Head pose and gaze direction tracking for detecting a drowsy driver

This paper proposes a system that uses gaze direction tracking and head pose estimation to detect drowsiness of a driver. Head pose is estimated by calculating optic flow of the facial features, which are acquired with a corner detection algorithm. Analysis of the driver's head behavior leads to three moving components: nodding, shaking, and tilting. To track the gaze direction of the driver, we trace the center point of the pupil using CDF analysis and estimate the frequency of eye-movement.