Article Sidebar
Views PDF: 0
BUILDING A TRAFFIC SIGN RECOGNITION SYSTEM TO SUPPORT SAFE DRIVING
Main Article Content
Abstract
Amidst rapid urbanization and the development of transportation infrastructure in Vietnam, traffic volume is increasing nationwide. This poses numerous challenges to traffic safety, including an increased risk of accidents, failure to recognize or miss traffic signs, especially in adverse weather conditions. This research aims to build a traffic sign recognition system that supports safe driving based on deep learningmethods in the field of Artificial Intelligence and Computer Vision. The YOLO model is used to detect and support real-time sign recognition and give warnings to drivers. However, the system still faces many challenges due to factors such as low light, bad weather, or obscured signage, which affect the accuracy of the system. In addition, real-time processing requirements and limited deployment capabilities on hardware devices also need to be addressed. The results of the study show that the model is capable of recognizing traffic signs with good accuracy and meeting real-time requirements. The system can be integrated with cameras to give timely warnings to drivers, contributing to improving traffic safety in real conditions.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Keywords
Traffic Sign Recognition, Artificial Intelligence, Computer Vision, YOLO, Deep Learning
References
Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection [Preprint]. arXiv. https://arxiv.org/abs/2004.10934
Bộ Công an. (2026). Tình hình tai nạn giao thông, cháy, nổ và xử lý hành chính về trật tự, an toàn giao thông năm 2025. Cổng Thông tin điện tử Bộ Công an. Retrieved xx xx, 2026, from https://bocongan.gov.vn/
Ghosh, S., & Lee, T. S. (2000). Intelligent transportation systems: New principles and architectures. CRC Press.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. https://www.deeplearningbook.org
Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLOv8 [Computer software]. GitHub. https://github.com/ultralytics/ultralytics
Kaggle. (n.d.). Kaggle. Retrieved April 19, 2026, from https://www.kaggle.com
Melo, J. P., et al. (2024). Traffic sign detection and recognition using YOLO object detection algorithm: A systematic review. Mathematics, 12(2), Article 297. https://doi.org/10.3390/math12020297
OpenCV. (n.d.). Getting started with videos. Retrieved April 19, 2026, from https://docs.opencv.org/4.x/dd/d43/tutorial_py_video_display.html
OpenCV. (n.d.). Image processing (imgproc module). Retrieved April 19, 2026, from https://docs.opencv.org/4.x/d7/dbd/group__imgproc.html
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779-788).
Roboflow. (n.d.). Roboflow. Retrieved April 19, 2026, from https://roboflow.com
Stallkamp, J., Schlipsing, M., Salmen, J., & Igel, C. (2012). Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Networks, 32, 323-332. https://doi.org/10.1016/j.neunet.2012.02.016
TFSVN. (n.d.). Tổng hợp đầy đủ các biển báo giao thông đường bộ từ 01/01/2025. https://tfsvn.com.vn/cac-bien-bao-giao-thong-duong-bo-tu-01-01-2025/
Ultralytics. (n.d.). YOLOv8 models. Retrieved April 19, 2026, from https://docs.ultralytics.com/vi/models/yolov8/