Hyperspectral unmixing based on mixtures of Dirichlet components
Autor(a) principal: | |
---|---|
Data de Publicação: | 2012 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.21/5085 |
Resumo: | This paper introduces a new unsupervised hyperspectral unmixing method conceived to linear but highly mixed hyperspectral data sets, in which the simplex of minimum volume, usually estimated by the purely geometrically based algorithms, is far way from the true simplex associated with the endmembers. The proposed method, an extension of our previous studies, resorts to the statistical framework. The abundance fraction prior is a mixture of Dirichlet densities, thus automatically enforcing the constraints on the abundance fractions imposed by the acquisition process, namely, nonnegativity and sum-to-one. A cyclic minimization algorithm is developed where the following are observed: 1) The number of Dirichlet modes is inferred based on the minimum description length principle; 2) a generalized expectation maximization algorithm is derived to infer the model parameters; and 3) a sequence of augmented Lagrangian-based optimizations is used to compute the signatures of the endmembers. Experiments on simulated and real data are presented to show the effectiveness of the proposed algorithm in unmixing problems beyond the reach of the geometrically based state-of-the-art competitors. |
id |
RCAP_a485b66bc18573c47e055a771d7483f7 |
---|---|
oai_identifier_str |
oai:repositorio.ipl.pt:10400.21/5085 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Hyperspectral unmixing based on mixtures of Dirichlet componentsAugmented Lagrangian method of multipliersBlind hyperspectral unmixingDependent componentsGeneralized expectation maximization (GEM)Minimum desciption length (MDL)Mixtures of Dirichlet densitiesThis paper introduces a new unsupervised hyperspectral unmixing method conceived to linear but highly mixed hyperspectral data sets, in which the simplex of minimum volume, usually estimated by the purely geometrically based algorithms, is far way from the true simplex associated with the endmembers. The proposed method, an extension of our previous studies, resorts to the statistical framework. The abundance fraction prior is a mixture of Dirichlet densities, thus automatically enforcing the constraints on the abundance fractions imposed by the acquisition process, namely, nonnegativity and sum-to-one. A cyclic minimization algorithm is developed where the following are observed: 1) The number of Dirichlet modes is inferred based on the minimum description length principle; 2) a generalized expectation maximization algorithm is derived to infer the model parameters; and 3) a sequence of augmented Lagrangian-based optimizations is used to compute the signatures of the endmembers. Experiments on simulated and real data are presented to show the effectiveness of the proposed algorithm in unmixing problems beyond the reach of the geometrically based state-of-the-art competitors.IEEE - Inst Electrical Electronics Engineers IncRCIPLNascimento, JoseBioucas-Dias, José. M.2015-09-07T13:54:46Z2012-032012-03-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.21/5085engNASCIMENTO, José M. P.; DIAS-Bioucas, José M. – Hyperspectral unmixing based on mixtures of Dirichlet components. IEEE Transactions on Geoscience and Remote Sensing. ISSN: 0196-2892. Vol. 50, N.º 3 (2012), pp. 863-878.0196-289210.1109/TGRS.2011.2163941metadata only accessinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-08-03T09:47:59Zoai:repositorio.ipl.pt:10400.21/5085Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:14:24.756398Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Hyperspectral unmixing based on mixtures of Dirichlet components |
title |
Hyperspectral unmixing based on mixtures of Dirichlet components |
spellingShingle |
Hyperspectral unmixing based on mixtures of Dirichlet components Nascimento, Jose Augmented Lagrangian method of multipliers Blind hyperspectral unmixing Dependent components Generalized expectation maximization (GEM) Minimum desciption length (MDL) Mixtures of Dirichlet densities |
title_short |
Hyperspectral unmixing based on mixtures of Dirichlet components |
title_full |
Hyperspectral unmixing based on mixtures of Dirichlet components |
title_fullStr |
Hyperspectral unmixing based on mixtures of Dirichlet components |
title_full_unstemmed |
Hyperspectral unmixing based on mixtures of Dirichlet components |
title_sort |
Hyperspectral unmixing based on mixtures of Dirichlet components |
author |
Nascimento, Jose |
author_facet |
Nascimento, Jose Bioucas-Dias, José. M. |
author_role |
author |
author2 |
Bioucas-Dias, José. M. |
author2_role |
author |
dc.contributor.none.fl_str_mv |
RCIPL |
dc.contributor.author.fl_str_mv |
Nascimento, Jose Bioucas-Dias, José. M. |
dc.subject.por.fl_str_mv |
Augmented Lagrangian method of multipliers Blind hyperspectral unmixing Dependent components Generalized expectation maximization (GEM) Minimum desciption length (MDL) Mixtures of Dirichlet densities |
topic |
Augmented Lagrangian method of multipliers Blind hyperspectral unmixing Dependent components Generalized expectation maximization (GEM) Minimum desciption length (MDL) Mixtures of Dirichlet densities |
description |
This paper introduces a new unsupervised hyperspectral unmixing method conceived to linear but highly mixed hyperspectral data sets, in which the simplex of minimum volume, usually estimated by the purely geometrically based algorithms, is far way from the true simplex associated with the endmembers. The proposed method, an extension of our previous studies, resorts to the statistical framework. The abundance fraction prior is a mixture of Dirichlet densities, thus automatically enforcing the constraints on the abundance fractions imposed by the acquisition process, namely, nonnegativity and sum-to-one. A cyclic minimization algorithm is developed where the following are observed: 1) The number of Dirichlet modes is inferred based on the minimum description length principle; 2) a generalized expectation maximization algorithm is derived to infer the model parameters; and 3) a sequence of augmented Lagrangian-based optimizations is used to compute the signatures of the endmembers. Experiments on simulated and real data are presented to show the effectiveness of the proposed algorithm in unmixing problems beyond the reach of the geometrically based state-of-the-art competitors. |
publishDate |
2012 |
dc.date.none.fl_str_mv |
2012-03 2012-03-01T00:00:00Z 2015-09-07T13:54:46Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.21/5085 |
url |
http://hdl.handle.net/10400.21/5085 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
NASCIMENTO, José M. P.; DIAS-Bioucas, José M. – Hyperspectral unmixing based on mixtures of Dirichlet components. IEEE Transactions on Geoscience and Remote Sensing. ISSN: 0196-2892. Vol. 50, N.º 3 (2012), pp. 863-878. 0196-2892 10.1109/TGRS.2011.2163941 |
dc.rights.driver.fl_str_mv |
metadata only access info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
metadata only access |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
IEEE - Inst Electrical Electronics Engineers Inc |
publisher.none.fl_str_mv |
IEEE - Inst Electrical Electronics Engineers Inc |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133401638240256 |