Surface Recalibration as a New Method Improving Gaze-Based Human-Computer Interaction

Cezary Biele, Paweł Kobyliński

2018 W: Intelligent Human Systems Integration : Proceedings of the 1st International Conference on Intelligent Human Systems Integration (IHSI 2018): Integrating People and Intelligent Systems, January 7–9, 2018, Dubai, United Arab Emirates / Tareq Ahram, Waldemar Karwowski ; Cham: Springer, s. 197-202

The main problem of a gaze-based interaction is the correct mapping from an output of eye tracker to a gaze point. In this paper we propose a new method of improvement of the gaze-based human computer interaction using: (a) a procedure to estimate the error introduced by screen tracking algorithms (surface recalibration) and (b) using the obtained error data to transform the eye-tracking data in real-time (data transformation). In order to test the developed method, we conducted initial pilot study using simple target pointing procedure. Initial data gathered during these tests shows that our method may increase the effectiveness (measured as target pointing speed) of the gaze-based interaction using mobile eye trackers. In future studies it is worth testing this method using stationary eye trackers as it can be an effective way of facilitating gaze-based interaction by counteracting calibration errors that would yield gaze-based system unusable.