Enhanced YOLOR for Accurate and Real-Time Traffic Sign Detection in Autonomous Driving

Safa Teboulbi; Seifeddine Messaoud; Mohamed Ali Hajjaji; Mohamed Atri; Abdellatif Mtibaa

doi:10.48084/etasr.12102

Authors

Safa Teboulbi Laboratory of Systems Integration & Emerging Energies, National Engineering School of Sfax, Sfax University, Tunisia | Higher Institute of Computer Sciences and Mathematics of Monastir, University of Monastir, Tunisia
Seifeddine Messaoud Laboratory of Condensed Matter and Nanoscience (LR11ES40), Department of Physics, Faculty of Sciences of Monastir, University of Monastir, Tunisia
Mohamed Ali Hajjaji Research Laboratory in Algebra Numbers Theory and Intelligent Systems (RLANTIS), University of Monastir, Tunisia | Higher Institute of Applied Sciences and Technology of Sousse, University of Sousse, Tunisia
Mohamed Atri Computer Engineering Department, King Khalid University, Abha, Saudi Arabia
Abdellatif Mtibaa Laboratory of Systems Integration & Emerging Energies, National Engineering School of Sfax, Sfax University, Sfax, Tunisia

Volume: 15 | Issue: 4 | Pages: 25376-25381 | August 2025 | https://doi.org/10.48084/etasr.12102

Received: 13 May 2025 | Revised: 10 June 2025 | Accepted: 21 June 2025 | Online: 2 August 2025

Corresponding author: Safa Teboulbi

Abstract

Traffic sign detection systems are vital for improving road safety and supporting autonomous navigation in urban environments. This paper presents a fine-tuned traffic sign detection system based on the You Only Learn One Representation (YOLOR) architecture. The model was trained and evaluated on a dataset comprising 15 traffic sign classes: Green Light, Red Light, Speed Limit 10, Speed Limit 100, Speed Limit 110, Speed Limit 120, Speed Limit 20, Speed Limit 30, Speed Limit 40, Speed Limit 50, Speed Limit 60, Speed Limit 70, Speed Limit 80, Speed Limit 90, and Stop. To enhance detection performance across diverse classes, the model was fine-tuned to accurately detect and classify these elements under varying conditions. The experimental results demonstrate strong detection capabilities, achieving a precision of 87.5%, a recall of 87.8%, a mean Average Precision at IoU 0.5 (mAP@0.5) of 88.5%, and a mAP across IoU thresholds from 0.5 to 0.95 (mAP@0.5:0.95) of 77.7%. These results highlight the effectiveness of the YOLOR-based approach for real-world traffic sign recognition tasks, offering a promising solution for intelligent transportation and autonomous driving applications. Furthermore, the model's competitive performance compared to recent methods reinforces its relevance in current state-of-the-art benchmarks.

Keywords:

computer vision, traffic signs detection, fine-tuned YOLOR, autonomous driving

Downloads

Download data is not yet available.

References

T. Saidani, "Deep Learning Approach: YOLOv5-based Custom Object Detection," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12158–12163, Dec. 2023. DOI: https://doi.org/10.48084/etasr.6397

C. Y. Wang, I. H. Yeh, and H. Y. M. Liao, "You Only Learn One Representation: Unified Network for Multiple Tasks." arXiv, May 10, 2021.

V. T. Tran, T. S. To, T. N. Nguyen, and T. D. Tran, "Safety Helmet Detection at Construction Sites Using YOLOv5 and YOLOR," in Intelligence of Things: Technologies and Applications, 2022, pp. 339–347. DOI: https://doi.org/10.1007/978-3-031-15063-0_32

N. Pawar et al., "Miniscule Object Detection in Aerial Images Using YOLOR: A Review," in Proceedings of International Conference on Communication and Computational Technologies, 2023, pp. 697–708. DOI: https://doi.org/10.1007/978-981-19-3951-8_52

H. Sun, D. Lu, X. Li, J. Tan, J. Zhao, and D. Hou, "Research on multi-apparent defects detection of concrete bridges based on YOLOR," Structures, vol. 65, Jul. 2024, Art. no. 106735. DOI: https://doi.org/10.1016/j.istruc.2024.106735

