Search papers, labs, and topics across Lattice.
The authors construct a marker-free gaze tracking system for standard monocular webcams by coupling iris localization with head pose estimated via optical depth from defocus. This approach directly addresses the sensitivity of monocular appearance-based gaze trackers to head movement and distance variations without relying on active depth sensors or calibration markers. Evaluated across varying user-to-screen distances, mapping an 8-dimensional pose and displacement vector through variational Bayesian multinomial logistic regression outperformed five existing baseline methods.
Commodity laptop webcams can infer accurate, distance-invariant 3D gaze by extracting passive depth-from-defocus cues without dedicated RGB-D hardware or external markers.
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.
