A hybrid physiological-visual approach for real-time driver drowsiness detection: Design and experimental validation
Keywords:
Driver drowsiness detection, Real-time, EAR-MAR, Hybrid, Physiological-visualAbstract
Drowsy driving remains a significant contributor to traffic accidents in Indonesia, where most incidents are attributable to human error. With advances in vehicle technologies, opportunities arise to enhance road safety through real-time driver monitoring systems. This study proposes the development of a drowsiness detection device that uses a hybrid measurement method integrating physiological and visual indicators. The system incorporates the MAX30102 sensor for heart-rate monitoring and a camera-based visual analysis that employs Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) to detect signs of drowsiness. The system is programmed using Python and C++. A series of experimental evaluations was conducted, including sensor performance testing; comparative analysis of the MAX30102 and a medical-grade oximeter; accuracy evaluation of EAR and MAR; impact of distance variation on detection latency; angular variation (yaw, pitch, roll); and the effect of light intensity on detection reliability. The experimental results demonstrate a detection success rate of 90%, indicating the system’s potential for reliable real-time application. Future work will focus on improving system accuracy, such as nighttime driving and inclement weather, and validating the system’s effectiveness in real-world driving scenarios.
References
1. I. F. Faisal and S. Kharisma, Agi Putra, ‘Pengembangan Aplikasi Pendeteksi Kantuk Pada Pengendara Kendaraan Bermotor Dengan Menggunakan Sensor Detak Jantung Pada Smartwatch,’ Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 10, pp. 9568–9578, 2019.
2. S. Sathasivam, A. K. Mahamad, S. Saon, A. Sidek, M. M. Som, and H. A. Ameen, ‘Drowsiness Detection System using Eye Aspect Ratio Technique,’ 2020 IEEE Student Conf. Res. Dev. SCOReD 2020, no. September, pp. 448–452, 2020, doi: 10.1109/SCOReD50371.2020.9251035.
3. A. Kuwahara, K. Nishikawa, R. Hirakawa, H. Kawano, and Y. Nakatoh, ‘Eye fatigue estimation using blink detection based on Eye Aspect Ratio Mapping(EARM),’ Cogn. Robot., vol. 2, no. January, pp. 50–59, 2022, doi: 10.1016/j.cogr.2022.01.003.
4. J. Jose, J. Andrew, K. Raimond, S. Vincent, and R. Jennifer Eunice, ‘SleepyWheels: An ensemble model for drowsiness detection leading to accident prevention,’ J. Auton. Intell., vol. 7, no. 3, 2024, doi: 10.32629/jai.v7i3.1117.
5. R. H, ‘Real Time Driver Drowsiness Detection System using OpenCV,’ Int. J. Res. Appl. Sci. Eng. Technol., vol. 9, no. VI, pp. 3254–3260, 2021, doi: 10.22214/ijraset.2021.35811.
6. T. Zhu et al., ‘Research on a Real-Time Driver Fatigue Detection Algorithm Based on Facial Video Sequences,’ Appl. Sci., vol. 12, no. 4, 2022, doi: 10.3390/app12042224.
7. M. A. Yaman Albadawi, Maen Takruri, ‘A Review of Recent Developments in Driver Drowsiness,’ pp. 1–41, 2022.
8. J. S. Bajaj, N. Kumar, and R. K. Kaushal, ‘Performance analysis of hybrid model to detect driver drowsiness at early stage,’ Int. J. Appl. Sci. Eng., vol. 20, no. 3, 2023, doi: 10.6703/IJASE.202309_20(3).010.
9. J. D. and J. Seladi-Schulman, ‘What is a Dangerous Heart Rate?,’ 2024. E. Sugawara and H. Nikaido, ‘Properties of AdeABC and AdeIJK efflux systems of Acinetobacter baumannii compared with those of the AcrAB- TolC system of Escherichia coli,’ Antimicrob. Agents Chemother., vol. 58, no.12, pp. 7250–7257, 2014, doi: 10.1128/AAC.03728-14.
10. W. Dewi, C., Chen, R. C., Chang, C. W. and H. S. H., Jiang, X., & Yu, ‘Eye aspect ratio for real-time drowsiness detection to improve driver safety.Electronics,’ Electronics, vol. 19, p. 11, 2022.
11. fritzing, ‘Fritzing: Open-source hardware initiative. Fritzing.’ .
12. Y. Hamza, G., Es-Sadek, M. Z., & Taher, ‘Enhancing Road Safety: A Multi- Modal Drowsiness Detection System for Drivers,’ Int. J. Adv. Comput. Sci. Appl., vol. 16(1), 2025.
13. ResearchGate, ‘On the rhythm of head movements in Finnish and Swedish Sign Language sentences: The yaw, pitch, and roll angles in the human head motion,’ 2025.
14. S. A. Ludwig and K. D. Burnham, ‘Comparison of Euler Estimate using Extended Kalman Filter, Madgwick and Mahony on Quadcopter Flight Data,’ 2018 Int. Conf. Unmanned Aircr. Syst. ICUAS 2018, pp. 1236–1241, 2018, doi: 10.1109/ICUAS.2018.8453465.
Downloads
Published
Conference Proceedings Volume
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.