Using Pose Estimation to Map Gaze to Detected Fiducial Markers

We discuss several techniques for mapping the gaze point to fiducial markers detected in a video stream, as commonly used in Augmented Reality eye-tracking applications. Specifically, we focus on using the recovered camera rotation and translation determined by the apparent distortion of the marker. We exploit this to map Areas Of Interest (AOIs) in the plane relative to the given marker. This gives the advantage of not needing any more than a single marker. We also review how the recovered homography is transformed to the graphics world coordinates so that AOI visualization can be performed in world space instead of camera space