Non-Intrusive Gaze Tracking Using Artificial Neural Networks

Dean A. Pomerleau and Shumeet Baluja

Viewed in the context of machine vision, successful gaze tracking requires techniques to handle imprecise data, noisy images, and a possibly infinitely large image set. The most accurate gaze tracking has come from intrusive systems which either require the subject to keep their head stable, through chin rests etc., or systems which require the user to wear cumbersome equipment, ranging from special contact lenses to a camera placed on the user’s head to monitor the eye. The system described here attempts non-intrusive gaze tracking, in which the user is neither required to wear any special equipment, nor required to keep his head still.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.