Real-time 2D–3D door detection and state classification on a low-power device

Detalhes bibliográficos
Autor(a) principal: Ramôa, João Gaspar
Data de Publicação: 2021
Outros Autores: Lopes, Vasco, Alexandre, Luís, Mogo, Sandra
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.6/12633
Resumo: In this paper, we propose three methods for door state classifcation with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work ofine, in low-powered computers as the Jetson Nano, in real-time with the ability to diferentiate between open, closed and semi-open doors. We use the 3D object classifcation, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classifcation networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classifcation algorithm running in real-time on a low-power device.
id RCAP_32cba5cf67bc4b5c7286383cb4963c7c
oai_identifier_str oai:ubibliorum.ubi.pt:10400.6/12633
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Real-time 2D–3D door detection and state classification on a low-power deviceDoor detectionDoor state classifcationDoor segmentationJetson nano2D–3D Door datasetReal-TimeIn this paper, we propose three methods for door state classifcation with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work ofine, in low-powered computers as the Jetson Nano, in real-time with the ability to diferentiate between open, closed and semi-open doors. We use the 3D object classifcation, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classifcation networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classifcation algorithm running in real-time on a low-power device.uBibliorumRamôa, João GasparLopes, VascoAlexandre, LuísMogo, Sandra2023-01-10T09:44:50Z20212021-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.6/12633eng10.1007/s42452-021-04588-3info: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:RCAAP2024-11-27T12:40:45Zoai:ubibliorum.ubi.pt:10400.6/12633Portal AgregadorONGhttps://www.rcaap.pt/oai/openairemluisa.alvim@gmail.comopendoar:71602024-11-27T12:40:45Repositório 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 Real-time 2D–3D door detection and state classification on a low-power device
title Real-time 2D–3D door detection and state classification on a low-power device
spellingShingle Real-time 2D–3D door detection and state classification on a low-power device
Ramôa, João Gaspar
Door detection
Door state classifcation
Door segmentation
Jetson nano
2D–3D Door dataset
Real-Time
title_short Real-time 2D–3D door detection and state classification on a low-power device
title_full Real-time 2D–3D door detection and state classification on a low-power device
title_fullStr Real-time 2D–3D door detection and state classification on a low-power device
title_full_unstemmed Real-time 2D–3D door detection and state classification on a low-power device
title_sort Real-time 2D–3D door detection and state classification on a low-power device
author Ramôa, João Gaspar
author_facet Ramôa, João Gaspar
Lopes, Vasco
Alexandre, Luís
Mogo, Sandra
author_role author
author2 Lopes, Vasco
Alexandre, Luís
Mogo, Sandra
author2_role author
author
author
dc.contributor.none.fl_str_mv uBibliorum
dc.contributor.author.fl_str_mv Ramôa, João Gaspar
Lopes, Vasco
Alexandre, Luís
Mogo, Sandra
dc.subject.por.fl_str_mv Door detection
Door state classifcation
Door segmentation
Jetson nano
2D–3D Door dataset
Real-Time
topic Door detection
Door state classifcation
Door segmentation
Jetson nano
2D–3D Door dataset
Real-Time
description In this paper, we propose three methods for door state classifcation with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work ofine, in low-powered computers as the Jetson Nano, in real-time with the ability to diferentiate between open, closed and semi-open doors. We use the 3D object classifcation, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classifcation networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classifcation algorithm running in real-time on a low-power device.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-01-01T00:00:00Z
2023-01-10T09:44:50Z
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/10400.6/12633
url http://hdl.handle.net/10400.6/12633
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1007/s42452-021-04588-3
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
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 mluisa.alvim@gmail.com
_version_ 1817549667560325120

Registros relacionados