A Non-intrusive Approach for Driver's Drowsiness Detection

Fatigueness of the driver is considered a major cause that account to a large numbers of death worldwide. Thus it becomes necessary to develop a system that can help reduce such accidents. During drowsy state, significant differences in the facial features of the driver are observed in comparison to the normal state. The system proposed in the paper is focused on detection as well as alarming the driver after recording the physiological state of the driver. We made use of the non-intrusive approach which monitors the subject in real-time, wherein the blinking of eyes as well as the mouth shape (yawn) of the operator are observed, and if the operator's eyes are shut for more than the threshold value, or the operator is yawning, or if both of them are detected at the same instance then the driver's state is concluded for precautions. The proposed system is designed using Python Language, and OpenCV application is used for image processing employing the use of Viola - Jones Algorithm for the detection of facial features.