Automatic Selection of Object Recognition Methods using Reinforcement Learning

Studies in Computational Intelligence. Springer. Volume 262, Dedicated to the Memory of Professor Ryszard S.Michalski

Detalles Bibliográficos
Autores: Bianchi, Reinaldo, Ramisa, Arnau, López de Mántaras, Ramón
Tipo de recurso: artículo
Fecha de publicación:2010
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/31525
Acceso en línea:http://hdl.handle.net/10261/31525
Access Level:acceso abierto
Palabra clave:Object recognition
Computer vision
Mobile robot
id ES_2ff7b5df868b52fba4a6cc6f8f06bb02
oai_identifier_str oai:digital.csic.es:10261/31525
network_acronym_str ES
network_name_str España
repository_id_str
spelling Automatic Selection of Object Recognition Methods using Reinforcement LearningBianchi, ReinaldoRamisa, ArnauLópez de Mántaras, RamónObject recognitionComputer visionMobile robotStudies in Computational Intelligence. Springer. Volume 262, Dedicated to the Memory of Professor Ryszard S.MichalskiSelecting which algorithms should be used by a mobile robot computer vision system is a decision that is usually made a priori by the system developer, based on past experience and intuition, not systematically taking into account information that can be found in the images and in the visual process itself to learn which algorithm should be used, in execution time. This paper presents a method that uses Reinforcement Learning to decide which algorithm should be used to recognize objects seen by a mobile robot in an indoor environment, based on simple attributes extracted on-line from the images, such as mean intensity and intensity deviation. Two state-of-the-art object recognition algorithms can be selected: the constellation method proposed by Lowe together with its interest point detector and descriptor, the Scale-Invariant Feature Transform and Nist´er and Stew´enius Vocabulary Tree approach. A set of empirical evaluations was conducted using a image database acquired with a mobile robot in an indoor environment, and results obtained shows that the approach adopted here is very promising.This work has been partially funded by the FI grant and the BE grant from the AGAUR, the 2005-SGR-00093 project, supported by the Generalitat de Catalunya, the MIDCBR project grant TIN 2006-15140-C03-01 and FEDER funds. Reinaldo Bianchi is supported by CNPq grant 201591/2007-3.Peer reviewedSpringer NatureGeneralitat de CatalunyaEuropean CommissionConselho Nacional de Desenvolvimento Científico e Tecnológico (Brasil)201120112010info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501http://hdl.handle.net/10261/31525reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Ingléshttp://www.springerlink.com/info:eu-repo/semantics/openAccessoai:digital.csic.es:10261/315252026-05-22T06:33:51Z
dc.title.none.fl_str_mv Automatic Selection of Object Recognition Methods using Reinforcement Learning
title Automatic Selection of Object Recognition Methods using Reinforcement Learning
spellingShingle Automatic Selection of Object Recognition Methods using Reinforcement Learning
Bianchi, Reinaldo
Object recognition
Computer vision
Mobile robot
title_short Automatic Selection of Object Recognition Methods using Reinforcement Learning
title_full Automatic Selection of Object Recognition Methods using Reinforcement Learning
title_fullStr Automatic Selection of Object Recognition Methods using Reinforcement Learning
title_full_unstemmed Automatic Selection of Object Recognition Methods using Reinforcement Learning
title_sort Automatic Selection of Object Recognition Methods using Reinforcement Learning
dc.creator.none.fl_str_mv Bianchi, Reinaldo
Ramisa, Arnau
López de Mántaras, Ramón
author Bianchi, Reinaldo
author_facet Bianchi, Reinaldo
Ramisa, Arnau
López de Mántaras, Ramón
author_role author
author2 Ramisa, Arnau
López de Mántaras, Ramón
author2_role author
author
dc.contributor.none.fl_str_mv Generalitat de Catalunya
European Commission
Conselho Nacional de Desenvolvimento Científico e Tecnológico (Brasil)
dc.subject.none.fl_str_mv Object recognition
Computer vision
Mobile robot
topic Object recognition
Computer vision
Mobile robot
description Studies in Computational Intelligence. Springer. Volume 262, Dedicated to the Memory of Professor Ryszard S.Michalski
publishDate 2010
dc.date.none.fl_str_mv 2010
2011
2011
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/31525
url http://hdl.handle.net/10261/31525
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv http://www.springerlink.com/
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Springer Nature
publisher.none.fl_str_mv Springer Nature
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405513255485440
score 15.81155

Similares en LA Referencia