Free HTML5 by Under Review at CHI

Low-Profile Facial Motion Tracker

In this project, we demonstrate a novel system that tracks a user’s facial motions using two wide-angle cameras mounted discretely at the corners of eyeglasses. Avoiding the usage of cameras extended in-front of the face greatly improves the feasibility to integrate full-face tracking into a low-profile form factor. We demonstrate that a neural network-based model processing the wide-angle cameras can run in real-time at 24 fps on a mobile GPU and track independent facial movement for different parts of the face with a generalized global model. Using a short 2 minute personalization, the system improves it’s tracking performance by 13.5%.