Stop the Bus!: computer vision for automatic recognition of urban bus lines

Autores
Maina, Hernán J.; Sánchez, Jorge A.
Año de publicación
2020
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
In the present work, the problem of the detection and the recognition of bus line numbers of public transport in the city of C ordoba is addressed, using images obtained by standard mobile devices. The goal of this project is the exploitation of computer vision techniques and the analysis of images for the generation of a tool that potentially allows people with visual impairments to be assisted. To achieve this, a modular architecture based on object detectors and optical character recognition is presented and evaluated, mainly constituted by two stages: one for the detection buses, based on the SSD-MobileNet object detection model; and another, responsible for line number recognition, where the EAST and OCR-Tesseract text detection and recognition models are tested, respectively. With a maximum probability of recognition of 62% in a simple image; over an image sequence, the nal system was able to correctly recognize the bus line in 72% of the cases tested.
Sociedad Argentina de Informática
Materia
Ciencias Informáticas
Computer vision
Object detection
Text recognition
Text detection
Buses
Visual impairment
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/3.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/114923
Acceder
id SEDICI_fe060d58c108aa5039f2139fcd31e587
oai_identifier_str oai:sedici.unlp.edu.ar:10915/114923
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Stop the Bus!: computer vision for automatic recognition of urban bus linesMaina, Hernán J.Sánchez, Jorge A.Ciencias InformáticasComputer visionObject detectionText recognitionText detectionBusesVisual impairmentIn the present work, the problem of the detection and the recognition of bus line numbers of public transport in the city of C ordoba is addressed, using images obtained by standard mobile devices. The goal of this project is the exploitation of computer vision techniques and the analysis of images for the generation of a tool that potentially allows people with visual impairments to be assisted. To achieve this, a modular architecture based on object detectors and optical character recognition is presented and evaluated, mainly constituted by two stages: one for the detection buses, based on the SSD-MobileNet object detection model; and another, responsible for line number recognition, where the EAST and OCR-Tesseract text detection and recognition models are tested, respectively. With a maximum probability of recognition of 62% in a simple image; over an image sequence, the nal system was able to correctly recognize the bus line in 72% of the cases tested.Sociedad Argentina de Informática2020-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf128-141http://sedici.unlp.edu.ar/handle/10915/114923enginfo:eu-repo/semantics/altIdentifier/url/http://49jaiio.sadio.org.ar/pdfs/asai/ASAI-10.pdfinfo:eu-repo/semantics/altIdentifier/issn/2451-7585info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/3.0/Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-11-12T10:51:09Zoai:sedici.unlp.edu.ar:10915/114923Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-11-12 10:51:09.722SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Stop the Bus!: computer vision for automatic recognition of urban bus lines
title Stop the Bus!: computer vision for automatic recognition of urban bus lines
spellingShingle Stop the Bus!: computer vision for automatic recognition of urban bus lines
Maina, Hernán J.
Ciencias Informáticas
Computer vision
Object detection
Text recognition
Text detection
Buses
Visual impairment
title_short Stop the Bus!: computer vision for automatic recognition of urban bus lines
title_full Stop the Bus!: computer vision for automatic recognition of urban bus lines
title_fullStr Stop the Bus!: computer vision for automatic recognition of urban bus lines
title_full_unstemmed Stop the Bus!: computer vision for automatic recognition of urban bus lines
title_sort Stop the Bus!: computer vision for automatic recognition of urban bus lines
dc.creator.none.fl_str_mv Maina, Hernán J.
Sánchez, Jorge A.
author Maina, Hernán J.
author_facet Maina, Hernán J.
Sánchez, Jorge A.
author_role author
author2 Sánchez, Jorge A.
author2_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
Computer vision
Object detection
Text recognition
Text detection
Buses
Visual impairment
topic Ciencias Informáticas
Computer vision
Object detection
Text recognition
Text detection
Buses
Visual impairment
dc.description.none.fl_txt_mv In the present work, the problem of the detection and the recognition of bus line numbers of public transport in the city of C ordoba is addressed, using images obtained by standard mobile devices. The goal of this project is the exploitation of computer vision techniques and the analysis of images for the generation of a tool that potentially allows people with visual impairments to be assisted. To achieve this, a modular architecture based on object detectors and optical character recognition is presented and evaluated, mainly constituted by two stages: one for the detection buses, based on the SSD-MobileNet object detection model; and another, responsible for line number recognition, where the EAST and OCR-Tesseract text detection and recognition models are tested, respectively. With a maximum probability of recognition of 62% in a simple image; over an image sequence, the nal system was able to correctly recognize the bus line in 72% of the cases tested.
Sociedad Argentina de Informática
description In the present work, the problem of the detection and the recognition of bus line numbers of public transport in the city of C ordoba is addressed, using images obtained by standard mobile devices. The goal of this project is the exploitation of computer vision techniques and the analysis of images for the generation of a tool that potentially allows people with visual impairments to be assisted. To achieve this, a modular architecture based on object detectors and optical character recognition is presented and evaluated, mainly constituted by two stages: one for the detection buses, based on the SSD-MobileNet object detection model; and another, responsible for line number recognition, where the EAST and OCR-Tesseract text detection and recognition models are tested, respectively. With a maximum probability of recognition of 62% in a simple image; over an image sequence, the nal system was able to correctly recognize the bus line in 72% of the cases tested.
publishDate 2020
dc.date.none.fl_str_mv 2020-10
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/114923
url http://sedici.unlp.edu.ar/handle/10915/114923
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://49jaiio.sadio.org.ar/pdfs/asai/ASAI-10.pdf
info:eu-repo/semantics/altIdentifier/issn/2451-7585
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/3.0/
Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/3.0/
Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)
dc.format.none.fl_str_mv application/pdf
128-141
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1848605609252880384
score 12.976206

Publicaciones similares