Driver drowsiness is a major cause of road accidents, resulting in serious injuries and fatalities. This paper presents a real-time, non-intrusive Driver Drowsiness Detection System using multi-factor detection based on computer vision techniques. The system combines Haar Cascade classifiers for fast face detection with Dlib’s CNN-based facial landmark extraction to monitor key indicators such as Eye Aspect Ratio (EAR), Mouth Aspect Ratio (MAR), and head-pose estimation. To enhance reliability, multi-cue fusion and temporal smoothing are applied to analyze patterns across consecutive frames, reducing false positives. A combined drowsiness score is generated, and real-time alerts are provided through voice and beep notifications to ensure timely intervention. The proposed system achieves a balance between accuracy and computational efficiency, enabling deployment on standard hardware. It offers a scalable and practical solution for improving road safety and intelligent transportation systems.
Driver Drowsiness Detection, Computer Vision, Multi-factor Detection, Eye Aspect Ratio (EAR), Mouth Aspect Ratio (MAR)
IRE Journals:
Dharshanaa Sree T, Gana Sri M S, Swetha M, Vishmitha T, C. Janani "Driver Drowsiness Detection System Using Multi-Factor Detection" Iconic Research And Engineering Journals Volume 9 Issue 10 2026 Page 1207-1211 https://doi.org/10.64388/IREV9I10-1716171
IEEE:
Dharshanaa Sree T, Gana Sri M S, Swetha M, Vishmitha T, C. Janani
"Driver Drowsiness Detection System Using Multi-Factor Detection" Iconic Research And Engineering Journals, 9(10) https://doi.org/10.64388/IREV9I10-1716171