File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Normal Endmember Spectral Unmixing Method for Hyperspectral Imagery

TitleNormal Endmember Spectral Unmixing Method for Hyperspectral Imagery
Authors
Keywordsnormal endmember spectral unmixing (NESU)
normal compositional model (NCM)
hyperspectral imaging
spectral unmixing
particle swarm optimization (PSO)
Endmember variability
Issue Date2015
Citation
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, v. 8, n. 6, p. 2598-2606 How to Cite?
AbstractThe normal compositional model (NCM) has been introduced to characterize mixed pixels in hyperspectral images, particularly when endmember variability needs to be considered in the unmixing process. Each pixel is modeled as a linear combination of endmembers, which are treated as Gaussian random variables in order to capture such spectral variability. Since the combination coefficients (i.e., abundances) and the endmembers are unknown variables at the same time in the NCM, the parameter estimation is more difficult in comparison with conventional approaches. In order to address this issue, we propose a new Bayesian method, termed normal endmember spectral unmixing (NESU), for improved parameter estimation in this context. It considers the endmembers as known variables (resulting from the extraction of endmember bundles), then performs optimal estimations of the remaining unknown parameters, i.e., the abundances, using Bayesian inference. The particle swarm optimization (PSO) technique is adopted to estimate the optimal values of abundances according to their posterior probabilities. The performance of the proposed algorithm is evaluated using both synthetic and real hyperspectral data. The obtained results demonstrate that the proposed method leads to significant improvements in terms of unmixing accuracies.
Persistent Identifierhttp://hdl.handle.net/10722/298224
ISSN
2020 Impact Factor: 3.784
2020 SCImago Journal Rankings: 1.246
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhuang, Lina-
dc.contributor.authorZhang, Bing-
dc.contributor.authorGao, Lianru-
dc.contributor.authorLi, Jun-
dc.contributor.authorPlaza, Antonio-
dc.date.accessioned2021-04-08T03:07:56Z-
dc.date.available2021-04-08T03:07:56Z-
dc.date.issued2015-
dc.identifier.citationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, v. 8, n. 6, p. 2598-2606-
dc.identifier.issn1939-1404-
dc.identifier.urihttp://hdl.handle.net/10722/298224-
dc.description.abstractThe normal compositional model (NCM) has been introduced to characterize mixed pixels in hyperspectral images, particularly when endmember variability needs to be considered in the unmixing process. Each pixel is modeled as a linear combination of endmembers, which are treated as Gaussian random variables in order to capture such spectral variability. Since the combination coefficients (i.e., abundances) and the endmembers are unknown variables at the same time in the NCM, the parameter estimation is more difficult in comparison with conventional approaches. In order to address this issue, we propose a new Bayesian method, termed normal endmember spectral unmixing (NESU), for improved parameter estimation in this context. It considers the endmembers as known variables (resulting from the extraction of endmember bundles), then performs optimal estimations of the remaining unknown parameters, i.e., the abundances, using Bayesian inference. The particle swarm optimization (PSO) technique is adopted to estimate the optimal values of abundances according to their posterior probabilities. The performance of the proposed algorithm is evaluated using both synthetic and real hyperspectral data. The obtained results demonstrate that the proposed method leads to significant improvements in terms of unmixing accuracies.-
dc.languageeng-
dc.relation.ispartofIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing-
dc.subjectnormal endmember spectral unmixing (NESU)-
dc.subjectnormal compositional model (NCM)-
dc.subjecthyperspectral imaging-
dc.subjectspectral unmixing-
dc.subjectparticle swarm optimization (PSO)-
dc.subjectEndmember variability-
dc.titleNormal Endmember Spectral Unmixing Method for Hyperspectral Imagery-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/JSTARS.2014.2360888-
dc.identifier.scopuseid_2-s2.0-85027937942-
dc.identifier.volume8-
dc.identifier.issue6-
dc.identifier.spage2598-
dc.identifier.epage2606-
dc.identifier.eissn2151-1535-
dc.identifier.isiWOS:000359264000025-
dc.identifier.issnl1939-1404-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats