Towards a Driver Monitoring System for Estimating Driver Situational Awareness

Abstract

Autonomous vehicle technology is rapidly developing but the current state-of-the-art still has limitations and requires frequent human intervention. However, handovers from an autonomous vehicle to a human driver are challenging because a human operator may be unaware of the vehicle surroundings during a handover which can lead to dangerous driving outcomes. There is presently an urgent need to develop advanced driver-assistance systems capable of monitoring driver situational awareness within an autonomous vehicle and intelligently handing-over control to a human driver in emergency situations. Towards this goal, in this paper we present the development and evaluation of a vision-based system that identifies visual cues of a driver's situational awareness including their: head pose, eye pupil position, average head movement rate and visual focus of attention.