Cornell University researchers unveil GazeTrak, a pair of AI-powered sonar smartglasses capable of detecting facial expressions and your gaze using acoustic signals.
GazeTrak consists of one speaker and four microphones placed around within each eye frame to bounce and pick up soundwaves from the eyeball and the area around the eyes. The sound signals received are then sent to a customized deep learning pipeline that uses artificial intelligence to continuously infer the direction of the person’s gaze.
- #1 SELLING AI GLASSES - Move effortlessly through life with Ray-Ban Meta glasses. Capture photos and videos, listen to music, make hands-free calls or...
- CAPTURE WHAT YOU SEE AND HEAR HANDS-FREE - Capture exactly what you see and hear with an ultra-wide 12 MP camera and a five-mic system. Livestream it...
- LISTEN WITH OPEN-EAR AUDIO — Listen to music and more with discreet open-ear speakers that deliver rich, quality audio without blocking...
The privacy concerns associated with systems that use video will become more and more important as VR/AR headsets become much smaller and, ultimately, similar to today’s smartglasses. Because both technologies are so small and power-efficient, they will be a perfect match for lightweight, smart AR glasses,” said François Guimbretière, professor of information science in Cornell Bowers CIS.
