Driver Drowsiness Detection using Machine Learning with Visual Behaviour

Abstract

A person while driving a vehicle - if does not have proper sleep or rest, is more inclined to fall asleep which may cause a traffic accident. This is why a system is required which will detect the drowsiness of the driver. Recently, in research and development, machine learning methods have been used to predict a driver's conditions. Those conditions can be used as information that will improve road safety. A driver's condition can be estimated by basic characteristics age, gender and driving experience. Also, driver's driving behaviours, facial expressions, bio-signals can prove helpful in the estimation. Machine Learning has brought progression in video processing which enables images to be analysed with accuracy. In this paper, we proposed a method for detecting drowsiness by using convolution neural network model over position of eyes and extracting detailed features of the mouth using OpenCV and Dlib to count the yawning.