Eye detection and tracking using IR source

Abstract:

A real-time prototype of drowsy driver monitoring system using infrared sources to detect and track the eyes is presented. A special hardware is designed for controlling the LEDs and real-time image acquisition. This method adopts the differential image to enhance the accuracy and robustness of eye detection. A Kalman filter is implemented to track the eyes. The experimental results are discussed. The system is non-invesive, fast and reasonably accurate.