Unlocking the power of autonomous vehicles with deep learning for traffic sign detection

Tools

Baro-Thomas, T., Sadiq, A.S. ORCID: 0000-0002-5746-0257 and Taheir, M.A., 2023. Unlocking the power of autonomous vehicles with deep learning for traffic sign detection. In: Intelligent Computing and Networking: proceedings of IC-ICN 2023. Singapore: Springer. (Forthcoming)

Text
1737200_Sadiq.pdf - Post-print
Restricted to Repository staff only
Download (664kB)

Abstract

This paper presents a comprehensive examination of the use of deep learning, specifically Convolutional Neural Networks (CNN), for the detection and recognition of traffic signs with the aim of improving road safety in autonomous vehicles. Despite the extensive deployment of traffic signs and the significant investments made to reduce the incidence of road accidents, the high cost of smart vehicles equipped with these technologies remains a barrier to widespread adoption. The study takes an academic approach to evaluate the level of confidence in prediction and performance using CNN for the detection and recognition of traffic signs and provides recommendations for improvement. The paper aims to further the understanding of the use of deep learning in road safety for autonomous vehicles and to address the challenges associated with existing methods, including issues with accuracy, computational complexity, and real-time performance. By exploring the potential of CNN for the detection and recognition of traffic signs, the paper seeks to contribute to the development of more effective road safety technologies for autonomous vehicles and to improve the overall safety of drivers and other road users.

Item Type:

Chapter in book

Description:

Paper presented at the 14th International Conference on Intelligent Computing and Networking (IC-ICN 2023), India, 24-25 February 2023.

Creators:

Baro-Thomas, T., Sadiq, A.S. and Taheir, M.A.

Publisher:

Springer

Place of Publication:

Singapore

Date:

15 February 2023