Open Collections

A model-based fusion technique for ocular motion sensing

University of British Columbia

Electrooculography (EOG) uses an electrical signal that records the cornea-retinal differential potential of the eyeball, which is linearly proportional to the eye movement. In EOG, the electrodes placed in the outer canthus and lateral frontalis record the horizontal and vertical eye movements. A main challenge in these signals is that the eye movement information is compressed in the 0-35Hz range of the full spectrum of the recording (0-250/1000/2000Hz) depending on the dynamic range of the device. Moreover, these signals, like any other bio-signals, are contaminated heavily by artifacts and noises such as electroencephalography (EEG), eye-lid motions, illumination drift, skin drift, impedance drop of electrode, eye blinks, head movements, and DC drift. Researchers have attempted to addressing these issues using traditional techniques, including finite impulse response (FIR) filters, morphological filters, time series motifs and wavelet-based approaches. However, most of these approaches have not been able to improve the performance significantly without compromising other features of the system such as the computational cost, real-time performance and time lag. This thesis presents a model-based fusion technique for ocular motion sensing to improve the signal quality. The developed approach is tested with five different model-based approaches (Brownian, constant velocity, constant acceleration, Westheimer, and linear reciprocal). Among these, the approach based on the linear reciprocal human eye model show a significant overall improvement in the signal(500-700% improvement in SNR w.r.t. FIR and 40-50% decrement in computational cost). Therefore, it is concluded that the approach based on the linear reciprocal model provides the best fit in the implementation of high quality eye tracking systems.

Text

2021-10-31

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/71920

Mechanical Engineering

University of British Columbia

UBCV

http://creativecommons.org/licenses/by-nc-nd/4.0/