Giám sát tình trạng người lái và hỗ trợ can thiệp chủ động dựa trên công nghệ học sâu
Tóm tắt: 0
|
PDF: 1
##plugins.themes.academic_pro.article.main##
Author
-
Nguyen Le Chau ThanhThe University of Danang – University of Technology and Education, VietnamPhung Minh TungThe University of Danang – University of Technology and Education, VietnamKieu Quoc LongThe University of Danang – University of Technology and Education, VietnamHo Thang LanhThe University of Danang – University of Technology and Education, VietnamTrinh Phan Minh VuThe University of Danang – University of Technology and Education, Vietnam
Từ khóa:
Tóm tắt
Tình trạng buồn ngủ của tài xế là những nguyên nhân phổ biến gây ra các vụ tai nạn giao thông, đặc biệt là trên các tuyến đường dài và cao tốc. Trong những năm gần đây, nhiều nghiên cứu giám sát tình trạng người lái dựa trên công nghệ học sâu được đề xuất, chủ yếu tập trung vào việc cải thiện độ chính xác nhận diện và khả năng thích ứng nhiều điều kiện môi trường. Tuy nhiên, phần lớn các nghiên cứu này vẫn dừng lại ở mức cảnh báo, trong khi việc nhận diện để hỗ trợ giảm thiểu rủi ro chủ động và an toàn cho người lái vẫn còn hạn chế. Bài báo này đề xuất một hệ thống giám sát trạng thái người lái sử dụng mô hình học sâu để giám sát trạng thái mắt và hành vi ngáp của tài xế. Dựa vào kết quả nhận diện, một cơ chế hỗ trợ can thiệp mức độ nhẹ được triển khai nhằm giảm thiểu rủi ro cho người lái.
Tài liệu tham khảo
-
[1] AAA Foundation for Traffic Safety, “Prevalence of drowsy driving crashes: Estimates from a large-scale naturalistic driving study,” AAA Foundation for Traffic Safety, 2018. [Online]. Available: https://aaafoundation.org/prevalence-drowsy-driving-crashes-estimates-large-scale-naturalistic-driving-study/ [Accessed Jan. 1, 2026].
[2] National Highway Traffic Safety Administration, “Countermeasures that work: Drowsy driving,” National Highway Traffic Safety Administration, 2020. [Online]. Available: https://www.nhtsa.gov/book/countermeasures-that-work/drowsy-driving [Accessed Jan. 1, 2026].
[3] L. Di Milia, “Shift work, sleepiness and long distance driving,” Transportation Research Part F: Traffic Psychology and Behaviour, vol. 9, no. 4, pp. 278–285, 2006. https://doi.org/10.1016/j.trf.2006.01.006.
[4] M. L. Lee et al., “High risk of near-crash driving events following night-shift work,” Proceedings of the National Academy of Sciences of the United States of America, vol. 113, no. 1, pp. 176–181, 2016. https://doi.org/10.1073/pnas.1510383112.
[5] A. Sahayadhas, K. Sundaraj, and M. Murugappan, “Detecting driver drowsiness based on sensors: A review,” Sensors, vol. 12, no. 12, pp. 16937–16953, 2012. https://doi.org/10.3390/s121216937.
[6] I. Nasri, M. Karrouchi, K. Kassmi, and A. Messaoudi, “A review of driver drowsiness detection systems: Techniques, advantages and limitations,” arXiv preprint, arXiv:2206.07489, 2022. https://doi.org/10.48550/arXiv.2206.07489.
[7] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems 25 (NeurIPS), Lake Tahoe, NV, USA, 2012, pp. 1097–1105.
[8] Y. Kartynnik, A. Ablavatski, I. Grishchenko et al., “Real-time facial surface geometry from monocular video on mobile GPUs,” arXiv preprint, arXiv:1907.06724, 2019. https://doi.org/10.48550/arXiv.1907.06724.
[9] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Kauai, HI, USA, 2001, pp. 511–518.
[10] V. Kazemi and J. Sullivan, “One millisecond face alignment with an ensemble of regression trees,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, 2014, pp. 1867–1874. https://doi.org/10.1109/CVPR.2014.241.
