Repository | Book | Chapter
(2015) Artificial life and computational intelligence, Dordrecht, Springer.
Point of regard from eye velocity in stereoscopic virtual environments based on intersections of hypothesis surfaces
Jake Fountain , Stephan K. Chalup
pp. 125-141
A new method is proposed for utilising scene information for stereo eye tracking in stereoscopic 3D virtual environments. The approach aims to improve gaze tracking accuracy and reduce the required user engagement with eye tracking calibration procedures. The approach derives absolute Point of Regard (POR) from the angular velocity of the eyes without user engaged calibration of drift. The method involves reduction of a hypothesis set for the 3D POR via a process of transformation during saccades and intersection with scene geometry during fixations. A basic implementation of this concept has been demonstrated in simulation using the depth buffer of the scene and a particle representation for the hypothesis set. Future research directions will focus on optimisation of the algorithm and improved utilisation of scene information. The technique shows promise in improving gaze tracking techniques in general, including relative paradigms such as electrooculography.
Publication details
DOI: 10.1007/978-3-319-14803-8_10
Full citation:
Fountain, J. , Chalup, S. K. (2015)., Point of regard from eye velocity in stereoscopic virtual environments based on intersections of hypothesis surfaces, in M. Randall (ed.), Artificial life and computational intelligence, Dordrecht, Springer, pp. 125-141.
This document is unfortunately not available for download at the moment.