Review on Indian traffic sign detection and recognition using deep learning
Keywords:
Indian traffic sign detection, deep learning-based recognition, convolutional neural networks (CNN), intelligent transportation systems (ITS), computer vision in road safetyAbstract
Traffic sign detection and recognition (TSDR) plays a crucial role in intelligent transportation systems (ITS), advanced driver assistance systems (ADAS), and autonomous driving technologies. In the context of India, the development of robust traffic sign recognition systems is particularly challenging due to diverse road conditions, variations in sign design, occlusions, weather conditions, faded or damaged signs, and complex backgrounds. With the rapid advancement of artificial intelligence, deep learning techniques have emerged as powerful tools for automatically detecting and classifying traffic signs with high accuracy. This review paper presents a comprehensive analysis of recent research on Indian traffic sign detection and recognition using deep learning approaches. The study examines various deep learning architectures such as Convolutional Neural Networks (CNN), You Only Look Once (YOLO), Region-Based Convolutional Neural Networks (R-CNN), Faster R-CNN, and Single Shot MultiBox Detector (SSD) that have been applied for traffic sign detection and classification. It also reviews publicly available datasets and Indian-specific traffic sign datasets used for training and evaluation. The paper highlights the advantages of deep learning models in handling complex visual features, real-time detection requirements, and large-scale image datasets compared with traditional machine learning approaches. Furthermore, this review identifies key challenges associated with Indian traffic environments, including inconsistent sign visibility, illumination variations, and limited annotated datasets. The comparative analysis of existing methodologies is presented in terms of accuracy, computational efficiency, and real-time implementation capability. Finally, the paper discusses potential future research directions, including the integration of edge computing, transfer learning, and lightweight deep learning models for efficient deployment in intelligent transportation systems. This review aims to provide researchers and practitioners with a clear understanding of current developments, challenges, and emerging opportunities in Indian traffic sign detection and recognition using deep learning techniques.
References
Megalingam, Rajesh Kannan, et al. "Indian traffic sign detection and recognition using deep learning." International journal of transportation science and technology 12.3 (2023): 683-699.
Latif, G., Alghmgham, D. A., Maheswar, R., Alghazo, J., Sibai, F., & Aly, M. H. (2023). Deep learning in Transportation: Optimized driven deep residual networks for Arabic traffic sign recognition. Alexandria Engineering Journal, 80, 134-143.
Hamza, A. S. S. E. M. L. A. L. I., &Nawal, S. A. E. L. (2024). Traffic sign classification using deep learning comparative study. Procedia Computer Science, 233, 939-949.
Yaamini, H. G., Swathi, K. J., Manohar, N., & Kumar, A. (2025). Lane and traffic sign detection for autonomous vehicles: Addressing challenges on indian road conditions. MethodsX, 14, 103178.
Chen, H., Ali, M. A., Nukman, Y., AbdRazak, B., Turaev, S., Chen, Y., ... &Abdulghafor, R. (2024). Computational methods for automatic traffic signs recognition in autonomous driving on road: A systematic review. Results in Engineering, 24, 103553.
VartakKoli, R. D., & Sharma, A. (2024). A systematic study of traffic sign recognition and obstacle detection in autonomous vehicles. International Journal of Intelligent Unmanned Systems, 12(4), 399-417.
Islam, M. A., &Farid, D. M. (2025). The Bangladesh road traffic sign dataset in real-world images for traffic sign recognition. Data in brief, 60, 111523.
Saxena, S., Dey, S., Shah, M., & Gupta, S. (2024). Traffic sign detection in unconstrained environment using improved YOLOv4. Expert Systems with Applications, 238, 121836.
Olszewski, M., Małysiak-Mrozek, B., Tokarz, K., Pochopień, B., Hung, C. L., Pułka, A., &Mrozek, D. (2025). Effective Detection and Recognition of Traffic Signs with Light Convolutional Neural Networks. Procedia Computer Science, 270, 4469-4478.
Zheng, L., Liang, B., & Jiang, A. (2017, November). Recent advances of deep learning for sign language recognition. In 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) (pp. 1-7). IEEE.
Al-Mahbashi, M., Ahmed, A., Khader, A., Ahmad, S., Damos, M. A., & Abdu, A. (2026). A Robust Vision-Based Framework for Traffic Sign and Light Detection in Automated Driving Systems. Computer Modeling in Engineering & Sciences, 146(1).
Choudhary, P., &Dey, S. (2026). FAIERDet: Fuzzy-based adaptive image enhancement for real-time traffic sign detection and recognition under varying light conditions. Expert Systems with Applications, 295, 128795.
Assiri, M. S., &Selim, M. M. (2025). A swin transformer-driven framework for gesture recognition to assist hearing impaired people by integrating deep learning with secretary bird optimization algorithm. Ain Shams Engineering Journal, 16(6), 103383.
Meshram, K., Saurabh, A., Kharole, V., Mishra, U., Onyelowe, K. C., Kamchoom, V., &Arunachalam, K. P. (2025). Design of an integrated model for pothole detection and repair optimization using multimodal transformers and hybrid deep learning. Case Studies in Construction Materials, e05431.
Assemlali, H., Bouhsissin, S., &Sael, N. (2025). Deep learning-driven CNN model for detection and classification of dynamic obstacles. Green Energy and Intelligent Transportation, 100334.
Downloads
How to Cite
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.




