vix.ing · top · new · best · stats · spec

A Statistical Approach to Continuous Self-Calibrating Eye Gaze Tracking\n for Head-Mounted Virtual Reality Systems

2016/12/20 by Subarna Tripathi, Tripathi, Subarna, Brian Guenter +1
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gaze Tracking and Assistive Technology #Glaucoma and retinal disorders #Retinal Imaging and Analysis

paper · pdf · doi:10.48550/arxiv.1612.06919

openalex publication_date 2016/12/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a novel, automatic eye gaze tracking scheme inspired by smooth\npursuit eye motion while playing mobile games or watching virtual reality\ncontents. Our algorithm continuously calibrates an eye tracking system for a\nhead mounted display. This eliminates the need for an explicit calibration step\nand automatically compensates for small movements of the headset with respect\nto the head. The algorithm finds correspondences between corneal motion and\nscreen space motion, and uses these to generate Gaussian Process Regression\nmodels. A combination of those models provides a continuous mapping from\ncorneal position to screen space position. Accuracy is nearly as good as\nachieved with an explicit calibration step.\n

Related