Real-time object detection and classification of small and similar figures in image processing

Autores
Algorry, Aldo M.; Giles Garcia, Arian; Wolfmann, A Gustavo
Año de publicación
2017
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Fil: Algorry, Aldo M. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: Giles García, Arian. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: Wolfmann, A. Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
In the current work we present an image processing architecture for realtime object detection and classification. We use a combination of the widely known techniques YOLO v2 and Convolutional Neural Network classifiers, obtaining great improvements in the detection level with a minimum loss of performance compared to YOLO v2. We apply this technique in a domain where the objects to be detected are like each other and occupy small areas in the images, as it occurs with video traffic signs domain. With this approach, we achieve real-time video processingcapabilities for a test set of 10 different signs classes. The tests results achieved process time levels faster than widely recognized algorithms, such as Fast R-CNN and Faster R-CNN, so it allows to project its use in real-time object detection.
Fil: Algorry, Aldo M. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: Giles García, Arian. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: Wolfmann, A. Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Otras Ciencias de la Computación e Información
Materia
Traffic Signs
Lightweight CNN
YOLO
Computación
Nivel de accesibilidad
acceso abierto
Condiciones de uso
Repositorio
Repositorio Digital Universitario (UNC)
Institución
Universidad Nacional de Córdoba
OAI Identificador
oai:rdu.unc.edu.ar:11086/556430
Acceder
id RDUUNC_b34c988945b98b9532ab6c2c2c858dbd
oai_identifier_str oai:rdu.unc.edu.ar:11086/556430
network_acronym_str RDUUNC
repository_id_str 2572
network_name_str Repositorio Digital Universitario (UNC)
spelling Real-time object detection and classification of small and similar figures in image processingAlgorry, Aldo M.Giles Garcia, ArianWolfmann, A GustavoTraffic SignsLightweight CNNYOLOComputaciónFil: Algorry, Aldo M. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Fil: Giles García, Arian. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Fil: Wolfmann, A. Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.In the current work we present an image processing architecture for realtime object detection and classification. We use a combination of the widely known techniques YOLO v2 and Convolutional Neural Network classifiers, obtaining great improvements in the detection level with a minimum loss of performance compared to YOLO v2. We apply this technique in a domain where the objects to be detected are like each other and occupy small areas in the images, as it occurs with video traffic signs domain. With this approach, we achieve real-time video processingcapabilities for a test set of 10 different signs classes. The tests results achieved process time levels faster than widely recognized algorithms, such as Fast R-CNN and Faster R-CNN, so it allows to project its use in real-time object detection.Fil: Algorry, Aldo M. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Fil: Giles García, Arian. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Fil: Wolfmann, A. Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Otras Ciencias de la Computación e Información2017info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf9781538626528http://hdl.handle.net/11086/556430enginfo:eu-repo/semantics/openAccessreponame:Repositorio Digital Universitario (UNC)instname:Universidad Nacional de Córdobainstacron:UNC2025-10-23T11:18:33Zoai:rdu.unc.edu.ar:11086/556430Institucionalhttps://rdu.unc.edu.ar/Universidad públicaNo correspondehttp://rdu.unc.edu.ar/oai/snrdoca.unc@gmail.comArgentinaNo correspondeNo correspondeNo correspondeopendoar:25722025-10-23 11:18:33.956Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdobafalse
dc.title.none.fl_str_mv Real-time object detection and classification of small and similar figures in image processing
title Real-time object detection and classification of small and similar figures in image processing
spellingShingle Real-time object detection and classification of small and similar figures in image processing
Algorry, Aldo M.
Traffic Signs
Lightweight CNN
YOLO
Computación
title_short Real-time object detection and classification of small and similar figures in image processing
title_full Real-time object detection and classification of small and similar figures in image processing
title_fullStr Real-time object detection and classification of small and similar figures in image processing
title_full_unstemmed Real-time object detection and classification of small and similar figures in image processing
title_sort Real-time object detection and classification of small and similar figures in image processing
dc.creator.none.fl_str_mv Algorry, Aldo M.
Giles Garcia, Arian
Wolfmann, A Gustavo
author Algorry, Aldo M.
author_facet Algorry, Aldo M.
Giles Garcia, Arian
Wolfmann, A Gustavo
author_role author
author2 Giles Garcia, Arian
Wolfmann, A Gustavo
author2_role author
author
dc.subject.none.fl_str_mv Traffic Signs
Lightweight CNN
YOLO
Computación
topic Traffic Signs
Lightweight CNN
YOLO
Computación
dc.description.none.fl_txt_mv Fil: Algorry, Aldo M. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: Giles García, Arian. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: Wolfmann, A. Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
In the current work we present an image processing architecture for realtime object detection and classification. We use a combination of the widely known techniques YOLO v2 and Convolutional Neural Network classifiers, obtaining great improvements in the detection level with a minimum loss of performance compared to YOLO v2. We apply this technique in a domain where the objects to be detected are like each other and occupy small areas in the images, as it occurs with video traffic signs domain. With this approach, we achieve real-time video processingcapabilities for a test set of 10 different signs classes. The tests results achieved process time levels faster than widely recognized algorithms, such as Fast R-CNN and Faster R-CNN, so it allows to project its use in real-time object detection.
Fil: Algorry, Aldo M. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: Giles García, Arian. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: Wolfmann, A. Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Otras Ciencias de la Computación e Información
description Fil: Algorry, Aldo M. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
publishDate 2017
dc.date.none.fl_str_mv 2017
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv 9781538626528
http://hdl.handle.net/11086/556430
identifier_str_mv 9781538626528
url http://hdl.handle.net/11086/556430
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.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:Repositorio Digital Universitario (UNC)
instname:Universidad Nacional de Córdoba
instacron:UNC
reponame_str Repositorio Digital Universitario (UNC)
collection Repositorio Digital Universitario (UNC)
instname_str Universidad Nacional de Córdoba
instacron_str UNC
institution UNC
repository.name.fl_str_mv Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdoba
repository.mail.fl_str_mv oca.unc@gmail.com
_version_ 1846785308470804480
score 12.982451

Publicaciones similares