Traffic sign segmentation and classification using statistical learning methods

Traffic signs are an essential part of any circulation system, and failure detection by the driver may significantly increase the accident risk. Currently, automatic traffic sign detection systems still have some performance limitations, specially for achromatic signs and variable lighting condition...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor Principal: Rojo ?lvarez, Jos? Luis
Formato: Artículos
Lenguaje:eng
Publicado: 2016
Materias:
Acceso en línea:http://repositorio.educacionsuperior.gob.ec/handle/28000/3033
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:localhost:28000-3033
recordtype dspace
spelling oai:localhost:28000-30332017-04-05T21:31:25Z Traffic sign segmentation and classification using statistical learning methods Rojo ?lvarez, Jos? Luis DRIVER SUPPORT SYSTEM TRAFFIC SIGN DETECTION CHROMATIC AND ACHROMATIC SEGMENTATIONS MACHINE LEARNING TECHNIQUES Traffic signs are an essential part of any circulation system, and failure detection by the driver may significantly increase the accident risk. Currently, automatic traffic sign detection systems still have some performance limitations, specially for achromatic signs and variable lighting conditions. In this work, we propose an automatic traffic-sign detection method capable of detecting both chromatic and achromatic signs, while taking into account rotations, scale changes, shifts, partial deformations, and shadows. The proposed system is divided into three stages: (1) segmentation of chromatic and achromatic scene elements using L?a?b?L?a?b? and HSI spaces, where two machine learning techniques (k-Nearest Neighbors and Support Vector Machines) are benchmarked; (2) post-processing in order to discard non-interest regions, to connect fragmented signs, and to separate signs located at the same post; and (3) sign-shape classification by using Fourier Descriptors, which yield significant advantage in comparison to other contour-based methods, and subsequent shape recognition with machine learning techniques. Experiments with two databases of real-world images captured with different cameras yielded a sign detection rate of about 97% with a false alarm rate between 3% and 4%, depending on the database. Our method can be readily used for maintenance, inventory, or driver support system applications. Universidad De Las Fuerzas Armadas http://www.sciencedirect.com/science/article/pii/S0925231214015598 2016-11-09T16:57:23Z 2016-11-09T16:57:23Z 2015 article Lillo Castellano, J.M. et al.. (2015). Traffic sign segmentation and classification using statistical learning methods. Neurocomputing Volume 153. pp. 286?299 0925-2312 http://repositorio.educacionsuperior.gob.ec/handle/28000/3033 eng restrictedAccess pp. 286?299
institution SENESCYT
collection Repositorio SENESCYT
biblioteca Biblioteca Senescyt
language eng
format Artículos
topic DRIVER SUPPORT SYSTEM
TRAFFIC SIGN DETECTION
CHROMATIC AND ACHROMATIC SEGMENTATIONS
MACHINE LEARNING TECHNIQUES
spellingShingle DRIVER SUPPORT SYSTEM
TRAFFIC SIGN DETECTION
CHROMATIC AND ACHROMATIC SEGMENTATIONS
MACHINE LEARNING TECHNIQUES
Rojo ?lvarez, Jos? Luis
Traffic sign segmentation and classification using statistical learning methods
description Traffic signs are an essential part of any circulation system, and failure detection by the driver may significantly increase the accident risk. Currently, automatic traffic sign detection systems still have some performance limitations, specially for achromatic signs and variable lighting conditions. In this work, we propose an automatic traffic-sign detection method capable of detecting both chromatic and achromatic signs, while taking into account rotations, scale changes, shifts, partial deformations, and shadows. The proposed system is divided into three stages: (1) segmentation of chromatic and achromatic scene elements using L?a?b?L?a?b? and HSI spaces, where two machine learning techniques (k-Nearest Neighbors and Support Vector Machines) are benchmarked; (2) post-processing in order to discard non-interest regions, to connect fragmented signs, and to separate signs located at the same post; and (3) sign-shape classification by using Fourier Descriptors, which yield significant advantage in comparison to other contour-based methods, and subsequent shape recognition with machine learning techniques. Experiments with two databases of real-world images captured with different cameras yielded a sign detection rate of about 97% with a false alarm rate between 3% and 4%, depending on the database. Our method can be readily used for maintenance, inventory, or driver support system applications.
author Rojo ?lvarez, Jos? Luis
author_facet Rojo ?lvarez, Jos? Luis
author_sort Rojo ?lvarez, Jos? Luis
title Traffic sign segmentation and classification using statistical learning methods
title_short Traffic sign segmentation and classification using statistical learning methods
title_full Traffic sign segmentation and classification using statistical learning methods
title_fullStr Traffic sign segmentation and classification using statistical learning methods
title_full_unstemmed Traffic sign segmentation and classification using statistical learning methods
title_sort traffic sign segmentation and classification using statistical learning methods
publishDate 2016
url http://repositorio.educacionsuperior.gob.ec/handle/28000/3033
_version_ 1634995102536433664
score 11,871979