhi ; Pizurica, Aleksandra ; WU, Ji ; JIN, Yaqiu ; SHI, Jiancheng. / Double reweighted sparse regression for hyperspectral unmixing. Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.4 p.
@conference{172ce83cf1a74242b8287253ce6414b3,
title = "Double reweighted sparse regression for hyperspectral unmixing",
abstract = "Spectral unmixing is an important technology in hyperspectral image applications. Recently, sparse regression is widely used in hyperspectral unmixing. This paper proposes a double reweighted sparse regression method for hyperspectral unmixing. The proposed method enhances the sparsity of abundance fraction in both spectral and spatial domains through double weights, in which one is used to enhance the sparsity of endmembers in the spectral library, and the other to improve the sparseness of abundance fraction of every material. Experimental results on both synthetic and real hyperspectral data sets demonstrate effectiveness of the proposed method both visually and quantitatively.",
keywords = "hyperspectral unmixing, double weights, sparse regression, geophysical image processing, hyperspectral imaging",
author = "Rui Wang and Hengchao Li and Wenzhi Liao and Aleksandra Pizurica and Ji WU and Yaqiu JIN and Jiancheng SHI",
year = "2016",
month = "11",
day = "3",
doi = "10.1109/IGARSS.2016.7730822",
language = "English",
pages = "6986--6989",
note = "2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IGARSS 2016 ; Conference date: 10-07-2016 Through 15-07-2016",

}

Wang, R, Li, H, Liao, W, Pizurica, A, WU, J, JIN, Y & SHI, J 2016, 'Double reweighted sparse regression for hyperspectral unmixing' Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China, 10/07/16 - 15/07/16, pp. 6986-6989. https://doi.org/10.1109/IGARSS.2016.7730822

Double reweighted sparse regression for hyperspectral unmixing. / Wang, Rui; Li, Hengchao; Liao, Wenzhi; Pizurica, Aleksandra; WU, Ji; JIN, Yaqiu; SHI, Jiancheng.

2016. 6986-6989 Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Double reweighted sparse regression for hyperspectral unmixing

AU - Wang, Rui

AU - Li, Hengchao

AU - Liao, Wenzhi

AU - Pizurica, Aleksandra

AU - WU, Ji

AU - JIN, Yaqiu

AU - SHI, Jiancheng

PY - 2016/11/3

Y1 - 2016/11/3

N2 - Spectral unmixing is an important technology in hyperspectral image applications. Recently, sparse regression is widely used in hyperspectral unmixing. This paper proposes a double reweighted sparse regression method for hyperspectral unmixing. The proposed method enhances the sparsity of abundance fraction in both spectral and spatial domains through double weights, in which one is used to enhance the sparsity of endmembers in the spectral library, and the other to improve the sparseness of abundance fraction of every material. Experimental results on both synthetic and real hyperspectral data sets demonstrate effectiveness of the proposed method both visually and quantitatively.

AB - Spectral unmixing is an important technology in hyperspectral image applications. Recently, sparse regression is widely used in hyperspectral unmixing. This paper proposes a double reweighted sparse regression method for hyperspectral unmixing. The proposed method enhances the sparsity of abundance fraction in both spectral and spatial domains through double weights, in which one is used to enhance the sparsity of endmembers in the spectral library, and the other to improve the sparseness of abundance fraction of every material. Experimental results on both synthetic and real hyperspectral data sets demonstrate effectiveness of the proposed method both visually and quantitatively.

KW - hyperspectral unmixing

KW - double weights

KW - sparse regression

KW - geophysical image processing

KW - hyperspectral imaging

UR - http://hdl.handle.net/1854/LU-7181939

U2 - 10.1109/IGARSS.2016.7730822

DO - 10.1109/IGARSS.2016.7730822

M3 - Paper

SP - 6986

EP - 6989

ER -

Wang R, Li H, Liao W, Pizurica A, WU J, JIN Y et al. Double reweighted sparse regression for hyperspectral unmixing. 2016. Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China. https://doi.org/10.1109/IGARSS.2016.7730822