Road Safety by Detecting Drowsiness while Driving using Machine Learning

Driver drowsiness is one of the major causes of road accidents, leading to countless injuries, fatalities, and property damage every year. In this paper, we introduce a real-time drowsiness detection system that uses computer vision to monitor the driver's alertness. The system works with a regular webcam and tracks facial landmarks to analyze eye aspect ratio and blinking behavior. If the driver shows signs of drowsiness, such as slow blinking or prolonged eye closure, the system immediately triggers an audible alarm to wake them up and avoid a possible accident. We've built the system using Python along with OpenCV, dlib, and pygame libraries, which makes it affordable and easy to implement. Our experiments show that it performs well in normal lighting conditions, offering a practical and non-intrusive way to improve road safety