Volume 2 - Issue 2, March - April 2026

Driver fatigue and drowsiness are among the most significant contributors to road accidents globally, often leading to severe injuries and fatalities. This project presents a Real-Time Driver Drowsiness Detection System designed to provide an automated, lowcost safety intervention. The system utilizes Computer Vision and Machine Learning techniques to monitor driver alertness through a standard webcam interface. The core methodology involves detecting the driver's face and eyes using Haar Cascade Classifiers, a computationally efficient object detection algorithm. Once the eye regions are localized, the Eye Aspect Ratio (EAR) is calculated using Euclidean distances between facial landmarks to determine the state of the eyes (open or closed). A temporal thresholding logic is applied to differentiate between natural physiological blinking and prolonged eye closure indicative of drowsiness.

Jayshree Khairnar, Purva Jagtap, Bhavesha Sakhare, Akanksha Rayjade, Prachi Shinde,"Real-Time Driver Drowsiness Detection System" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(2): Page(1506-1509) Mar-Apr 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.