Driver Drowsiness Detection Using OpenCV

The advancement of computing technology has provided the means for building intelligent vehicle systems. The driver drowsiness detection system is one of the potential applications of intelligent vehicle systems. Here we employ machine learning techniques to detect driver drowsiness. The input is given in the form of a real-time webcam video, which will be processed in real-time. The system gives an output in the form of a sound alert and also a message alert will be sent if the user is found closing their eyes. The proposed system aims to lessen the number of accidents that occur due to drivers’ drowsiness and fatigue, which will in turn increase transportation safety. The existing system leverages CNN which accounts for its low accuracy and high processing time. The proposed system leverages eye aspect ratio, mouth aspect ratio, and head tilt to detect the drowsiness.