EyeEcho: Continuous and Low-power Facial Expression Tracking on Glasses

TL;DR

EyeEcho is introduced, a minimally-obtrusive acoustic sensing system designed to enable glasses to continuously monitor facial expressions, and its potential to be deployed on a commercial-off-the-shelf (COTS) smartphone, offering real-time facial expression tracking.

Abstract

In this paper, we introduce EyeEcho, a minimally-obtrusive acoustic sensing system designed to enable glasses to continuously monitor facial expressions. It utilizes two pairs of speakers and microphones mounted on glasses, to emit encoded inaudible acoustic signals directed towards the face, capturing subtle skin deformations associated with facial expressions. The reflected signals are processed through a customized machine-learning pipeline to estimate full facial movements. EyeEcho samples at 83.3 Hz with a relatively low power consumption of 167 mW. Our user study involving 12 participants demonstrates that, with just four minutes of training data, EyeEcho achieves highly accurate tracking performance across different real-world scenarios, including sitting, walking, and after remounting the devices. Additionally, a semi-in-the-wild study involving 10 participants further validates EyeEcho's performance in naturalistic scenarios while participants engage in various daily activities. Finally, we showcase EyeEcho's potential to be deployed on a commercial-off-the-shelf (COTS) smartphone, offering real-time facial expression tracking.

Figures (21)

• Figure 1: Designed Facial Expressions and Corresponding Differential Echo Profiles.
• Figure 2: Design of Hardware and Glasses Form Factor.
• Figure 3: Overview of EyeEcho System.
• Figure 4: Comparison of Differential Echo Profiles of Three Facial Movements.
• Figure 5: The Degree of Deformation of Different Facial Parts when Performing Different Facial Expressions to the Most Extreme State.