[11] C. Nogueira, L. Fernandes, J. N. D. Fernandes, and J. S. Cardoso, “Explaining bounding boxes in deep object detectors using post hoc methods for autonomous driving systems,” Sensors, vol. 24, no. 2, article 516, 2024. https://doi.org/10.3390/s24020516.
[12] M. M. Abdelsamie, S. S. Azab, and H. A. Hefny, “Deep multi-task learning: A review of concepts, methods, and cross-domain applications,” International Journal of Data Science and Analytics, vol. 21, article 77, 2026. https://doi.org/10.1007/s41060-025-00892-y.
[13] O. Sener and V. Koltun, “Multi-task learning as multi-objective optimization,” arXiv preprint, arXiv:1810.04650, 2018. https://doi.org/10.48550/arXiv.1810.04650.
[14] S. Ruder, “An overview of multi-task learning in deep neural networks,” arXiv preprint, arXiv:1706.05098, 2017. https://doi.org/10.48550/arXiv.1706.05098.
[15] H. Matsuo and A. Khiat, “Early detection of reduced alertness using subsidiary behavior,” SAE Technical Paper 2012-01-0737, 2012. https://doi.org/10.4271/2012-01-0737.
[16] J. F. Wierwille and L. A. Ellsworth, “Evaluation of driver drowsiness by trained raters,” Accident Analysis & Prevention, vol. 26, no. 5, pp. 571–581, 1994. https://doi.org/10.1016/0001-4575(94)90036-1.
[17] Q. Han et al., “A dense multi-pooling convolutional network for driving fatigue detection,” Scientific Reports, vol. 15, 2025. https://doi.org/10.1038/s41598-025-99441-7.
[18] H. Mohammadi, A. H. Alavi, and M. R. Daliri, “Driver drowsiness estimation using EEG signals with a dynamical encoder–decoder modeling framework,” Scientific Reports, vol. 12, article 2483, 2022. https://doi.org/10.1038/s41598-022-06308-2.
[19] M. S. Awais, N. Badruddin, and M. Drieberg, “PERCLOS threshold for drowsiness detection during real driving,” International Journal of Vehicular Technology, 2017, article 4357356. https://doi.org/10.1155/2017/4357356.
[20] A. Kapoor, W. Burleson, and R. Picard, “System and method for driver drowsiness detection using behavioral and sensor-based physiological measures,” Sensors, vol. 23, no. 3, article 1292, 2023. https://doi.org/10.3390/s23031292.
[21] LED Roadway Lighting: Impact on Driver Sleep Health and Alertness. Washington, DC: National Academies of Sciences, Engineering, and Medicine, The National Academies Press, 2021.
[22] H. Behbahani, N. Nadimi, H. Alenoori, and M. Sayadi, “Developing a new surrogate safety indicator based on motion equations,” Promet – Traffic & Transportation, vol. 26, no. 5, pp. 451–460, 2014. https://doi.org/10.7307/ptt.v26i5.1388.
[23] A. R. A. van der Horst and J. H. Hogema, Time-to-Collision and Collision Avoidance Systems. Groningen, Netherlands: University of Groningen, Research Report, 1994.
[24] European New Car Assessment Programme, “AEB Car-to-Car Systems Test Protocol,” Euro NCAP, 2022.
[25] T. D. Gillespie, Fundamentals of Vehicle Dynamics. Warrendale, PA: SAE International, 1992.
[26] R. Rajamani, Vehicle Dynamics and Control, 2nd ed. New York: Springer, 2012.
[27] U. Kiencke and L. Nielsen, Automotive Control Systems: For Engine, Driveline, and Vehicle, 2nd ed. Berlin: Springer, 2005.
[28] N. L. C. Thanh et al., “Design and install anit-lock braking system (ABS) combined with regenerative braking system on 110cc Honda Lead motorcycle,” in Proceedings of the 7th ATIGB International Scientific Conference, 2022, pp. 79–84.
[29] N. L. C. Thanh, N. V. Dong, and N. V. Hai, “ABS technology solutions to increase braking performance for motorcycle,” The University of Danang - Journal of Science and Technology, vol. 21, no. 5, pp. 13-18, 2023. https://jst-ud.vn/jst-ud/article/view/8384.

