Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data

Recently, 6D pose estimation methods have shown robust performance on highly cluttered scenes and different illumination conditions. However, occlusions are still challenging, with recognition rates decreasing to less than 10% for half-visible objects in some datasets. In this paper, we propose to u...

Descripción completa

Detalles Bibliográficos
Autores: Vidal Verdaguer, Joel, Lin, Chyi Yeu, Martí Marly, Robert
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10256/20491
Acceso en línea:http://hdl.handle.net/10256/20491
Access Level:acceso abierto
Palabra clave:Visió per ordinador
Computer vision
Reconeixement de formes (Informàtica)
Pattern recognition systems
Visualització tridimensional (Informàtica)
Three-dimensional display systems
id ES_8dfea6d83abdb6b29f446ed32f95feed
oai_identifier_str oai:recercat.cat:10256/20491
network_acronym_str ES
network_name_str España
repository_id_str
spelling Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d dataVidal Verdaguer, JoelLin, Chyi YeuMartí Marly, RobertVisió per ordinadorComputer visionReconeixement de formes (Informàtica)Pattern recognition systemsVisualització tridimensional (Informàtica)Three-dimensional display systemsRecently, 6D pose estimation methods have shown robust performance on highly cluttered scenes and different illumination conditions. However, occlusions are still challenging, with recognition rates decreasing to less than 10% for half-visible objects in some datasets. In this paper, we propose to use top-down visual attention and color cues to boost performance of a state-of-the-art method on occluded scenarios. More specifically, color information is employed to detect potential points in the scene, improve feature-matching, and compute more precise fitting scores. The proposed method is evaluated on the Linemod occluded (LM-O), TUD light (TUD-L), Tejani (IC-MI) and Doumanoglou (IC-BIN) datasets, as part of the SiSo BOP benchmark, which includes challenging highly occluded cases, illumination changing scenarios, and multiple instances. The method is analyzed and discussed for different parameters, color spaces and metrics. The presented results show the validity of the proposed approach and their robustness against illumination changes and multiple instance scenarios, specially boosting the performance on relatively high occluded cases. The proposed solution provides an absolute improvement of up to 30% for levels of occlusion between 40% to 50%, outperforming other approaches with a best overall recall of 71% for the LM-O, 92% for TUD-L, 99.3% for IC-MI and 97.5% for IC-BINAuthors acknowledge the financial support from the Spanish Science, Innovation and Universities Ministry under grant number RTI2018-096333-B-I00MDPI (Multidisciplinary Digital Publishing Institute)Agencia Estatal de Investigación2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionpeer-reviewedapplication/pdfhttp://hdl.handle.net/10256/20491http://hdl.handle.net/10256/20491Sensors, 2021, vol. 21, núm. 23, p. 8090Articles publicats (D-ATC)reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)Inglésinfo:eu-repo/semantics/altIdentifier/doi/10.3390/s21238090info:eu-repo/semantics/altIdentifier/eissn/1424-8220RTI2018-096333-B-I00info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-096333-B-I00Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:10256/204912026-05-29T05:05:01Z
dc.title.none.fl_str_mv Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data
title Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data
spellingShingle Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data
Vidal Verdaguer, Joel
Visió per ordinador
Computer vision
Reconeixement de formes (Informàtica)
Pattern recognition systems
Visualització tridimensional (Informàtica)
Three-dimensional display systems
title_short Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data
title_full Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data
title_fullStr Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data
title_full_unstemmed Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data
title_sort Visual attention and color cues for 6d pose estimation on occluded scenarios using rgb-d data
dc.creator.none.fl_str_mv Vidal Verdaguer, Joel
Lin, Chyi Yeu
Martí Marly, Robert
author Vidal Verdaguer, Joel
author_facet Vidal Verdaguer, Joel
Lin, Chyi Yeu
Martí Marly, Robert
author_role author
author2 Lin, Chyi Yeu
Martí Marly, Robert
author2_role author
author
dc.contributor.none.fl_str_mv Agencia Estatal de Investigación
dc.subject.none.fl_str_mv Visió per ordinador
Computer vision
Reconeixement de formes (Informàtica)
Pattern recognition systems
Visualització tridimensional (Informàtica)
Three-dimensional display systems
topic Visió per ordinador
Computer vision
Reconeixement de formes (Informàtica)
Pattern recognition systems
Visualització tridimensional (Informàtica)
Three-dimensional display systems
description Recently, 6D pose estimation methods have shown robust performance on highly cluttered scenes and different illumination conditions. However, occlusions are still challenging, with recognition rates decreasing to less than 10% for half-visible objects in some datasets. In this paper, we propose to use top-down visual attention and color cues to boost performance of a state-of-the-art method on occluded scenarios. More specifically, color information is employed to detect potential points in the scene, improve feature-matching, and compute more precise fitting scores. The proposed method is evaluated on the Linemod occluded (LM-O), TUD light (TUD-L), Tejani (IC-MI) and Doumanoglou (IC-BIN) datasets, as part of the SiSo BOP benchmark, which includes challenging highly occluded cases, illumination changing scenarios, and multiple instances. The method is analyzed and discussed for different parameters, color spaces and metrics. The presented results show the validity of the proposed approach and their robustness against illumination changes and multiple instance scenarios, specially boosting the performance on relatively high occluded cases. The proposed solution provides an absolute improvement of up to 30% for levels of occlusion between 40% to 50%, outperforming other approaches with a best overall recall of 71% for the LM-O, 92% for TUD-L, 99.3% for IC-MI and 97.5% for IC-BIN
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
peer-reviewed
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10256/20491
http://hdl.handle.net/10256/20491
url http://hdl.handle.net/10256/20491
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.3390/s21238090
info:eu-repo/semantics/altIdentifier/eissn/1424-8220
RTI2018-096333-B-I00
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-096333-B-I00
dc.rights.none.fl_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI (Multidisciplinary Digital Publishing Institute)
publisher.none.fl_str_mv MDPI (Multidisciplinary Digital Publishing Institute)
dc.source.none.fl_str_mv Sensors, 2021, vol. 21, núm. 23, p. 8090
Articles publicats (D-ATC)
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_ 1869413092134223872
score 15.812455

Similares en LA Referencia