Home / Current Issue / Paper 1712571
Real-Time Drowsiness Detection
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
Abstract
Driver drowsiness is a major cause of road acci- dents, especially during long-distance and night-time driving. Fatigue severely degrades reaction time, decision-making ability, and situational awareness, leading to life-threatening incidents. Existing detection techniques such as physiological sensing and vehicle behavior monitoring often suffer from intrusiveness or environmental sensitivity. This paper presents a real-time hybrid drowsiness detection system combining the speed of Haar Cascade classifiers with the accuracy of a Convolutional Neural Network (CNN) for open/closed eye-state classification. The system continuously monitors eye regions and evaluates prolonged eye closure using temporal thresholding to determine the onset of drowsiness. The lightweight design ensures real-time performance at 24?28 FPS on standard CPU hardware, achieving an accuracy of 96%. The proposed system effectively addresses limitations in classical EAR-based systems identified in previous research, including issues with illumination, spectacles reflection, and head movement. Experimental results demonstrate strong robustness and make the approach suitable for integration into low-cost ADAS systems.
Keywords
Drowsiness Detection, CNN, Haar Cascade, Eye- State Classification, Computer Vision, Deep Learning.
References
[1] Jagbeer Singh, Ritika Kanojia, Rishika Singh, Rishita Bansal, and Sakshi Bansal, “Driver Drowsiness Detection System – An Approach by Machine Learning Application,” Journal of Pharmaceutical Negative Results, 2022.
[2] Simone Abtahi et al., “Driver Drowsiness Monitoring Based on Yawning Detection,” IEEE Transactions on Instrumentation and Measurement, 2016.
[3] Rami N. Khushaba et al., “Driver Drowsiness Classification Using Fuzzy Wavelet Packet Features,” IEEE Transactions on Biomedical Engineering, 2011.
[4] Paul Viola and Michael Jones, “Rapid Object Detection Using a Boosted Cascade,” CVPR, 2001.
[5] Teresa Soukupová and Jan Cˇ ech, “Real-Time Eye Blink Detection,” CVWW, 2016.
[6] Gang Li and Wan-Young Chung, “Driver Drowsiness Detection Using HRV and SVM,” Sensors, 2013.
[7] Yeongmin Jeong et al., “Driver Drowsiness Detection Using CNN,” Journal of Electrical Engineering, 2019.
[8] Anand Sahayadhas et al., “Detecting Driver Drowsiness – A Review,” Sensors, 2012.
[9] Hyeonwoo Jo and Donghyun Jung, “Real-Time Drowsiness Alert Sys- tem,” Applied Sciences, 2021.
[10] Luis Miguel Bergasa et al., “Monitoring Driver Vigilance,” IEEE T-ITS, 2006.
How to cite this paper
@article{1712571,
author = {Sufiya Begum, Safdar Iqbal, Mohammad Foorqan, Md Zahoor Rahi, Md Asif Alam},
title = {Real-Time Drowsiness Detection},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {6},
pages = {140-145},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1712571.pdf},
abstract = {Driver drowsiness is a major cause of road acci- dents, especially during long-distance and night-time driving. Fatigue severely degrades reaction time, decision-making ability, and situational awareness, leading to life-threatening incidents. Existing detection techniques such as physiological sensing and vehicle behavior monitoring often suffer from intrusiveness or environmental sensitivity. This paper presents a real-time hybrid drowsiness detection system combining the speed of Haar Cascade classifiers with the accuracy of a Convolutional Neural Network (CNN) for open/closed eye-state classification. The system continuously monitors eye regions and evaluates prolonged eye closure using temporal thresholding to determine the onset of drowsiness. The lightweight design ensures real-time performance at 24?28 FPS on standard CPU hardware, achieving an accuracy of 96%. The proposed system effectively addresses limitations in classical EAR-based systems identified in previous research, including issues with illumination, spectacles reflection, and head movement. Experimental results demonstrate strong robustness and make the approach suitable for integration into low-cost ADAS systems.},
keywords = {Drowsiness Detection, CNN, Haar Cascade, Eye- State Classification, Computer Vision, Deep Learning.},
month = {December},
doi = {https://doi.org/10.64388/IREV9I6-1712571}
}