Deep Learning for Traffic Sign Recognition in Autonomous Vehicles: Challenges, Trends and Future Directions

Year : 2026 | Volume : 13 | Issue : 02 | Page : 1 7
By

Pradip S. Togrikar,

Pritish M. Vibhute,

  1. Research Scholar, Department of Electronics & Computer Engineering, Sanjivani University, Maharashtra, India
  2. Associate Professor, Department of Electronics & Computer Engineering, Sanjivani University, Maharashtra, India

Abstract

Traffic Sign Recognition (TSR) serves as a fundamental task in the domain of autonomous vehicles (AVs), enabling systems to detect, classify, and respond to road signs with the level of accuracy and speed required for safe navigation. As AV technology continues to evolve, the role of intelligent TSR systems has become increasingly vital. Traditional computer vision techniques, while foundational, often fall short under challenging real-world conditions such as poor lighting, occlusion, and environmental variability. The emergence of deep learning has significantly transformed TSR, offering robust feature extraction and superior generalization capabilities. Convolutional Neural Networks (CNNs) have been widely adopted for image classification tasks, while real-time object detection frameworks like YOLO (You Only Look Once) have enabled fast and accurate sign localization. More recently, Vision Transformers (ViTs) have shown promise in capturing global context and improving performance in complex scenarios. Despite these advances, several challenges persist. Deep learning models can be sensitive to adversarial attacks, require large annotated datasets, and often struggle in edge cases involving small or distorted signs. This review critically evaluates state-of-the-art deep learning approaches for TSR, highlighting their strengths and limitations. Furthermore, it discusses emerging trends such as transfer learning, self-supervised learning, data augmentation, and the integration of multimodal data from additional sensors. Future directions are explored with an emphasis on enhancing robustness, interpretability, and real-time capabilities of TSR systems in autonomous vehicles. By consolidating current research and outlining key challenges, this study aims to provide a foundation for future advancements in intelligent traffic sign recognition.

Keywords: Traffic sign recognition, deep learning, YOLO, vision transformers, autonomous vehicles, intelligent transportation systems

[This article belongs to Journal of Advancements in Robotics ]

How to cite this article: Pradip S. Togrikar, Pritish M. Vibhute. Deep Learning for Traffic Sign Recognition in Autonomous Vehicles: Challenges, Trends and Future Directions. Journal of Advancements in Robotics. 2026; 13(02):1-7.
How to cite this URL: Pradip S. Togrikar, Pritish M. Vibhute. Deep Learning for Traffic Sign Recognition in Autonomous Vehicles: Challenges, Trends and Future Directions. Journal of Advancements in Robotics. 2026; 13(02):1-7. Available from: https://journals.stmjournals.com/joarb/article=2026/view=259256

