ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation

Semantic segmentation is a challenging task that addresses most of the perception needs of intelligent vehicles (IVs) in an unified way. Deep neural networks excel at this task, as they can be trained end-to-end to accurately classify multiple object categories in an image at pixel level. However, a...

ver descrição completa

Detalhes bibliográficos
Autores: Romera Carmena, Eduardo|||0000-0001-6250-6160, Álvarez López, José Mª, Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077, Arroyo Contera, Roberto
Formato: artículo
Fecha de publicación:2018
País:España
Recursos:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/43227
Acesso em linha:http://hdl.handle.net/10017/43227
https://dx.doi.org/10.1109/TITS.2017.2750080
Access Level:acceso abierto
Palavra-chave:Intelligent vehicles
Scene understanding
Realtime
Semantic segmentation
Deep Learning
Residual layers
Electrónica
Electronics
id ES_b22ccef193c78ca8a75e12b07088c8b6
oai_identifier_str oai:ebuah.uah.es:10017/43227
network_acronym_str ES
network_name_str España
repository_id_str
spelling ERFNet: efficient residual factorized ConvNet for real-time semantic segmentationRomera Carmena, Eduardo|||0000-0001-6250-6160Álvarez López, José MªBergasa Pascual, Luis Miguel|||0000-0002-0087-3077Arroyo Contera, RobertoIntelligent vehiclesScene understandingRealtimeSemantic segmentationDeep LearningResidual layersElectrónicaElectronicsSemantic segmentation is a challenging task that addresses most of the perception needs of intelligent vehicles (IVs) in an unified way. Deep neural networks excel at this task, as they can be trained end-to-end to accurately classify multiple object categories in an image at pixel level. However, a good tradeoff between high quality and computational resources is yet not present in the state-of-the-art semantic segmentation approaches, limiting their application in real vehicles. In this paper, we propose a deep architecture that is able to run in real time while providing accurate semantic segmentation. The core of our architecture is a novel layer that uses residual connections and factorized convolutions in order to remain efficient while retaining remarkable accuracy. Our approach is able to run at over 83 FPS in a single Titan X, and 7 FPS in a Jetson TX1 (embedded device). A comprehensive set of experiments on the publicly available Cityscapes data set demonstrates that our system achieves an accuracy that is similar to the state of the art, while being orders of magnitude faster to compute than other architectures that achieve top precision. The resulting tradeoff makes our model an ideal approach for scene understanding in IV applications. The code is publicly available at: https://github.com/Eromera/erfnet.Ministerio de Economía y CompetitividadComunidad de MadridIEEE20182018-01-01journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10017/43227https://dx.doi.org/10.1109/TITS.2017.2750080reponame:e_Buah Biblioteca Digital Universidad de Alcaláinstname:Universidad de Alcalá (UAH)InglésengMinisterio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 Not available TRA2015-70501-C2-1-R VEHICULO INTELIGENTE PARA PERSONAS MAYORESComunidad de Madrid http://dx.doi.org/10.13039/100012818 Not available S2013%2FMIT-2748 ROBOTICA APLICADA A LA MEJORA DE LA CALIDAD DE VIDA DE LOS CIUDADANOS, FASE IIIopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:ebuah.uah.es:10017/432272026-06-18T11:13:07Z
dc.title.none.fl_str_mv ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation
title ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation
spellingShingle ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation
Romera Carmena, Eduardo|||0000-0001-6250-6160
Intelligent vehicles
Scene understanding
Realtime
Semantic segmentation
Deep Learning
Residual layers
Electrónica
Electronics
title_short ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation
title_full ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation
title_fullStr ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation
title_full_unstemmed ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation
title_sort ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation
dc.creator.none.fl_str_mv Romera Carmena, Eduardo|||0000-0001-6250-6160
Álvarez López, José Mª
Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Arroyo Contera, Roberto
author Romera Carmena, Eduardo|||0000-0001-6250-6160
author_facet Romera Carmena, Eduardo|||0000-0001-6250-6160
Álvarez López, José Mª
Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Arroyo Contera, Roberto
author_role author
author2 Álvarez López, José Mª
Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Arroyo Contera, Roberto
author2_role author
author
author
dc.subject.none.fl_str_mv Intelligent vehicles
Scene understanding
Realtime
Semantic segmentation
Deep Learning
Residual layers
Electrónica
Electronics
topic Intelligent vehicles
Scene understanding
Realtime
Semantic segmentation
Deep Learning
Residual layers
Electrónica
Electronics
description Semantic segmentation is a challenging task that addresses most of the perception needs of intelligent vehicles (IVs) in an unified way. Deep neural networks excel at this task, as they can be trained end-to-end to accurately classify multiple object categories in an image at pixel level. However, a good tradeoff between high quality and computational resources is yet not present in the state-of-the-art semantic segmentation approaches, limiting their application in real vehicles. In this paper, we propose a deep architecture that is able to run in real time while providing accurate semantic segmentation. The core of our architecture is a novel layer that uses residual connections and factorized convolutions in order to remain efficient while retaining remarkable accuracy. Our approach is able to run at over 83 FPS in a single Titan X, and 7 FPS in a Jetson TX1 (embedded device). A comprehensive set of experiments on the publicly available Cityscapes data set demonstrates that our system achieves an accuracy that is similar to the state of the art, while being orders of magnitude faster to compute than other architectures that achieve top precision. The resulting tradeoff makes our model an ideal approach for scene understanding in IV applications. The code is publicly available at: https://github.com/Eromera/erfnet.
publishDate 2018
dc.date.none.fl_str_mv 2018
2018-01-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10017/43227
https://dx.doi.org/10.1109/TITS.2017.2750080
url http://hdl.handle.net/10017/43227
https://dx.doi.org/10.1109/TITS.2017.2750080
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 Not available TRA2015-70501-C2-1-R VEHICULO INTELIGENTE PARA PERSONAS MAYORES
Comunidad de Madrid http://dx.doi.org/10.13039/100012818 Not available S2013%2FMIT-2748 ROBOTICA APLICADA A LA MEJORA DE LA CALIDAD DE VIDA DE LOS CIUDADANOS, FASE III
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:e_Buah Biblioteca Digital Universidad de Alcalá
instname:Universidad de Alcalá (UAH)
instname_str Universidad de Alcalá (UAH)
reponame_str e_Buah Biblioteca Digital Universidad de Alcalá
collection e_Buah Biblioteca Digital Universidad de Alcalá
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417031971897344
score 15,301603

Registos relacionados