A study on the application of the YOLOv8 model for road traffic sign recognition in Vietnam
Published: July 5, 2026
Abstract
Automatic traffic sign recognition has emerged as a mandatory standard and a technological requirement for modern intelligent systems as well as for self-driving cars in particular. The conventional approach of machine learning methods often reveals limitations regarding feature generalization and computational efficiency. This paper explores the distinct advantages of an existing YOLO (You Only Look Once) model and applies it to the task of traffic sign detection. The conducted experiment demonstrates highly impressive and relatively accurate results for both detection and classification on the training data set. Furthermore, the inference time for prediction on the test set meets the real-time requirement when vehicles move in urban areas. Therefore, an optimum YOLO model could offer one reliable alternative for addressing critical traffic safety issues in the future.
Keywords
mAPBounding boxIoU
References
1.
Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection, https://doi.org/10.48550/arXiv.2004.10934.
Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, and Guiguang Ding (2024). YOLOv10: Real-Time End-to-End Object Detection, https://arxiv.org/pdf/2405.14458.
3.
Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, Conference on Computer Vision and Pattern Recognition.
Hao Chen, Zhan Chen and HangYu (2023). Enhanced YOLOv5: An efficient Road Object Detection Method, Sensors (MDPI).
6.
Ilya Loshchilov and Frank Hutter (2019). Decoupled Weight Decay Regularization, International Conference on Learning Representations.
7.
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi (2016). You Only Look Once: Unified, Real-Time Object Detection, Conference on Computer Vision and Pattern Recognition.
8.
Navneet Dalal and Bill Triggs (2005). Histograms of Oriented Gradients for Human Detection. Conference on Computer Vision and Pattern Recognition.
9.
Paul Viola and Michael Jones (2001). Rapid Object Detection using a Boosted Cascade of Simple Features, Conference on Computer Vision and Pattern Recognition.
10.
Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, and Jian Yang (2020). Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, Conference on Neural Information Processing Systems.
