Vision-based Real-time Driver Fatigue

Abstract — In modern days, a large no of automobile accidents are caused due to driver fatigue. To address the problem we propose a vision-based real-time driver fatigue detection system based on eye-tracking, which is an active safety system. Eye tracking is one of the key technologies, for, future driver assistance systems since human eyes contain much information about the driver's condition such as gaze, attention level, and fatigue level. Face and eyes of the driver are first localized and then marked in every frame obtained from the video source. The eyes are tracked in real time using correlation function with an automatically generated online template. Additionally, driver’s distraction and conversations with passengers during driving can lead to serious results. A real-time vision-based model for monitoring driver’s unsafe states, including fatigue state is proposed. A time-based eye glance to mitigate driver distraction is proposed