Partially Connected Neural Networks for an Efficient Classification of Traffic Signs

Road signs recognition plays an important role in improving traffic safety for both drivers and pedestrians. To ensure this recognition, many approaches are proposed by researchers. To overcome the limitations of the existing methods, Deep Learning approaches are used. This type of approaches achiev...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bousarhane Btissam, Bouzidi Driss
Formato:	article
Lenguaje:	EN
Publicado:	FRUCT 2021
Materias:	traffic signs recognition classification deep learning cnns Telecommunication TK5101-6720
Acceso en línea:	https://doaj.org/article/4655cb2fc7214567a7f56846929a716e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4655cb2fc7214567a7f56846929a716e
record_format	dspace
spelling	oai:doaj.org-article:4655cb2fc7214567a7f56846929a716e2021-11-20T15:59:33ZPartially Connected Neural Networks for an Efficient Classification of Traffic Signs2305-72542343-073710.23919/FRUCT53335.2021.9599985https://doaj.org/article/4655cb2fc7214567a7f56846929a716e2021-10-01T00:00:00Zhttps://www.fruct.org/publications/fruct30/files/Bti.pdfhttps://doaj.org/toc/2305-7254https://doaj.org/toc/2343-0737Road signs recognition plays an important role in improving traffic safety for both drivers and pedestrians. To ensure this recognition, many approaches are proposed by researchers. To overcome the limitations of the existing methods, Deep Learning approaches are used. This type of approaches achieves high recognition performances, and is also less sensitive to real world adverse conditions. However, they are in contrast very computationally expensive. From this perspective, the objective of this work is to adopt an approach that aims to reduce the computational complexity of these networks, in order to ensure a fast and efficient classification of traffic signs, especially for low and limited resources environments.Bousarhane BtissamBouzidi DrissFRUCTarticletraffic signsrecognitionclassificationdeep learningcnnsTelecommunicationTK5101-6720ENProceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 30, Iss 1, Pp 16-23 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	traffic signs recognition classification deep learning cnns Telecommunication TK5101-6720
spellingShingle	traffic signs recognition classification deep learning cnns Telecommunication TK5101-6720 Bousarhane Btissam Bouzidi Driss Partially Connected Neural Networks for an Efficient Classification of Traffic Signs
description	Road signs recognition plays an important role in improving traffic safety for both drivers and pedestrians. To ensure this recognition, many approaches are proposed by researchers. To overcome the limitations of the existing methods, Deep Learning approaches are used. This type of approaches achieves high recognition performances, and is also less sensitive to real world adverse conditions. However, they are in contrast very computationally expensive. From this perspective, the objective of this work is to adopt an approach that aims to reduce the computational complexity of these networks, in order to ensure a fast and efficient classification of traffic signs, especially for low and limited resources environments.
format	article
author	Bousarhane Btissam Bouzidi Driss
author_facet	Bousarhane Btissam Bouzidi Driss
author_sort	Bousarhane Btissam
title	Partially Connected Neural Networks for an Efficient Classification of Traffic Signs
title_short	Partially Connected Neural Networks for an Efficient Classification of Traffic Signs
title_full	Partially Connected Neural Networks for an Efficient Classification of Traffic Signs
title_fullStr	Partially Connected Neural Networks for an Efficient Classification of Traffic Signs
title_full_unstemmed	Partially Connected Neural Networks for an Efficient Classification of Traffic Signs
title_sort	partially connected neural networks for an efficient classification of traffic signs
publisher	FRUCT
publishDate	2021
url	https://doaj.org/article/4655cb2fc7214567a7f56846929a716e
work_keys_str_mv	AT bousarhanebtissam partiallyconnectedneuralnetworksforanefficientclassificationoftrafficsigns AT bouzididriss partiallyconnectedneuralnetworksforanefficientclassificationoftrafficsigns
_version_	1718419419718221824

Partially Connected Neural Networks for an Efficient Classification of Traffic Signs

Ejemplares similares