A DEEP LEARNING APPROACH FOR DRIVER FATIGUE DETECTION
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no2E.421Keywords:
Driver fatigue detection, deep learning, eye state recognition, computer vision, YOLOAbstract
Driver fatigue is a major contributing factor to traffic accidents worldwide, motivating the development of reliable, non-invasive, and real-time monitoring systems. This paper presents a vision-based driver fatigue detection system built upon the YOLO (You Only Look Once) deep learning framework. The proposed system integrates face detection and eye-state classification (open/closed) to infer driver fatigue from monocular video streams captured by a standard camera. Compared with traditional fatigue detection approaches based on physiological signals or vehicle dynamics, the proposed method requires no wearable sensors and exhibits low deployment cost and high practical applicability. YOLO is adopted as the core detection model due to its anchor-free design, efficient feature extraction, and fast inference speed. A customized dataset is constructed by combining public datasets with self-collected images, augmented through random background fusion, scaling, and rotation to enhance robustness and generalization. Experimental results demonstrate that the proposed system achieves high detection accuracy and stable real-time performance under typical driving conditions. The results indicate that the proposed approach is suitable for real-world driver monitoring applications and can serve as a foundation for more advanced fatigue detection systems.
References
[1] Z. Mardi, S. N. Ashtiani, and M. Mikaili, “EEG-based Drowsiness Detection for Safe Driving Using Chaotic Features and Statistical Tests,” Journal of Medical Signals and Sensors, vol. 1, no. 2, pp. 130–137, 2011. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC3342623/
[2] R. Li, Y. V. Chen, and L. Zhang, “A Method for Fatigue Detection Based on Driver's Steering Wheel Grip,” International Journal of Industrial Ergonomics, vol. 82, Art. no. 103083, 2021. doi: https://doi.org/10.1016/j.ergon.2021.103083
[3] T. Soukupová and J. Čech, “Real-Time Eye Blink Detection Using Facial Landmarks,” in Proc. Computer Vision Winter Workshop (CVWW), 2016, pp. 1–8. Available: https://vision.fe.uni-lj.si/cvww2016/proceedings/papers/05.pdf
[4] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 779–788. doi: https://doi.org/10.1109/CVPR.2016.91
[5] A. Amidei, S. Spinsante, G. Iadarola, S. Benatti, F. Tramarin, P. Pavan, and L. Rovati, “Driver Drowsiness Detection: A Machine Learning Approach on Skin Conductance,” Sensors, vol. 23, no. 8, Art. no. 4004, 2023. doi: https://doi.org/10.3390/s23084004
[6] K. Lu, A. S. Dahlman, J. Karlsson, and S. Candefjord, “Detecting Driver Fatigue Using Heart Rate Variability: A Systematic Review,” Accident Analysis & Prevention, vol. 178, Art. no. 106830, 2022. doi: https://doi.org/10.1016/j.aap.2022.106830
[7] J. Xi, S. Wang, T. Ding, J. Tian, H. Shao, and X. Miao, “Detection Model on Fatigue Driving Behaviors Based on the Operating Parameters of Freight Vehicles,” Applied Sciences, vol. 11, no. 15, Art. no. 7132, 2021. doi: https://doi.org/10.3390/app11157132
[8] G. Sikander and S. Anwar, “Driver Fatigue Detection Systems: A Review,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 6, pp. 2339–2352, 2019. doi: https://doi.org/10.1109/TITS.2018.2868499.
[9] F. Song, X. Tan, X. Liu, and S. Chen, “Eyes Closeness Detection From Still Images With Multi-Scale Histograms of Principal Oriented Gradients,” Pattern Recognition, vol. 47, no. 9, pp. 2825–2837, 2014. doi: https://doi.org/10.1016/j.patcog.2014.03.024
[10] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A Large-Scale Hierarchical Image Database,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2009, pp. 248–255. doi: https://doi.org/10.1109/CVPR.2009.5206848
