An enhanced triplet CNN based on body parts for person re-identificacion

Descripción del Articulo

This work was supported by grant 234-2015-FONDECYT (Master Program) from Cienciactiva of the National Council for Science,Technology and Technological Innovation (CONCYTEC-PERU).
Detalles Bibliográficos
Autores: Espinoza J.D., Chavez G.C., Torres G.H.
Formato: objeto de conferencia
Fecha de Publicación:2018
Institución:Consejo Nacional de Ciencia Tecnología e Innovación
Repositorio:CONCYTEC-Institucional
Lenguaje:español
OAI Identifier:oai:repositorio.concytec.gob.pe:20.500.12390/510
Enlace del recurso:https://hdl.handle.net/20.500.12390/510
https://doi.org/10.1109/SCCC.2017.8405126
Nivel de acceso:acceso abierto
Materia:State of the art
Computers
Camera view
Feature representation
Human bodies
Improve performance
Overfitting
Partial occlusions
Person re identifications
Computer science
https://purl.org/pe-repo/ocde/ford#1.02.01
id CONC_2cce8b5eb6b53d1f5c6798e0ce139dfc
oai_identifier_str oai:repositorio.concytec.gob.pe:20.500.12390/510
network_acronym_str CONC
network_name_str CONCYTEC-Institucional
repository_id_str 4689
dc.title.none.fl_str_mv An enhanced triplet CNN based on body parts for person re-identificacion
title An enhanced triplet CNN based on body parts for person re-identificacion
spellingShingle An enhanced triplet CNN based on body parts for person re-identificacion
Espinoza J.D.
State of the art
Computers
Camera view
Feature representation
Human bodies
Improve performance
Overfitting
Partial occlusions
Person re identifications
Computer science
https://purl.org/pe-repo/ocde/ford#1.02.01
title_short An enhanced triplet CNN based on body parts for person re-identificacion
title_full An enhanced triplet CNN based on body parts for person re-identificacion
title_fullStr An enhanced triplet CNN based on body parts for person re-identificacion
title_full_unstemmed An enhanced triplet CNN based on body parts for person re-identificacion
title_sort An enhanced triplet CNN based on body parts for person re-identificacion
author Espinoza J.D.
author_facet Espinoza J.D.
Chavez G.C.
Torres G.H.
author_role author
author2 Chavez G.C.
Torres G.H.
author2_role author
author
dc.contributor.author.fl_str_mv Espinoza J.D.
Chavez G.C.
Torres G.H.
dc.subject.none.fl_str_mv State of the art
topic State of the art
Computers
Camera view
Feature representation
Human bodies
Improve performance
Overfitting
Partial occlusions
Person re identifications
Computer science
https://purl.org/pe-repo/ocde/ford#1.02.01
dc.subject.es_PE.fl_str_mv Computers
Camera view
Feature representation
Human bodies
Improve performance
Overfitting
Partial occlusions
Person re identifications
Computer science
dc.subject.ocde.none.fl_str_mv https://purl.org/pe-repo/ocde/ford#1.02.01
description This work was supported by grant 234-2015-FONDECYT (Master Program) from Cienciactiva of the National Council for Science,Technology and Technological Innovation (CONCYTEC-PERU).
publishDate 2018
dc.date.accessioned.none.fl_str_mv 2024-05-30T23:13:38Z
dc.date.available.none.fl_str_mv 2024-05-30T23:13:38Z
dc.date.issued.fl_str_mv 2018
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
dc.identifier.isbn.none.fl_str_mv 9781538634837
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/20.500.12390/510
dc.identifier.doi.none.fl_str_mv https://doi.org/10.1109/SCCC.2017.8405126
dc.identifier.scopus.none.fl_str_mv 2-s2.0-85050964708
identifier_str_mv 9781538634837
2-s2.0-85050964708
url https://hdl.handle.net/20.500.12390/510
https://doi.org/10.1109/SCCC.2017.8405126
dc.language.iso.none.fl_str_mv spa
language spa
dc.relation.ispartof.none.fl_str_mv Proceedings - International Conference of the Chilean Computer Science Society, SCCC
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv IEEE Computer Society
publisher.none.fl_str_mv IEEE Computer Society
dc.source.none.fl_str_mv reponame:CONCYTEC-Institucional
instname:Consejo Nacional de Ciencia Tecnología e Innovación
instacron:CONCYTEC
instname_str Consejo Nacional de Ciencia Tecnología e Innovación
instacron_str CONCYTEC
institution CONCYTEC
reponame_str CONCYTEC-Institucional
collection CONCYTEC-Institucional
repository.name.fl_str_mv Repositorio Institucional CONCYTEC
repository.mail.fl_str_mv repositorio@concytec.gob.pe
_version_ 1839175807770034176
