IJETEV1I1A005 - REAL TIME DRIVE FATIGUE AND DETECTION RECOGNITION USING COMPUTER VISION
AUTHORS : Vishvanath Sundharam G, Muthusamy P, Sam Sundar N, Hari Haran N, Selvanesan M
ABSTRACT – Driver drowsiness and distraction are among the leading causes of road accidents worldwide, necessitating the development of intelligent, real-time monitoring systems to enhance driving safety. This paper presents a non-intrusive Driver Monitoring System (DMS) based on computer vision and deep learning techniques for the detection of driver fatigue and inattentive behavior. The proposed approach leverages a YOLO-powered object recognition framework to identify critical facial regions such as the eyes, mouth, and head orientation from live in-vehicle camera feeds. Key behavioral metrics, including the Percentage of Eye Closure (PERCLOS) and Mouth Aspect Ratio (MAR), are computed to assess alertness levels. The system is designed to operate under varying lighting conditions and diverse driver profiles, providing timely audio or visual alerts upon detecting drowsiness or distraction.