Design of Real-time Drowsiness Detection System using Dlib

Drowsiness while driving is a highly prevalent problem that leads to thousands of fatal accidents every year. A solution to prevent accidents and fatalities is the need of the hour and while there are complex systems developed that provide solutions for detecting drowsiness in drivers, this paper explores a simpler, yet highly effectual method of doing the same. In this paper, drowsy driver detection system is designed using Python and Dlib model. Dlib's shape detector is used to map the coordinates of the facial landmarks of the input video and drowsiness detected by monitoring aspect ratios of eyes and mouth. Performance evaluation of the proposed system designed is carried out by testing videos from a standard public dataset as well as real-time video captured in our lab. The proposed system gave a maximum recognition accuracy of 96.71% for dataset video input.