Endmember Constraint Non-Negative Tensor Factorization Via Total Variation for Hyperspectral Unmixing

Hyperspectral unmixing (HU), estimating endmembers and the corresponding abundances, is crucial for the development of hyperspectral images (HSIs). To improve the unmixing performance, various spatial regularizers are imposed on the abundance matrix. Note that endmember information is also important...

Full description

Saved in:
Bibliographic Details
Published in2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS pp. 3313 - 3316
Main Authors Wang, Jin-Ju, Wang, Ding-Cheng, Huang, Ting-Zhu, Huang, Jie
Format Conference Proceeding
LanguageEnglish
Published IEEE 11.07.2021
Subjects
Correlation
endmember constraint
Geoscience and remote sensing
Hyperspectral imaging
Hyperspectral unmixing
non-negative tensor factorization
Roads
Soil
Tensors
Online AccessGet full text

Cover

More Information
Summary:Hyperspectral unmixing (HU), estimating endmembers and the corresponding abundances, is crucial for the development of hyperspectral images (HSIs). To improve the unmixing performance, various spatial regularizers are imposed on the abundance matrix. Note that endmember information is also important for HU, especially when the spectral signature in HSIs are highly correlated. In this paper, we investigate information from both endmembers and abundances and propose an endmember constraint non-negative tensor factorization via total variation (EC-NTF-TV) for HU. For estimating end-members, we introduce an endmember constraint to alleviate the spectral signatures' high correlation. In addition, we adopt the TV regularization to exploit the spatial correlation in abundance maps. Finally, we solve the proposed model under the augmented multiplicative update framework. Both synthetic and real hyperspectral data experiments demonstrate the effectiveness of the proposed algorithm.
ISSN:2153-7003
DOI:10.1109/IGARSS47720.2021.9554468