Optimization of EOG-Based Horizontal Gaze Tracking Lightweight Deep Learning Algorithm in a Virtual Environment

Hyungwoo Jin, Woontack Woo

http://doi.org/10.5626/JOK.2024.51.2.184

This study presents an algorithm for real-time prediction of eye blinks with high accuracy and minimal parameters, utilizing a deep learning model. Previous eye-tracking algorithms relied on the assumption that the EOG(Electrooculography) signal from the pupil is linear with the angle [1,2]. However, the algorithm presented in this paper has an induction bias based on the data available. As a result, a lightweight deep learning network with layers like 1D CNN(Convolutional Neural Network) and residual block can make real-time prediction. In this study, we conducted an experiment using a device that could predicts eye movements, even while wearing an HMD(Head Mount Display) designed for virtual environments, via deep learning model predictions of eye blinks. Reconstruction of the eye using EOG data, as studied here, has the potential to yield realistic reconstructions. By researching up and down movements and extreme eye movements, the real-time nature of the avatar"s eyes may be utilized.