Driver Hypovigilance Detection for Safe Driving using Infrared Camera

Driver safety can be made possible by continually monitoring the hypovigilance of the driver. Researchers have worked on analysing the driver drowsiness or inattention detection by using the camera mounted on the vehicle. This paper works on Infrared camera based monitoring of the hypovigilance (normal, fatigue, drowsy, visual and cognitive inattention) which is nothing but monitoring the state of the driver during different timings of the day. The simulator based environment was used to monitor and record the behaviour of the driver continuously for a period of two hours. The raw video is filtered and the features were extracted and classified using Support Vector Machine (SVM), k-Nearest Neighbour (KNN) and Ensemble classifier algorithm. The average accuracy of fusion of hypovigilance state for Behavioural measure is 64.1%.