A non-intrusive Kalman filter-based tracker for pursuit eye movement

TitleA non-intrusive Kalman filter-based tracker for pursuit eye movement
Publication TypeConference Papers
Year of Publication2002
AuthorsAbd-Almageed W, Fadali MS, Bebis G
Conference NameAmerican Control Conference, 2002. Proceedings of the 2002
Date Published2002///
ISBN Number0-7803-7298-0
KeywordsApplication software, characterization, Computer vision, Current measurement, deterministic component, Electric variables measurement, eye position estimation, eye tracking, gaze tracking, Human computer interaction, Kalman filter, Kalman filters, Lenses, Motion estimation, Optical reflection, pursuit eye movement, pursuit motion, random component, Skin, tracking

In this paper, we introduce a new non-intrusive approach to estimating the eye position during pursuit motion of the eye. We introduce a new characterization for the pursuit eye movement. Our characterization is based on the decomposition of the pursuit eye motion into a deterministic component and random component. We use a discrete Kalman filter to estimate the random component and calculate the deterministic component. We add the two components to obtain an estimate of the eye position. Simulation results are provided to illustrate the eye position estimation.