File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Fast Hyperspectral image Denoising based on low rank and sparse representations

TitleFast Hyperspectral image Denoising based on low rank and sparse representations
Authors
Keywordssparse representation
Denoising
signal subspace
BM4D
hyperspectral image
low rank structure
BM3D
non-local patch(cube)
Issue Date2016
Citation
International Geoscience and Remote Sensing Symposium (IGARSS), 2016, v. 2016-November, p. 1847-1850 How to Cite?
AbstractThe very high spectral resolution of Hyperspectral Images (HSIs) enables the identification of materials with subtle differences and the extraction subpixel information. However, the increasing of spectral resolution often implies an increasing in the noise linked with the image formation process. This degradation mechanism limits the quality of extracted information and its potential applications. This paper presents a new HSI denoising approach developed under the assumption that the clean HSI is low-rank and self-similar. Under these assumptions, the clean HSI admits extremely compact and sparse representations, which are exploited to derive a very fast and competitive denoising algorithm, named Fast Hyperspectral Denoising (FastHyDe), able to cope with Gaussian and Poissonian noise. In a series of experiments, the proposed approach competes with state-of-the-art methods, with much lower computational complexity.
Persistent Identifierhttp://hdl.handle.net/10722/298192

 

DC FieldValueLanguage
dc.contributor.authorZhuang, Lina-
dc.contributor.authorBioucas-Dias, Jose M.-
dc.date.accessioned2021-04-08T03:07:52Z-
dc.date.available2021-04-08T03:07:52Z-
dc.date.issued2016-
dc.identifier.citationInternational Geoscience and Remote Sensing Symposium (IGARSS), 2016, v. 2016-November, p. 1847-1850-
dc.identifier.urihttp://hdl.handle.net/10722/298192-
dc.description.abstractThe very high spectral resolution of Hyperspectral Images (HSIs) enables the identification of materials with subtle differences and the extraction subpixel information. However, the increasing of spectral resolution often implies an increasing in the noise linked with the image formation process. This degradation mechanism limits the quality of extracted information and its potential applications. This paper presents a new HSI denoising approach developed under the assumption that the clean HSI is low-rank and self-similar. Under these assumptions, the clean HSI admits extremely compact and sparse representations, which are exploited to derive a very fast and competitive denoising algorithm, named Fast Hyperspectral Denoising (FastHyDe), able to cope with Gaussian and Poissonian noise. In a series of experiments, the proposed approach competes with state-of-the-art methods, with much lower computational complexity.-
dc.languageeng-
dc.relation.ispartofInternational Geoscience and Remote Sensing Symposium (IGARSS)-
dc.subjectsparse representation-
dc.subjectDenoising-
dc.subjectsignal subspace-
dc.subjectBM4D-
dc.subjecthyperspectral image-
dc.subjectlow rank structure-
dc.subjectBM3D-
dc.subjectnon-local patch(cube)-
dc.titleFast Hyperspectral image Denoising based on low rank and sparse representations-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/IGARSS.2016.7729474-
dc.identifier.scopuseid_2-s2.0-85007415400-
dc.identifier.volume2016-November-
dc.identifier.spage1847-
dc.identifier.epage1850-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats