File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Region-Based Estimate of Endmember Variances for Hyperspectral Image Unmixing

TitleRegion-Based Estimate of Endmember Variances for Hyperspectral Image Unmixing
Authors
Keywordsnormal compositional model (NCM)
Endmember variability
hyperspectral unmixing
region-based stochastic expectation maximization (R-SEM)
Issue Date2016
Citation
IEEE Geoscience and Remote Sensing Letters, 2016, v. 13, n. 12, p. 1807-1811 How to Cite?
AbstractEndmember variability is receiving growing attention in the hyperspectral image (HSI) unmixing field. As an extension of linear mixing model (LMM), normal compositional model (NCM) assumes that the pixels of the HSI are linear combinations of random endmembers (as opposed to deterministic for the LMM). NCM explains spectral differences between the observed pixels and endmembers as endmember mixtures and endmember variances, the characteristic of which makes it possible to incorporate the endmember spectral variability in the unmixing process. But the tricky issue for using NCM is the estimation of endmember variances inhering in materials. This letter presents a new approach, termed region-based stochastic expectation maximization, to learn endmember variances from spatial information. The idea is assuming that significant homogeneous regions (composed of similar materials or similar mixture) exist in the HSI, such regions usually give visual indication that spatial-based spectral variability really exists in hyperspectral data. As modeled in NCM, spectral variances in homogeneous region can be approximately linear represented by endmember variances. Hence, given region-based spectral variances, we are able to learn endmember variances. In experiments with simulated data and Moffett field data, the proposed approach competes with other unmixing methods considering endmember variability, with better endmember variance estimates.
Persistent Identifierhttp://hdl.handle.net/10722/298188
ISSN
2020 Impact Factor: 3.966
2020 SCImago Journal Rankings: 1.372

 

DC FieldValueLanguage
dc.contributor.authorGao, Lianru-
dc.contributor.authorZhuang, Lina-
dc.contributor.authorZhang, Bing-
dc.date.accessioned2021-04-08T03:07:52Z-
dc.date.available2021-04-08T03:07:52Z-
dc.date.issued2016-
dc.identifier.citationIEEE Geoscience and Remote Sensing Letters, 2016, v. 13, n. 12, p. 1807-1811-
dc.identifier.issn1545-598X-
dc.identifier.urihttp://hdl.handle.net/10722/298188-
dc.description.abstractEndmember variability is receiving growing attention in the hyperspectral image (HSI) unmixing field. As an extension of linear mixing model (LMM), normal compositional model (NCM) assumes that the pixels of the HSI are linear combinations of random endmembers (as opposed to deterministic for the LMM). NCM explains spectral differences between the observed pixels and endmembers as endmember mixtures and endmember variances, the characteristic of which makes it possible to incorporate the endmember spectral variability in the unmixing process. But the tricky issue for using NCM is the estimation of endmember variances inhering in materials. This letter presents a new approach, termed region-based stochastic expectation maximization, to learn endmember variances from spatial information. The idea is assuming that significant homogeneous regions (composed of similar materials or similar mixture) exist in the HSI, such regions usually give visual indication that spatial-based spectral variability really exists in hyperspectral data. As modeled in NCM, spectral variances in homogeneous region can be approximately linear represented by endmember variances. Hence, given region-based spectral variances, we are able to learn endmember variances. In experiments with simulated data and Moffett field data, the proposed approach competes with other unmixing methods considering endmember variability, with better endmember variance estimates.-
dc.languageeng-
dc.relation.ispartofIEEE Geoscience and Remote Sensing Letters-
dc.subjectnormal compositional model (NCM)-
dc.subjectEndmember variability-
dc.subjecthyperspectral unmixing-
dc.subjectregion-based stochastic expectation maximization (R-SEM)-
dc.titleRegion-Based Estimate of Endmember Variances for Hyperspectral Image Unmixing-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/LGRS.2016.2614101-
dc.identifier.scopuseid_2-s2.0-85006747006-
dc.identifier.volume13-
dc.identifier.issue12-
dc.identifier.spage1807-
dc.identifier.epage1811-
dc.identifier.issnl1545-598X-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats