Real Time Traffic Sign Classification Using Deep Learning

DOI

10.2991/978-94-6463-718-2_80How to use a DOI?

Keywords

Realtime; intelligent transportation systems; ADAS; CNN

Abstract

Traffic sign recognition is a critical component in the improvement of ITS and also the creation of self-driven and partly self-driven motor vehicles and ADAS. Automated traffic sign classification is the process of real-time interpretation of traffic sign displayed so that drivers and vehicles can be informed of the right decision to make. This not only helps in the direction but also plays a great role in enhancing road safety by contributing to the reduction of traffic accident rates. The real-time traffic sign classification technique that is proposed here involves the use of Convolutional Neural Networks (CNNs); a deep learning architecture. CNNs are rather appropriate for image recognition because they contain some mechanisms that allow them to detect some objects in images automatically, including edges, shapes, or patterns. Thus, the high accuracy and robustness of this approach are reached due to training the model on the large and diverse dataset and system’s ability to recognize a large number of traffic signs in different conditions, for example, in different lighting, weather, or in the presence of cluttered roads. This model’s training dataset consists of more than 35,000 images which include 43 classes of traffic signs. The use of a big number of samples from each class enhances the ability of the model to generalize on various traffic signs, enhancing the model’s performance in real conditions. Due to real-time processing capacity, this technique allows the vehicle to observe the environment continuously, identify traffic signs that are relevant and inform the driver or the autonomous system.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - M. Gurupriya
AU  - Abhilash Veluru
AU  - Hruday Venkat
AU  - P. Revanth Varma
AU  - K. C. Rohit
PY  - 2025
DA  - 2025/05/23
TI  - Real Time Traffic Sign Classification Using Deep Learning
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 944
EP  - 953
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_80
DO  - 10.2991/978-94-6463-718-2_80
ID  - Gurupriya2025
ER  -