An Early Warning System for Driver Fatigue Detection Using Viola-Jones Over Hog Algorithm

Accident prevention encompasses a wide range of strategies, practices, and safety measures aimed at reducing the likelihood of accidents, injuries, and fatalities in various settings, including on the road, at home, in the workplace, and in public spaces. Drowsiness detection refers to the use of technology and methods to monitor and identify signs of drowsiness or fatigue in individuals, particularly drivers, in order to prevent accidents and improve road safety. Drowsiness detection systems typically use a combination of sensors, algorithms, and real-time data analysis to assess a person's level of alertness. For predicting the responsiveness of driver drowsiness behavior using Viola-Jones (VJ) machine learning algorithm, it helps to prevent the driver from falling asleep which causes accidents includes severe injuries and may cause death. Viola-Jones (VJ) machine learning algorithm for blink frequency for analyzing the behavior of driver drowsiness behavior. Viola-Jones (VJ) has significantly better sensitivity Blink frequency percentage is better for Viola Jones (95.14%) compared to HOG (90.84%). There was statistical significance between Voila-Jones (VJ) and HOG t (p=0.000). Viola-Jones (VJ) helps in predicting better sensitivity percentage for driver drowsiness behavior. If the driver is said to be drowsy the algorithm will detect it and make the alarm noise to wake him up.