File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Using Low-Rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing

TitleUsing Low-Rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing
Authors
KeywordsHyperspectral image (HSI)
Low rank
Nonlinear unmixing
Tensor decomposition
Issue Date2021
Citation
IEEE Transactions on Geoscience and Remote Sensing, 2021 How to Cite?
AbstractTensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-order tensor, which can perfectly retain the spatial information in the image. In this article, we extend the linear tensor method to the nonlinear tensor method and propose a nonlinear low-rank tensor unmixing algorithm to solve the generalized bilinear model (GBM). Specifically, the linear and nonlinear parts of the GBM can both be expressed as tensors. Furthermore, the low-rank structures of abundance maps and nonlinear interaction abundance maps are exploited by minimizing their nuclear norm, thus taking full advantage of the high spatial correlation in HSIs. Synthetic and real-data experiments show that the low rank of abundance maps and nonlinear interaction abundance maps exploited in our method can improve the performance of the nonlinear unmixing. A MATLAB demo of this work will be available at https://github.com/LinaZhuang for the sake of reproducibility.
Persistent Identifierhttp://hdl.handle.net/10722/298385
ISSN
2020 Impact Factor: 5.6
2020 SCImago Journal Rankings: 2.141

 

DC FieldValueLanguage
dc.contributor.authorGao, Lianru-
dc.contributor.authorWang, Zhicheng-
dc.contributor.authorZhuang, Lina-
dc.contributor.authorYu, Haoyang-
dc.contributor.authorZhang, Bing-
dc.contributor.authorChanussot, Jocelyn-
dc.date.accessioned2021-04-08T03:08:18Z-
dc.date.available2021-04-08T03:08:18Z-
dc.date.issued2021-
dc.identifier.citationIEEE Transactions on Geoscience and Remote Sensing, 2021-
dc.identifier.issn0196-2892-
dc.identifier.urihttp://hdl.handle.net/10722/298385-
dc.description.abstractTensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-order tensor, which can perfectly retain the spatial information in the image. In this article, we extend the linear tensor method to the nonlinear tensor method and propose a nonlinear low-rank tensor unmixing algorithm to solve the generalized bilinear model (GBM). Specifically, the linear and nonlinear parts of the GBM can both be expressed as tensors. Furthermore, the low-rank structures of abundance maps and nonlinear interaction abundance maps are exploited by minimizing their nuclear norm, thus taking full advantage of the high spatial correlation in HSIs. Synthetic and real-data experiments show that the low rank of abundance maps and nonlinear interaction abundance maps exploited in our method can improve the performance of the nonlinear unmixing. A MATLAB demo of this work will be available at https://github.com/LinaZhuang for the sake of reproducibility.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Geoscience and Remote Sensing-
dc.subjectHyperspectral image (HSI)-
dc.subjectLow rank-
dc.subjectNonlinear unmixing-
dc.subjectTensor decomposition-
dc.titleUsing Low-Rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TGRS.2021.3065990-
dc.identifier.scopuseid_2-s2.0-85103247834-
dc.identifier.eissn1558-0644-
dc.identifier.issnl0196-2892-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats