Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems

This paper presents an efficient two-stage traffic sign recognition system. First, 3D point cloud data is acquired by a LINX Mobile Mapper system and processed to automatically detect traffic signs based on their retro-reflective material. Then, classification is carried out over the point cloud pro...

Descripción completa

Detalles Bibliográficos
Autores: Arcos García, Álvaro, Soilán, Mario, Álvarez García, Juan Antonio, Riveiro, Belén
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2017
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/125642
Acceso en línea:https://hdl.handle.net/11441/125642
https://doi.org/10.1016/j.eswa.2017.07.042
Access Level:acceso abierto
Palabra clave:Mobile mapping sensors
Point cloud
Traffic sign
Deep learning
Convolutional neural network
Spatial transformer network
id ES_c8a8dfbf7e1f61775886ba7bd782c5a9
oai_identifier_str oai:idus.us.es:11441/125642
network_acronym_str ES
network_name_str España
repository_id_str
spelling Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systemsArcos García, ÁlvaroSoilán, MarioÁlvarez García, Juan AntonioRiveiro, BelénMobile mapping sensorsPoint cloudTraffic signDeep learningConvolutional neural networkSpatial transformer networkThis paper presents an efficient two-stage traffic sign recognition system. First, 3D point cloud data is acquired by a LINX Mobile Mapper system and processed to automatically detect traffic signs based on their retro-reflective material. Then, classification is carried out over the point cloud projection on RGB images applying a Deep Neural Network which comprises convolutional and spatial transformer layers. This network is evaluated in three European traffic sign datasets. On the GTSRB, it outperforms previous state-of-the-art published works and achieves top-1 rank with an accuracy of 99.71%. Furthermore, a Spanish traffic sign recognition dataset is released.Ministerio de Economía y Competitividad TIN2013-46801-C4-1-RMinisterio de Economia y Competitividad TIN2013-46801-C4-4-RElsevierLenguajes y Sistemas InformáticosTIC134: Sistemas InformáticosMinisterio de Economía y Competitividad (MINECO). España2017info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/125642https://doi.org/10.1016/j.eswa.2017.07.042reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésExpert Systems With Applications, 89, 286-295.TIN2013-46801-C4-1-RTIN2013-46801-C4-4-Rhttps://www.sciencedirect.com/science/article/pii/S0957417417305195info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1256422026-06-17T12:51:07Z
dc.title.none.fl_str_mv Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems
title Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems
spellingShingle Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems
Arcos García, Álvaro
Mobile mapping sensors
Point cloud
Traffic sign
Deep learning
Convolutional neural network
Spatial transformer network
title_short Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems
title_full Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems
title_fullStr Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems
title_full_unstemmed Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems
title_sort Exploiting synergies of mobile mapping sensors and deep learning for traffic sign recognition systems
dc.creator.none.fl_str_mv Arcos García, Álvaro
Soilán, Mario
Álvarez García, Juan Antonio
Riveiro, Belén
author Arcos García, Álvaro
author_facet Arcos García, Álvaro
Soilán, Mario
Álvarez García, Juan Antonio
Riveiro, Belén
author_role author
author2 Soilán, Mario
Álvarez García, Juan Antonio
Riveiro, Belén
author2_role author
author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
TIC134: Sistemas Informáticos
Ministerio de Economía y Competitividad (MINECO). España
dc.subject.none.fl_str_mv Mobile mapping sensors
Point cloud
Traffic sign
Deep learning
Convolutional neural network
Spatial transformer network
topic Mobile mapping sensors
Point cloud
Traffic sign
Deep learning
Convolutional neural network
Spatial transformer network
description This paper presents an efficient two-stage traffic sign recognition system. First, 3D point cloud data is acquired by a LINX Mobile Mapper system and processed to automatically detect traffic signs based on their retro-reflective material. Then, classification is carried out over the point cloud projection on RGB images applying a Deep Neural Network which comprises convolutional and spatial transformer layers. This network is evaluated in three European traffic sign datasets. On the GTSRB, it outperforms previous state-of-the-art published works and achieves top-1 rank with an accuracy of 99.71%. Furthermore, a Spanish traffic sign recognition dataset is released.
publishDate 2017
dc.date.none.fl_str_mv 2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/125642
https://doi.org/10.1016/j.eswa.2017.07.042
url https://hdl.handle.net/11441/125642
https://doi.org/10.1016/j.eswa.2017.07.042
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Expert Systems With Applications, 89, 286-295.
TIN2013-46801-C4-1-R
TIN2013-46801-C4-4-R
https://www.sciencedirect.com/science/article/pii/S0957417417305195
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419304686977024
score 15,301603

Similares en LA Referencia