Building the what and where systems: multi-scale lines, edges and keypoints
Autor(a) principal: | |
---|---|
Data de Publicação: | 2005 |
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/10400.1/162 |
Resumo: | Computer vision for realtime applications requires tremendous computational power because all images must be processed from the first to the last pixel. Ac tive vision by probing specific objects on the basis of already acquired context may lead to a significant reduction of processing. This idea is based on a few concepts from our visual cortex (Rensink, Visual Cogn. 7, 17-42, 2000): (1) our physical surround can be seen as memory, i.e. there is no need to construct detailed and complete maps, (2) the bandwidth of the what and where systems is limited, i.e. only one object can be probed at any time, and (3) bottom-up, low-level feature extraction is complemented by top-down hypothesis testing, i.e. there is a rapid convergence of activities in dendritic/axonal connections. |
id |
RCAP_fe6e01a926250afe1bd96527af9e783f |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/162 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Building the what and where systems: multi-scale lines, edges and keypointsVisão computorizadaCórtex visual621.38Computer vision for realtime applications requires tremendous computational power because all images must be processed from the first to the last pixel. Ac tive vision by probing specific objects on the basis of already acquired context may lead to a significant reduction of processing. This idea is based on a few concepts from our visual cortex (Rensink, Visual Cogn. 7, 17-42, 2000): (1) our physical surround can be seen as memory, i.e. there is no need to construct detailed and complete maps, (2) the bandwidth of the what and where systems is limited, i.e. only one object can be probed at any time, and (3) bottom-up, low-level feature extraction is complemented by top-down hypothesis testing, i.e. there is a rapid convergence of activities in dendritic/axonal connections.ReadingSapientiaRodrigues, J. M. F.Almeida, D.Nunes, S.Lam, Robertodu Buf, J. M. H.2009-02-13T17:09:59Z20052005-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfapplication/pdfhttp://hdl.handle.net/10400.1/162engWorkshop on Active Vision VII (7WAV 2005). - Reading, 12 September 2005. - p 8AUT: JRO00913; RLA01073; DUB00865;info: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:RCAAP2023-07-24T10:10:53Zoai:sapientia.ualg.pt:10400.1/162Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:54:34.510346Repositório 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 |
Building the what and where systems: multi-scale lines, edges and keypoints |
title |
Building the what and where systems: multi-scale lines, edges and keypoints |
spellingShingle |
Building the what and where systems: multi-scale lines, edges and keypoints Rodrigues, J. M. F. Visão computorizada Córtex visual 621.38 |
title_short |
Building the what and where systems: multi-scale lines, edges and keypoints |
title_full |
Building the what and where systems: multi-scale lines, edges and keypoints |
title_fullStr |
Building the what and where systems: multi-scale lines, edges and keypoints |
title_full_unstemmed |
Building the what and where systems: multi-scale lines, edges and keypoints |
title_sort |
Building the what and where systems: multi-scale lines, edges and keypoints |
author |
Rodrigues, J. M. F. |
author_facet |
Rodrigues, J. M. F. Almeida, D. Nunes, S. Lam, Roberto du Buf, J. M. H. |
author_role |
author |
author2 |
Almeida, D. Nunes, S. Lam, Roberto du Buf, J. M. H. |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Sapientia |
dc.contributor.author.fl_str_mv |
Rodrigues, J. M. F. Almeida, D. Nunes, S. Lam, Roberto du Buf, J. M. H. |
dc.subject.por.fl_str_mv |
Visão computorizada Córtex visual 621.38 |
topic |
Visão computorizada Córtex visual 621.38 |
description |
Computer vision for realtime applications requires tremendous computational power because all images must be processed from the first to the last pixel. Ac tive vision by probing specific objects on the basis of already acquired context may lead to a significant reduction of processing. This idea is based on a few concepts from our visual cortex (Rensink, Visual Cogn. 7, 17-42, 2000): (1) our physical surround can be seen as memory, i.e. there is no need to construct detailed and complete maps, (2) the bandwidth of the what and where systems is limited, i.e. only one object can be probed at any time, and (3) bottom-up, low-level feature extraction is complemented by top-down hypothesis testing, i.e. there is a rapid convergence of activities in dendritic/axonal connections. |
publishDate |
2005 |
dc.date.none.fl_str_mv |
2005 2005-01-01T00:00:00Z 2009-02-13T17:09:59Z |
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/10400.1/162 |
url |
http://hdl.handle.net/10400.1/162 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Workshop on Active Vision VII (7WAV 2005). - Reading, 12 September 2005. - p 8 AUT: JRO00913; RLA01073; DUB00865; |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf application/pdf |
dc.publisher.none.fl_str_mv |
Reading |
publisher.none.fl_str_mv |
Reading |
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_ |
1799133144862949376 |