Real-time semantic segmentation for fisheye urban driving images based on ERFNet

The interest in fisheye cameras has recently risen in the autonomous vehicles field, as they are able to reduce the complexity of perception systems while improving the management of dangerous driving situations. However, the strong distortion inherent to these cameras makes the usage of conventiona...

Descripción completa

Detalles Bibliográficos
Autores: Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077, Saez Contreras, Álvaro, López Guillén, María Elena, Romera Carmena, Eduardo|||0000-0001-6250-6160, Tradacete Ágreda, Miguel|||0000-0002-9255-8532, Gómez Huélamo, Carlos, Egido Sierra, Javier del
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/43126
Acceso en línea:http://hdl.handle.net/10017/43126
https://dx.doi.org/10.3390/s19030503
Access Level:acceso abierto
Palabra clave:Fisheye
Intelligent vehicles
CNN (Convolutional Neural Network)
Deep Learning
Distortion
Electrónica
Electronics
id ES_e7d0003a7d37d4c2f3107c07fbd375df
oai_identifier_str oai:ebuah.uah.es:10017/43126
network_acronym_str ES
network_name_str España
repository_id_str
spelling Real-time semantic segmentation for fisheye urban driving images based on ERFNetBergasa Pascual, Luis Miguel|||0000-0002-0087-3077Saez Contreras, ÁlvaroLópez Guillén, María ElenaRomera Carmena, Eduardo|||0000-0001-6250-6160Tradacete Ágreda, Miguel|||0000-0002-9255-8532Gómez Huélamo, CarlosEgido Sierra, Javier delFisheyeIntelligent vehiclesCNN (Convolutional Neural Network)Deep LearningDistortionElectrónicaElectronicsThe interest in fisheye cameras has recently risen in the autonomous vehicles field, as they are able to reduce the complexity of perception systems while improving the management of dangerous driving situations. However, the strong distortion inherent to these cameras makes the usage of conventional computer vision algorithms difficult and has prevented the development of these devices. This paper presents a methodology that provides real-time semantic segmentation on fisheye cameras leveraging only synthetic images. Furthermore, we propose some Convolutional Neural Networks (CNN) architectures based on Efficient Residual Factorized Network (ERFNet) that demonstrate notable skills handling distortion and a new training strategy that improves the segmentation on the image borders. Our proposals are compared to similar state-of-the-art works showing an outstanding performance and tested in an unknown real world scenario using a fisheye camera integrated in an open-source autonomous electric car, showing a high domain adaptation capability.Ministerio de Economía y CompetitividadComunidad de MadridDirección General de TráficoMDPI20192019-01-25journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10017/43126https://dx.doi.org/10.3390/s19030503reponame: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 MAYORESDGT Not available SPIP2017-02305Comunidad 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:10017/431262026-06-18T11:13:07Z
dc.title.none.fl_str_mv Real-time semantic segmentation for fisheye urban driving images based on ERFNet
title Real-time semantic segmentation for fisheye urban driving images based on ERFNet
spellingShingle Real-time semantic segmentation for fisheye urban driving images based on ERFNet
Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Fisheye
Intelligent vehicles
CNN (Convolutional Neural Network)
Deep Learning
Distortion
Electrónica
Electronics
title_short Real-time semantic segmentation for fisheye urban driving images based on ERFNet
title_full Real-time semantic segmentation for fisheye urban driving images based on ERFNet
title_fullStr Real-time semantic segmentation for fisheye urban driving images based on ERFNet
title_full_unstemmed Real-time semantic segmentation for fisheye urban driving images based on ERFNet
title_sort Real-time semantic segmentation for fisheye urban driving images based on ERFNet
dc.creator.none.fl_str_mv Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Saez Contreras, Álvaro
López Guillén, María Elena
Romera Carmena, Eduardo|||0000-0001-6250-6160
Tradacete Ágreda, Miguel|||0000-0002-9255-8532
Gómez Huélamo, Carlos
Egido Sierra, Javier del
author Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
author_facet Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Saez Contreras, Álvaro
López Guillén, María Elena
Romera Carmena, Eduardo|||0000-0001-6250-6160
Tradacete Ágreda, Miguel|||0000-0002-9255-8532
Gómez Huélamo, Carlos
Egido Sierra, Javier del
author_role author
author2 Saez Contreras, Álvaro
López Guillén, María Elena
Romera Carmena, Eduardo|||0000-0001-6250-6160
Tradacete Ágreda, Miguel|||0000-0002-9255-8532
Gómez Huélamo, Carlos
Egido Sierra, Javier del
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Fisheye
Intelligent vehicles
CNN (Convolutional Neural Network)
Deep Learning
Distortion
Electrónica
Electronics
topic Fisheye
Intelligent vehicles
CNN (Convolutional Neural Network)
Deep Learning
Distortion
Electrónica
Electronics
description The interest in fisheye cameras has recently risen in the autonomous vehicles field, as they are able to reduce the complexity of perception systems while improving the management of dangerous driving situations. However, the strong distortion inherent to these cameras makes the usage of conventional computer vision algorithms difficult and has prevented the development of these devices. This paper presents a methodology that provides real-time semantic segmentation on fisheye cameras leveraging only synthetic images. Furthermore, we propose some Convolutional Neural Networks (CNN) architectures based on Efficient Residual Factorized Network (ERFNet) that demonstrate notable skills handling distortion and a new training strategy that improves the segmentation on the image borders. Our proposals are compared to similar state-of-the-art works showing an outstanding performance and tested in an unknown real world scenario using a fisheye camera integrated in an open-source autonomous electric car, showing a high domain adaptation capability.
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-01-25
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/10017/43126
https://dx.doi.org/10.3390/s19030503
url http://hdl.handle.net/10017/43126
https://dx.doi.org/10.3390/s19030503
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
DGT Not available SPIP2017-02305
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 MDPI
publisher.none.fl_str_mv MDPI
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_ 1869422887190921216
score 15,300719

Similares en LA Referencia