spelling Publicationrp00692600rp00690600rp00691600Espinoza J.D.Chavez G.C.Torres G.H.2024-05-30T23:13:38Z2024-05-30T23:13:38Z20189781538634837https://hdl.handle.net/20.500.12390/510https://doi.org/10.1109/SCCC.2017.84051262-s2.0-85050964708This work was supported by grant 234-2015-FONDECYT (Master Program) from Cienciactiva of the National Council for Science,Technology and Technological Innovation (CONCYTEC-PERU).Person re-identificacion consists of reidentificating person through a set of images that is taken by different camera views. Despite recent advances in this field, this problem still remains a challenge due to partial occlusions, changes in illumination, variation in human body poses. In this paper, we present an enhanced Triplet CNN based on body-parts for person re-identification (AETCNN). We design a new model able to learn local body-part features and integrate them to produce the final feature representation of each input person. In addition, to avoid over-fitting due to the small size of the dataset, we propose an improvement in triplet assignment to speed up the convergence and improve performance. Experiments show that our approach achieves very promising results in (CUHK01) dataset and we advance state of the art, improving most of the results of the state of the art with a simpler architecture, achieving 76.50% in rank 1.Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica - ConcytecspaIEEE Computer SocietyProceedings - International Conference of the Chilean Computer Science Society, SCCCinfo:eu-repo/semantics/openAccessState of the artComputers-1Camera view-1Feature representation-1Human bodies-1Improve performance-1Overfitting-1Partial occlusions-1Person re identifications-1Computer science-1https://purl.org/pe-repo/ocde/ford#1.02.01-1An enhanced triplet CNN based on body parts for person re-identificacioninfo:eu-repo/semantics/conferenceObjectreponame:CONCYTEC-Institucionalinstname:Consejo Nacional de Ciencia Tecnología e Innovacióninstacron:CONCYTEC#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#20.500.12390/510oai:repositorio.concytec.gob.pe:20.500.12390/5102024-05-30 15:35:37.764http://purl.org/coar/access_right/c_14cbinfo:eu-repo/semantics/closedAccessmetadata only accesshttps://repositorio.concytec.gob.peRepositorio Institucional CONCYTECrepositorio@concytec.gob.pe#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="ec9698e3-071a-4b0b-9bac-bc0cc94fb4a8"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>spa</Language> <Title>An enhanced triplet CNN based on body parts for person re-identificacion</Title> <PublishedIn> <Publication> <Title>Proceedings - International Conference of the Chilean Computer Science Society, SCCC</Title> </Publication> </PublishedIn> <PublicationDate>2018</PublicationDate> <DOI>https://doi.org/10.1109/SCCC.2017.8405126</DOI> <SCP-Number>2-s2.0-85050964708</SCP-Number> <ISBN>9781538634837</ISBN> <Authors> <Author> <DisplayName>Espinoza J.D.</DisplayName> <Person id="rp00692" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Chavez G.C.</DisplayName> <Person id="rp00690" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Torres G.H.</DisplayName> <Person id="rp00691" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>IEEE Computer Society</DisplayName> <OrgUnit /> </Publisher> </Publishers> <Keyword>State of the art</Keyword> <Keyword>Computers</Keyword> <Keyword>Camera view</Keyword> <Keyword>Feature representation</Keyword> <Keyword>Human bodies</Keyword> <Keyword>Improve performance</Keyword> <Keyword>Overfitting</Keyword> <Keyword>Partial occlusions</Keyword> <Keyword>Person re identifications</Keyword> <Keyword>Computer science</Keyword> <Abstract>Person re-identificacion consists of reidentificating person through a set of images that is taken by different camera views. Despite recent advances in this field, this problem still remains a challenge due to partial occlusions, changes in illumination, variation in human body poses. In this paper, we present an enhanced Triplet CNN based on body-parts for person re-identification (AETCNN). We design a new model able to learn local body-part features and integrate them to produce the final feature representation of each input person. In addition, to avoid over-fitting due to the small size of the dataset, we propose an improvement in triplet assignment to speed up the convergence and improve performance. Experiments show that our approach achieves very promising results in (CUHK01) dataset and we advance state of the art, improving most of the results of the state of the art with a simpler architecture, achieving 76.50% in rank 1.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication> -1
score 13.448654
An enhanced triplet CNN based on body parts for person re-identificacion
Nota importante:
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).

Ejemplares Similares