E. Kizilay and I. Aydin, "A YOLOR Based Visual Detection of Amateur Drones," in 2022 International Conference on Decision Aid Sciences and Applications (DASA), Chiangrai, Thailand, Mar. 2022, pp. 1446–1449. DOI: https://doi.org/10.1109/DASA54658.2022.9765252

G. Rjoub, J. Bentahar, and Y. A. Joarder, "Active Federated YOLOR Model for Enhancing Autonomous Vehicles Safety," in Mobile Web and Intelligent Information Systems, 2022, pp. 49–64. DOI: https://doi.org/10.1007/978-3-031-14391-5_4

A. Balasubramaniam and S. Pasricha, "Object Detection in Autonomous Vehicles: Status and Open Challenges." arXiv, Jan. 19, 2022. DOI: https://doi.org/10.1007/978-3-031-28016-0_17

M. Masmoudi, H. Ghazzai, M. Frikha, and Y. Massoud, "Object Detection Learning Techniques for Autonomous Vehicle Applications," in 2019 IEEE International Conference on Vehicular Electronics and Safety (ICVES), Cairo, Egypt, Sep. 2019, pp. 1–5. DOI: https://doi.org/10.1109/ICVES.2019.8906437

J. E. Hoffmann, H. G. Tosso, M. M. D. Santos, J. F. Justo, A. W. Malik, and A. U. Rahman, "Real-Time Adaptive Object Detection and Tracking for Autonomous Vehicles," IEEE Transactions on Intelligent Vehicles, vol. 6, no. 3, pp. 450–459, Sep. 2021. DOI: https://doi.org/10.1109/TIV.2020.3037928

T. Yan, W. Sun, and K. Cui, "Real-time Ship Object Detection with YOLOR," in Proceedings of the 2022 5th International Conference on Signal Processing and Machine Learning, Jul. 2022, pp. 203–210. DOI: https://doi.org/10.1145/3556384.3556415

Y. F. Huang, T. J. Liu, C. A. Lin, and K. H. Liu, "SOAda-YOLOR: Small Object Adaptive YOLOR Algorithm for Road Object Detection," in 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Oct. 2023, pp. 1652–1658. DOI: https://doi.org/10.1109/APSIPAASC58517.2023.10317144

C. F. Liou, T. H. Lee, and J. I. Guo, "Asynchronous Multi-Task Learning Based on One Stage YOLOR Algorithm," in 2023 IEEE 32nd International Symposium on Industrial Electronics (ISIE), Jun. 2023, pp. 1–5. DOI: https://doi.org/10.1109/ISIE51358.2023.10228120

P. J. Darabi, "Traffic Signs Detection." Kaggle, [Online]. Available: https://www.kaggle.com/datasets/pkdarabi/cardetection.

J. Chu, C. Zhang, M. Yan, H. Zhang, and T. Ge, "TRD-YOLO: A Real-Time, High-Performance Small Traffic Sign Detection Algorithm," Sensors, vol. 23, no. 8, Jan. 2023, Art. no. 3871. DOI: https://doi.org/10.3390/s23083871

L. Jiang, P. Zhan, T. Bai, and H. Yu, "YOLO-CCA: A Context-Based Approach for Traffic Sign Detection." arXiv, Dec. 05, 2024.

U. Kamal, T. I. Tonmoy, S. Das, and Md. K. Hasan, "Automatic Traffic Sign Detection and Recognition Using SegU-Net and a Modified Tversky Loss Function With L1-Constraint," IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 4, pp. 1467–1479, Apr. 2020. DOI: https://doi.org/10.1109/TITS.2019.2911727

H. Zhang, M. Liang, and Y. Wang, "YOLO-BS: a traffic sign detection algorithm based on YOLOv8," Scientific Reports, vol. 15, no. 1, Mar. 2025, Art. no. 7558. DOI: https://doi.org/10.1038/s41598-025-88184-0

S. Du et al., "TSD-YOLO: Small traffic sign detection based on improved YOLO v8," IET Image Processing, vol. 18, no. 11, pp. 2884–2898, 2024. DOI: https://doi.org/10.1049/ipr2.13141

Z. Lin et al., "YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multi-Branch Feature Interaction." arXiv, Mar. 30, 2025.