Gaze Tracking by Joint Head and Eye Pose Estimation Under Free Head Movement

Recent trends in the field of eye-gaze tracking have been shifting towards the estimation of gaze direction in everyday life settings, hence calling for methods that alleviate the constraints typically associated with existing methods, which limit their applicability in less controlled conditions. In this paper, we propose a method for eye-gaze estimation as a function of both eye and head pose components, without requiring prolonged user-cooperation prior to gaze estimation. Our method exploits the trajectories of salient feature trackers spread randomly over the face region for the estimation of the head rotation angles, which are subsequently used to drive a spherical eye-in-head rotation model that compensates for the changes in eye region appearance under head rotation. We investigate the validity of the proposed method on a publicly available data set.