Simultaneous and causal appearance learning and tracking

A novel way to learn and track simultaneously the appearance of a previously non-seen face without intrusive techniques can be found in this article. The presented approach has a causal behaviour: no future frames are needed to process the current ones. The model used in the tracking process is refi...

ver descrição completa

Detalhes bibliográficos
Autores: Melenchón Maldonado, Javier, Iriondo Sanz, Ignasi, Meler Corretjé, Lourdes
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2005
País:España
Recursos:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositório:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:20.500.14342/3190
Acesso em linha:http://hdl.handle.net/20.500.14342/3190
Access Level:Acceso aberto
Palavra-chave:Imatges--Processament
Imatges--Processament--Tècniques digitals
Reconeixement facial (Informàtica)
Reconeixement òptic de formes
62
id ES_e2497a1cc9b6aec78b864bb2ccd95a13
oai_identifier_str oai:recercat.cat:20.500.14342/3190
network_acronym_str ES
network_name_str España
repository_id_str
spelling Simultaneous and causal appearance learning and trackingMelenchón Maldonado, JavierIriondo Sanz, IgnasiMeler Corretjé, LourdesImatges--ProcessamentImatges--Processament--Tècniques digitalsReconeixement facial (Informàtica)Reconeixement òptic de formes62A novel way to learn and track simultaneously the appearance of a previously non-seen face without intrusive techniques can be found in this article. The presented approach has a causal behaviour: no future frames are needed to process the current ones. The model used in the tracking process is refined with each input frame thanks to a new algorithm for the simultaneous and incremental computation of the singular value decomposition (SVD) and the mean of the data. Previously developed methods about iterative computation of SVD are taken into account and an original way to extract the mean information from the reduced SVD of a matrix is also considered. Furthermore, the results are produced with linear computational cost and sublinear memory requirements with respect to the size of the data. Finally, experimental results are included, showing the tracking performance and some comparisons between the batch and our incremental computation of the SVD with mean information.Universitat Autònoma de BarcelonaUniversitat Ramon Llull. La Salle2005info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersion11 p.http://hdl.handle.net/20.500.14342/3190reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésElectronic letters on computer vision and image analysis, Vol. 5, No 3 (2005)© L'autor/aAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:20.500.14342/31902026-05-29T05:05:01Z
dc.title.none.fl_str_mv Simultaneous and causal appearance learning and tracking
title Simultaneous and causal appearance learning and tracking
spellingShingle Simultaneous and causal appearance learning and tracking
Melenchón Maldonado, Javier
Imatges--Processament
Imatges--Processament--Tècniques digitals
Reconeixement facial (Informàtica)
Reconeixement òptic de formes
62
title_short Simultaneous and causal appearance learning and tracking
title_full Simultaneous and causal appearance learning and tracking
title_fullStr Simultaneous and causal appearance learning and tracking
title_full_unstemmed Simultaneous and causal appearance learning and tracking
title_sort Simultaneous and causal appearance learning and tracking
dc.creator.none.fl_str_mv Melenchón Maldonado, Javier
Iriondo Sanz, Ignasi
Meler Corretjé, Lourdes
author Melenchón Maldonado, Javier
author_facet Melenchón Maldonado, Javier
Iriondo Sanz, Ignasi
Meler Corretjé, Lourdes
author_role author
author2 Iriondo Sanz, Ignasi
Meler Corretjé, Lourdes
author2_role author
author
dc.contributor.none.fl_str_mv Universitat Ramon Llull. La Salle
dc.subject.none.fl_str_mv Imatges--Processament
Imatges--Processament--Tècniques digitals
Reconeixement facial (Informàtica)
Reconeixement òptic de formes
62
topic Imatges--Processament
Imatges--Processament--Tècniques digitals
Reconeixement facial (Informàtica)
Reconeixement òptic de formes
62
description A novel way to learn and track simultaneously the appearance of a previously non-seen face without intrusive techniques can be found in this article. The presented approach has a causal behaviour: no future frames are needed to process the current ones. The model used in the tracking process is refined with each input frame thanks to a new algorithm for the simultaneous and incremental computation of the singular value decomposition (SVD) and the mean of the data. Previously developed methods about iterative computation of SVD are taken into account and an original way to extract the mean information from the reduced SVD of a matrix is also considered. Furthermore, the results are produced with linear computational cost and sublinear memory requirements with respect to the size of the data. Finally, experimental results are included, showing the tracking performance and some comparisons between the batch and our incremental computation of the SVD with mean information.
publishDate 2005
dc.date.none.fl_str_mv 2005
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.14342/3190
url http://hdl.handle.net/20.500.14342/3190
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Electronic letters on computer vision and image analysis, Vol. 5, No 3 (2005)
dc.rights.none.fl_str_mv © L'autor/a
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv © L'autor/a
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 11 p.
dc.publisher.none.fl_str_mv Universitat Autònoma de Barcelona
publisher.none.fl_str_mv Universitat Autònoma de Barcelona
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422372190158848
score 15,812429

Registros relacionados