Title: Road signs recognition: state-of-the-art and perspectives

Authors: Btissam Bousarhane; Saloua Bensiali; Driss Bouzidi

Addresses: Smart Systems Laboratory (SSL), National School of Computer Science and Systems Analysis ENSIAS, Mohammed V University, Rabat, Morocco ' Department of Applied Statistics and Computer Science, Hassan II Institute of Agronomy and Veterinary Medicine, P.O. Box 6202, Morocco ' Smart Systems Laboratory (SSL), National School of Computer Science and Systems Analysis ENSIAS, Mohammed V University, Rabat, Morocco

Abstract: Making cars safer is a crucial element of saving lives on roads. In case of inattention or distraction, drivers need a performant system that is capable of assisting and alerting them when a road sign appears in their field of vision. To create such type of systems, we need to know first the major difficulties that still face traffic signs recognition, as presented in the first and second sections of this paper. We should also study the different methods proposed by researchers to overcome each of these challenges, as proposed in the third section. Evaluation metrics and criteria for proving the effectiveness of these approaches represents also an important element which section three of this article presents. Ameliorating the existing methods is crucial to ensure the effectiveness of the recognition process, especially by using deep learning algorithms and optimisation techniques, as discussed in the last section of this paper.

Keywords: road signs recognition; detection; classification; tracking; machine learning; deep learning; evaluation datasets; evaluation metrics; optimisation.

DOI: 10.1504/IJDATS.2021.114672

International Journal of Data Analysis Techniques and Strategies, 2021 Vol.13 No.1/2, pp.128 - 150

Received: 09 Nov 2018
Accepted: 03 May 2019

Published online: 23 Apr 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article