Home / Current Issue / Paper 1712930
A Literature Review on AI-Based Traffic Sign Recognition Systems
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence, Computer Vision and Deep
DOI: https://doi.org/10.64388/IREV9I6-1712930
Abstract
Traffic Sign Recognition (TSR) is a fundamental component of intelligent transportation systems and Advanced Driver Assistance Systems (ADAS). Accurate detection and classification of traffic signs enable safer driving, reduce human error, and support autonomous vehicle decision-making. Recent advancements in artificial intelligence, particularly deep learning and computer vision, have significantly improved TSR performance. Techniques such as Convolutional Neural Networks (CNNs), attention-based architectures, hybrid classifiers, and lightweight transformer models enable real-time recognition even on embedded platforms. However, real-world deployment still faces challenges including environmental variability, occlusion, sign degradation, regional diversity, and computational constraints. This manuscript provides a detailed review of recent AI-based TSR approaches, analyzes their advantages and limitations, identifies research gaps, and outlines future directions toward robust, scalable, and real-time TSR systems.
Keywords
Traffic Sign Recognition, Artificial Intelligence, Deep Learning, ADAS, Computer Vision, Autonomous Vehicles
How to cite this paper
@article{1712930,
author = {Shivangi Gupta, Priyanka Pandey, Trupti Hubli, Impana S},
title = {A Literature Review on AI-Based Traffic Sign Recognition Systems},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {6},
pages = {1374-1375},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1712930.pdf},
abstract = {Traffic Sign Recognition (TSR) is a fundamental component of intelligent transportation systems and Advanced Driver Assistance Systems (ADAS). Accurate detection and classification of traffic signs enable safer driving, reduce human error, and support autonomous vehicle decision-making. Recent advancements in artificial intelligence, particularly deep learning and computer vision, have significantly improved TSR performance. Techniques such as Convolutional Neural Networks (CNNs), attention-based architectures, hybrid classifiers, and lightweight transformer models enable real-time recognition even on embedded platforms. However, real-world deployment still faces challenges including environmental variability, occlusion, sign degradation, regional diversity, and computational constraints. This manuscript provides a detailed review of recent AI-based TSR approaches, analyzes their advantages and limitations, identifies research gaps, and outlines future directions toward robust, scalable, and real-time TSR systems.},
keywords = {Traffic Sign Recognition, Artificial Intelligence, Deep Learning, ADAS, Computer Vision, Autonomous Vehicles},
month = {December},
doi = {https://doi.org/10.64388/IREV9I6-1712930}
}