On the optical flow model selection through metaheuristics
Autor(a) principal: | |
---|---|
Data de Publicação: | 2015 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://jivp.eurasipjournals.com/content/2015/1/11 http://hdl.handle.net/11449/129416 |
Resumo: | Optical flow methods are accurate algorithms for estimating the displacement and velocity fields of objects in a wide variety of applications, being their performance dependent on the configuration of a set of parameters. Since there is a lack of research that aims to automatically tune such parameters, in this work, we have proposed an optimization-based framework for such task based on social-spider optimization, harmony search, particle swarm optimization, and Nelder-Mead algorithm. The proposed framework employed the well-known large displacement optical flow (LDOF) approach as a basis algorithm over the Middlebury and Sintel public datasets, with promising results considering the baseline proposed by the authors of LDOF. |
id |
UNSP_28b8edc1451cd5a064b404629ce66a77 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/129416 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
On the optical flow model selection through metaheuristicsOptimization methodsEvolutionary algorithmsOptical flow methodsOptical flow methods are accurate algorithms for estimating the displacement and velocity fields of objects in a wide variety of applications, being their performance dependent on the configuration of a set of parameters. Since there is a lack of research that aims to automatically tune such parameters, in this work, we have proposed an optimization-based framework for such task based on social-spider optimization, harmony search, particle swarm optimization, and Nelder-Mead algorithm. The proposed framework employed the well-known large displacement optical flow (LDOF) approach as a basis algorithm over the Middlebury and Sintel public datasets, with promising results considering the baseline proposed by the authors of LDOF.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Universidad de los Andes FAIUniversity of the Andes, Mons. Álvaro del Portillo, Santiago 12445, ChileSão Paulo State University, Av. Eng. Luiz Edmundo Carrijo Coube, Departamento de Computação, 14-01, Bauru 17033-360, SP, BrazilFAPESP: 2013/20387-7FAPESP: 2014/16250-9CNPq: 303182/2011-3CNPq: 470571/2013-6CNPq: 306166/2014-3Universidad de los Andes FAI: 05/2013SpringerUniversidade Estadual Paulista (Unesp)Universidade dos AndesPereira, Danillo R. [UNESP]Delpiano, JoséPapa, João P. [UNESP]2015-10-21T21:03:08Z2015-10-21T21:03:08Z2015-05-09info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article1-10application/pdfhttp://jivp.eurasipjournals.com/content/2015/1/11Eurasip Journal On Image And Video Processing. Cham: Springer International Publishing Ag, v. 2015, n. 11, p. 1-10, 2015.1687-5281http://hdl.handle.net/11449/12941610.1186/s13640-015-0066-5WOS:000354709700001WOS000354709700001.pdfWeb of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEurasip Journal On Image And Video Processing1.7370,409info:eu-repo/semantics/openAccess2024-04-23T16:10:42Zoai:repositorio.unesp.br:11449/129416Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T14:23:26.234385Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
On the optical flow model selection through metaheuristics |
title |
On the optical flow model selection through metaheuristics |
spellingShingle |
On the optical flow model selection through metaheuristics Pereira, Danillo R. [UNESP] Optimization methods Evolutionary algorithms Optical flow methods |
title_short |
On the optical flow model selection through metaheuristics |
title_full |
On the optical flow model selection through metaheuristics |
title_fullStr |
On the optical flow model selection through metaheuristics |
title_full_unstemmed |
On the optical flow model selection through metaheuristics |
title_sort |
On the optical flow model selection through metaheuristics |
author |
Pereira, Danillo R. [UNESP] |
author_facet |
Pereira, Danillo R. [UNESP] Delpiano, José Papa, João P. [UNESP] |
author_role |
author |
author2 |
Delpiano, José Papa, João P. [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Universidade dos Andes |
dc.contributor.author.fl_str_mv |
Pereira, Danillo R. [UNESP] Delpiano, José Papa, João P. [UNESP] |
dc.subject.por.fl_str_mv |
Optimization methods Evolutionary algorithms Optical flow methods |
topic |
Optimization methods Evolutionary algorithms Optical flow methods |
description |
Optical flow methods are accurate algorithms for estimating the displacement and velocity fields of objects in a wide variety of applications, being their performance dependent on the configuration of a set of parameters. Since there is a lack of research that aims to automatically tune such parameters, in this work, we have proposed an optimization-based framework for such task based on social-spider optimization, harmony search, particle swarm optimization, and Nelder-Mead algorithm. The proposed framework employed the well-known large displacement optical flow (LDOF) approach as a basis algorithm over the Middlebury and Sintel public datasets, with promising results considering the baseline proposed by the authors of LDOF. |
publishDate |
2015 |
dc.date.none.fl_str_mv |
2015-10-21T21:03:08Z 2015-10-21T21:03:08Z 2015-05-09 |
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://jivp.eurasipjournals.com/content/2015/1/11 Eurasip Journal On Image And Video Processing. Cham: Springer International Publishing Ag, v. 2015, n. 11, p. 1-10, 2015. 1687-5281 http://hdl.handle.net/11449/129416 10.1186/s13640-015-0066-5 WOS:000354709700001 WOS000354709700001.pdf |
url |
http://jivp.eurasipjournals.com/content/2015/1/11 http://hdl.handle.net/11449/129416 |
identifier_str_mv |
Eurasip Journal On Image And Video Processing. Cham: Springer International Publishing Ag, v. 2015, n. 11, p. 1-10, 2015. 1687-5281 10.1186/s13640-015-0066-5 WOS:000354709700001 WOS000354709700001.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Eurasip Journal On Image And Video Processing 1.737 0,409 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
1-10 application/pdf |
dc.publisher.none.fl_str_mv |
Springer |
publisher.none.fl_str_mv |
Springer |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128354286567424 |