Natural pursuit calibration: using motion trajectories for unobtrusive calibration of mobile eye trackers

Abstract

Although, gaze-based interaction has been investigated since the 1980s and remains a promising concept to support universal interaction within distributed IoT environments, main challenges like the Midas touch problem [6] or calibration are still frequent topics of research. In this work we present Natural Pursuit Calibration, a comfortable, unobtrusive technique enabling ongoing attention detection and eye tracker calibration in a real-world context. The user is able to perform calibration, without a digital user interface, artificial annotation of the environment and without assistance, by simply following any arbitrary moving target. Due to the characteristics of the calibration process it can be executed simultaneously to any primary task, without active user participation, resulting in a frequently updated calibration model.