Using Facial Analysis to Combat Distracted Driving in Autonomous Vehicles

Contrary to popular belief, current autonomous vehicles require an alert driver to be present to prevent injury or loss of life. This study proposes using facial analysis to determine whether a driver is focused and to notify them if they are not. A facial analysis system was developed to determine the orientation of the driver's head, measure the eye closure duration, and find signs of drowsiness. This was combined with an autonomous car model to simulate the integrated notification system. A series of tests using the facial orientation, eye closure, and drowsiness metrics were conducted to determine the system's functionality and limitations. In addition, a highway hypnosis detection method was separately developed and has yet to be validated. The prototype was able to detect a variety of distracted driving scenarios as well as implement countermeasures specific to autonomous cars.