Real Time Drowsiness Detection using Viola Jones & KLT

Technologies are developing day by day, sector for road transport implement new technologies for the welfare of people all over the world, even though the number of road accidents had increased day by day. Studies say that there are many reasons for these accidents but one of the main reasons is the mistake made by the driver, due to drowsiness or any other reason. The proposed methodology helps to detect whether the driver is drowsy or not. The violajones algorithm is used to detect the face and eyes. After detection, using Kanade Lucas Tomasi (KLT) the detected part is tracked. The eyeballs are detected using hough transform. Two conditions are set to analyze the drowsiness if the conditions are satisfied the system will raise the alarm to alert the driver. The alarm got stopped only if the driver awake from the drowsy situation. The proposed system was simulated using MATLAB 2017a. The result was analysed by testing 55 samples in real-time. The accuracy of the proposed system is 96.3%. The accuracy was analysed using the parameters like True Positive, True Negative, False Positive, False Negative. The method helps to reduce the number of road accidents and the proposed system does not need any physical contact with the driver so it is quite easy to implement.