An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions

Second order polynomials are commonly used for estimating the point-of-gaze in headmounted eye trackers. Studies in remote (desktop) eye trackers show that although some nonstandard 3 rd order polynomial models could provide better accuracy, high-order polynomials do not necessarily provide better results. Dierent than remote setups though, where gaze is estimated over a relatively narrow field-of-view surface (e.g. less than 30 X 20 degrees on t ypical computer displays), head-mounted gaze trackers (HMGT) are often desired to cover a relatively wider field-of-view to make sure that the gaze is detected in the scene image even for extreme eye angles. In this paper we investigate the behavior of the gaze estimation error distribution throughout the image of the scene camera when using polynomial functions. Using simulated scenarios, we describe effects of four different sources of error: interpolation, extrapolation, parallax, and radial distortion. We show that the use of third order polynomials result in more accurate gaze estimates in HMGT, and that the use of wide angle lenses might be beneficial in terms of error reduction.