Wakefulness State Estimation Method Using Eye Movement and Deep Learning

Abstract

In recent years, the number of traffic accidents caused by drivers falling asleep has increased. Many studies have reported that drowsiness occurs while driving, resulting in a need of a system to detect driver drowsiness. In this study, we use a camera sensor that can sense the state of a person while driving a car without any physical constraints and without awareness of the device. We also estimate the wakefulness state using deep learning and eye movements to detect any increase in wakefulness due to drowsiness. This estimation method is found to be highly accurate.