References

  1. Triki N, Karray M, Ksantini M. A real-time traffic sign recognition method using a new attention-based deep convolutional neural network for smart vehicles. Appl Sci (Basel). 2023;13(8):4793.
  2. Liang T, Bao H, Pan W, Pan F. Traffic sign detection via improved Sparse R-CNN for autonomous vehicles. J Adv Transp. 2022;2022:3825532.
  3. Kanagaraj N, Hicks D, Goyal A, Tiwari S, Singh G. Deep learning using computer vision in self-driving cars for lane and traffic sign detection. Int J Syst Assur Eng Manag. 2021;12(6):1011-25.
  4. Xie K, Zhang Z, Li B, Kang J, Niyato D, Xie S, et al. Efficient federated learning with spike neural networks for traffic sign recognition. IEEE Trans Veh Technol. 2022;71(9):9980-92.
  5. Dewi C, Chen RC, Jiang X, Yu H. Deep convolutional neural network for enhancing traffic sign recognition developed on YOLO v4. Multimed Tools Appl. 2022;81(26):37821-45.
  6. Güney E, Bayılmış C, Çakan B. An implementation of real-time traffic signs and road objects detection based on mobile GPU platforms. IEEE Access. 2022;10:86191-203.
  7. Singh K, Malik N. CNN based approach for traffic sign recognition system. Adv J Grad Res. 2022;11(1):23-33.
  8. Ahmed S, Kamal U, Hasan MK. DFR-TSD: a deep learning based framework for robust traffic sign detection under challenging weather conditions. IEEE Trans Intell Transp Syst. 2022;23(6):5150-62.
  9. Antonio GP, Maria-Dolores C. Multi-agent deep reinforcement learning to manage connected autonomous vehicles at tomorrow’s intersections. IEEE Trans Veh Technol. 2022;71(7):7033-43.
  10. Wan J, Ding W, Zhu H, Xia M, Huang Z, Tian L, et al. An efficient small traffic sign detection method based on YOLOv3. J Signal Process Syst. 2021;93(8):899-911.
  11. Bathla G, Bhadane K, Singh RK, Kumar R, Aluvalu R, Krishnamurthi R, et al. Autonomous vehicles and intelligent automation: applications, challenges, and opportunities. Mob Inf Syst. 2022;2022:7632892.
  12. Dewi C, Chen RC, Liu YT, Tai SK. Synthetic data generation using DCGAN for improved traffic sign recognition. Neural Comput Appl. 2022;34(24):21465-80.
  13. Hasanujjaman M, Chowdhury MZ, Jang YM. Sensor fusion in autonomous vehicle with traffic surveillance camera system: detection, localization, and AI networking. Sensors (Basel). 2023;23(6):3335.
  14. Chib PS, Singh P. Recent advancements in end-to-end autonomous driving using deep learning: a survey. IEEE Trans Intell Veh. 2024;9(1):103-18.
  15. Girdhar M, Hong J, Moore J. Cybersecurity of autonomous vehicles: a systematic literature review of adversarial attacks and defense models. IEEE Open J Veh Technol. 2023;4:417-37.
  16. Chen L, Teng S, Li B, Na X, Li Y, Li Z, et al. Milestones in autonomous driving and intelligent vehicles—Part II: perception and planning. IEEE Trans Syst Man Cybern Syst. 2023;53(10):6401-15.
  17. Zakaria NJ, Shapiai MI, Abd Ghani R, Yassin MN, Ibrahim MZ, Wahid N. Lane detection in autonomous vehicles: a systematic review. IEEE Access. 2023;11:3729-65.
  18. Parekh D, Poddar N, Rajpurkar A, Chahal M, Kumar N, Joshi GP, et al. A review on autonomous vehicles: progress, methods and challenges. Electronics (Basel). 2022;11(14):2162.
  19. Deng Y, Zhang T, Lou G, Zheng X, Jin J, Han QL. Deep learning-based autonomous driving systems: a survey of attacks and defenses. IEEE Trans Ind Inform. 2021;17(12):7897-912.
  20. Wang S, Li C, Ng DW, Eldar YC, Poor HV, Hao Q, et al. Federated deep learning meets autonomous vehicle perception: design and verification. IEEE Netw. 2023;37(3):16-25.
  21. Köylü F. A comparative analysis of YOLO-based traffic sign detections with a novel Turkish traffic sign dataset. IEEE Access. 2026;14:7744-63.
  22. Mani MK, Rajagopal S, Kavitha D, Ramachandran S. Deep learning-based traffic sign detection and recognition for autonomous vehicles. In: Digital twin and blockchain for smart cities. 2024. p. 407-28.
  23. Kozhamkulova Z, Bidakhmet Z, Vorogushina M, Tashenova Z, Tussupova B, Nurlybaeva E, et al. Development of deep learning models for traffic sign recognition in autonomous vehicles. Int J Adv Comput Sci Appl. 2024;15(5).
  24. Sah CK, Shaw AK, Lian X, Baig AS, Wen T, Jiang K, et al. Advancing autonomous vehicle intelligence: deep learning and multimodal LLM for traffic sign recognition and robust lane detection [Preprint]. 2025. arXiv:2503.06313.
  25. Mingwin S, Shisu Y, Wanwag Y, Huing S. Revolutionizing traffic sign recognition: unveiling the potential of vision transformers [Preprint]. 2024. arXiv:2404.19066.
  26. Omidian F, Abdi A. Appsign: multi-level approximate computing for real-time traffic sign recognition in autonomous vehicles [Preprint]. 2024. arXiv:2411.10988.
  27. Toshniwal D, Loya S, Khot A, Marda Y. Optimized detection and classification on GTRSB: advancing traffic sign recognition with convolutional neural networks [Preprint]. 2024. arXiv:2403.08283.
  28. Patel V, Mehta J, Iyer S, Sharma AK. Traffic sign recognition using deep learning. Int J Veh Auton Syst. 2022;16(2-4):97-107.
  29. Naik UP, Rajesh V, Kumar R. Implementation of YOLOv4 algorithm for multiple object detection in image and video dataset using deep learning and artificial intelligence for urban traffic video surveillance application. In: 2021 Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT); 2021 Sep 15. IEEE; 2021. p. 1-6.
  30. Lim XR, Lee CP, Lim KM, Ong TS. Enhanced traffic sign recognition with ensemble learning. J Sens Actuator Netw. 2023;12(2):33.
Regular Issue Subscription Review Article
Volume 13
Issue 02
Received 19/01/2026
Accepted 03/07/2026
Published 06/07/2026
Publication Time 168 Days

Login

My IP

PlumX Metrics

Support