Marker-free eye-gaze tracking using single camera and defocus depth
Marker-free eye-gaze estimation using a single image and depth from defocus
Computer Vision and Pattern Recognition
Summary
Tracking where someone is looking usually needs special markers or multiple cameras, but this paper shows a way to do it with just one regular 2D camera, like a laptop webcam. The method figures out where the iris is and the head’s position by looking at how out-of-focus the image is (depth from defocus). Then, it uses a smart math model to connect these features to where the person is looking on a screen. The authors tested this approach against other methods and found it worked well without needing any extra markers.
What this means in practice
- •For laptop manufacturers: Add eye-gaze tracking to laptops without requiring extra hardware or markers on users for improved user interaction.$Commercial implications: Enables built-in gaze tracking on standard laptops, opening opportunities for new user interface features and accessibility tools.
- •For assistive technology developers: Create eye-controlled interfaces for people with mobility challenges using a simple single-camera setup without extra devices.
Authors
David Hurtubise-Martin, Feriel Fass, Djemel Ziou, Marie-Flavie Auclair-Fortier
Abstract
This paper presents a marker-free eye-gaze estimation approach using a single 2D camera, such as an integrated laptop webcam. The gaze-related features are estimated from iris localization and head pose estimated by using depth from defocus. A variational Bayesian multinomial logistic regression framework is used as mapping from the estimated features to the position of regard, based on an 8-dimensional feature vector of head-pose and iris-displacement parameters. No external marker is needed. Experiments were conducted by estimating the gaze of people watching a computer screen at different distances and compared against five existing methods. The obtained scores demonstrate the effectiveness of the proposed approach.