Eye gaze tracking under natural head movements

Most available remote eye gaze trackers based on Pupil Cen-ter Corneal Reflection (PCCR) technique have two charac-teristics that prevent them from being widely used as an im-portant computer input device for human computer interac-tion. First, they must often be calibrated repeatedly for each individual; Second, they have low tolerance for head move-ments and require the user to hold the head uncomfortably still. In this paper, we propose a novel solution for the classi-cal PCCR technique that will simplify the calibration proce-dure and allow free head movements. The core of our method is to analytically obtain a head mapping function to compen-sate head movement. Specifically, the head mapping function allows to automatically map the eye movement measurement under an arbitrary head position to a reference head position so that the gaze can be estimated from the mapped eye mea-surement with respect to the reference head position. Fur-thermore, our method minimizes the calibration procedure to only one time for each individual. Our proposed method will significantly improve the usability of the eye gaze tracking technology, which is a major step for eye tracker to be ac-cepted as a natural computer input device.