Real time eye tracking and detection- A driving assistance system

Abstract

Distraction, drowsiness, and fatigue are the main factors of car accidents recently. To solve such problems, an Eye-tracking system based on camera is proposed in this paper. The system detects the driver's Distraction or sleepiness and gives an alert to the driver as an assistance system. The camera best position is chosen to be on the dashboard without distracting the driver. The system will detect the driver's face and eyes by using Viola-Jones Algorithm that includes Haar Classifiers that showed significant advantages regarding processing time and correct detection algorithms. A prepared scenario is tested in a designed simulator that is used to simulate real driving conditions in an indoor environment. The system is added in real-vehicle and tested in an outdoor environment. Whenever the system detects the distraction or sleepiness of the driver, the driver will be alerted through a displayed message on a screen and an audible sound for more attention. The results show the accuracy of the system with a correct detection rate of 82% for indoor tests and 72.8 % for the outdoor environment.