Real-Time Driver Microsleep Detection Using Lightweight MobileViT and Haar Cascade
DOI:
https://doi.org/10.69533/j5k7v326Keywords:
Driver Monitoring, Haar Cascade, Microsleep, MobileViT, Real-Time DetectionAbstract
Microsleep is a brief and involuntary loss of awareness that increases the risk of driving accidents. This study proposes a real-time microsleep detection system using Haar Cascade for eye localization and the lightweight MobileViT-XXS model for eye-state classification. The model was trained on a public dataset and achieved a training accuracy of 99.49%, a test accuracy of 98%, and a real-time accuracy of 90–94%. A microsleep event is detected when the eyes remain closed for ≥ 2 seconds. While the method performs well under controlled conditions, real-time testing revealed technical limitations such as sensitivity to lighting variation, non-frontal head pose, and motion, which affect detection stability and represent common robust-vision challenges. Despite these limitations, the system runs efficiently on CPU-only hardware and demonstrates strong potential as a lightweight early-warning system to support driving safety. Future research may explore expanding dataset diversity, improving environmental adaptation, and deploying the system on embedded or mobile platforms to enhance robustness and scalability.
Downloads
References
G. Shiva, S. Chari, and J. A. Prashant, “Real-time driver drowsiness detection based on integrative approach of deep learning and machine learning model,” Indones. J. Electr. Eng. Comput. Sci., vol. 39, no. 1, pp. 592–602, 2025, doi: 10.11591/ijeecs.v39.i1.pp592-602.
S. Begum, S. Iqbal, and M. Foorqan, “Real-Time Drowsiness Detection,” IRE Journals, vol. 9, no. 6, pp. 140–145, 2025, doi: DOI: https://doi.org/10.64388/IREV9I6-1712571.
T. S. Delwar, M. Singh, S. Mukhopadhyay, A. Kumar, and D. Parashar, “AI- and Deep Learning-Powered Driver Drowsiness Detection Method Using Facial Analysis,” pp. 1–24, 2025.
B. Fu, F. Boutros, C. Lin, and N. Damer, “A Survey on Drowsiness Detection – Modern Applications and Methods,” IEEE Trans. Intell. Transp. Syst., vol. 25, no. 3, pp. 1–23, 2024.
T. Fonseca, “Drowsiness Detection in Drivers : A Systematic Review of Deep Learning-Based Models,” Appl. Sci., vol. 15, pp. 1–43, 2025, doi: https://doi.org/10.3390/app15169018.
T. M. Hassan, W. Y. Ibrahim, H. A. Ali, and H. S. Marie, “Deep Learning-Based Driver Drowsiness Detection Using Facial Expression Analysis Faculty of Artificial Intelligence , Delta University for Science and Technology , Gamasa 35712 , Faculty Artificial Intelligence , Delta University for Science and Technolog,” Delta Univ. Sci. J., vol. 07, no. 2, pp. 164–176, 2024, doi: https://dusj.journals.ekb.eg.
N. Datta, T. Mahmud, M. Begum, M. T. Aziz, and D. Islam, “Convolutional neural network-based real-time drowsy driver detection for accident prevention,” TELKOMNIKA, vol. 23, no. 3, pp. 682–693, 2025, doi: 10.12928/TELKOMNIKA.v23i3.26059.
H. Z. Ilmadina, D. Apriliani, and D. S. Wibowo, “Deteksi Pengendara Mengantuk dengan Kombinasi Haar Cascade Classifier dan Support Vector Machine,” vol. 7, no. 1, pp. 1–7, 2022.
S. Makowski, P. Prasse, L. A. J, and T. Scheffer, “Detection of Drowsiness and Impending Microsleep from Eye Movements,” Proc. Mach. Learn. Res., vol. 1, pp. 1–18, 2023.
M. Venkateswarlu and V. R. R. Ch, “DrowsyDetectNet: Driver drowsiness detection using lightweight CNN with limited training data,” IEEE Access, vol. 12, pp. 1–15, 2024, doi: 10.1109/ACCESS.2024.3440585.
D. Salem and M. Waleed, “Real-time drowsiness detection via convolutional neural networks and transfer learning,” J. Eng. Appl. Sci., vol. 71, no. 122, pp. 1–10, 2024
R. Florez et al., “A real-time embedded system for driver drowsiness detection,” Sensors, vol. 24, no. 7810, pp. 1–15, 2024, doi: 10.3390/s24087810.
A. Phan et al., “Driver drowsiness detection and smart alerting using deep learning and IoT,” Multimedia Tools and Applications, pp. 1–23, 2023, doi: 10.1007/s11042-023-15987-2.
M. Venkateswarlu et al., “CNN-ViT: A multi-feature learning approach for driver drowsiness detection,” Pers. Ubiquitous Comput., pp. 1–12, 2025.
A. Bhanja et al., “A real-time driver drowsiness detection system,” ROBOSEM Journal, pp. 1–10, 2025.
S. Priyanka, R. Kumar, and A. Ahmed, “Data fusion-based multimodal deep learning for drowsiness recognition,” Computers & Electrical Engineering, vol. 109, pp. 1–15, 2024, doi: 10.1016/j.compeleceng.2024.109050.
R. Iswahyudi, A. F. Ihsan, and I. M. M. Matin, “Deteksi kantuk menggunakan CNN berdasarkan kedipan mata,” J. Fis. Teknol., vol. 4, no. 2, pp. 45–53, 2024.
A. Turki, S. Ammar, M. Karray, and M. Ksantini, “Facial expression-based drowsiness detection system for driver safety using deep learning techniques,” in Proc. 16th ICAART, vol. 3, pp. 726–733, 2024, doi: 10.5220/0012386000003655.
J. Chao, K. Li, and W. Sun, “Real-time microsleep detection using attention-based deep learning,” IEEE Trans. Human-Machine Systems, vol. 54, no. 1, pp. 112–123, 2025.
H. Wu and L. Zhang, “Mobile vision transformer for lightweight driver fatigue detection,” IEEE Sensors Journal, vol. 26, no. 4, pp. 2150–2162, 2026,
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Syahada Mawarda Hutagalung, Muhammad Alfariz Rasyid, Supiyandi, Aidil Halim Lubis (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
