Smooth-i

Abstract

Eye gaze for interaction is dependent on calibration. However, gaze calibration can deteriorate over time affecting the usability of the system. We propose to use motion matching of smooth pursuit eye movements and known motion on the display to determine when there is a drift in accuracy and use it as input for re-calibration. To explore this idea we developed Smooth-i, an algorithm that stores calibration points and updates them incrementally when inaccuracies are identified. To validate the accuracy of Smooth-i, we conducted a study with five participants and a remote eye tracker. A baseline calibration profile was used by all participants to test the accuracy of the Smooth-i re-calibration following interaction with moving targets. Results show that Smooth-i is able to manage re-calibration efficiently, updating the calibration profile only when inaccurate data samples are detected. CCS CONCEPTS • Human-centered computing → Interaction techniques;

Gaze behaviour on interacted objects during hand interaction in virtual reality for eye tracking calibration

“…Gaze calibration can also deteriorate and become inaccurate over time [Nyström et al 2013]. Work has therefore been done into re-calibration methods that asses the current calibration drift and only re-calibrate the parts that are needed, using smooth pursuits [Gomez and Gellersen 2018] or standard calibration points [Lander et al 2016]. However, while these methods are less timeconsuming than a full calibration, they still require the user to pause their current interaction to perform the needed re-calibration points or movements.…”

“…Therefore, alternative eye tracking calibration methods has become an extensive research field. Techniques that make the process unobtrusive or gamified [Flatla et al 2011;Gomez and Gellersen 2017;Renner et al 2011], using visual saliency models [Judd et al 2009;Sugano and Bulling 2015], smooth pursuit eye movements [Gomez and Gellersen 2017;Pfeuffer et al 2013;Tripathi and Guenter 2016] or by selecting optimal calibration points have been introduced [Gomez and Gellersen 2018;Lander et al 2016]. However, most commercial eye trackers still use the traditional calibration method due to its reliability.…”

Low-Cost Eye Tracking Calibration: A Knowledge-Based Study

“…To alleviate this drawback, in recent years, solutions have been proposed that seek to facilitate the calibration process, so that it becomes a simpler, more reliable and faster procedure to perform. Within this line of solutions, we find proposals such as [14][15][16] based on pursuit eye movement, which constitutes a more organic process. This is critical for the usability of future products, as pointed out by [17], and should be an aspect of concern in the development of new solutions.…”