On Intelligent Driver Monitoring based on smart-devices

Autonomous driving is undoubtedly the future of the automotive industry. However, the complete migration to those technologies is not a short-term goal and it will not happen simultaneously throughout the world. Thus, existing technologies such the Driver State Monitoring systems are still relevant and could potentially foresee and prevent the occurrence of accidents. To this end, in this paper we present IRIS, a Driver State Monitoring Android application, which aims at providing a real-time monitoring and assessment of the drowsiness and inattention level of a driver. IRIS is based on an on-device machine learning analysis of incoming frames from the front camera of a smartphone and is able to notify the driver through a set of alerts about his/her status. A set of on-road experiments was conducted to validate the feasibility of the solution.