Abstract

For optimal performance, gaze tracking systems are calibrated to match user characteristics. However, it can be difficult to collect accurate calibration data because human errors tend to dominate calibration data. This disclosure describes techniques of robust user gaze calibration for head-mounted devices (HMDs) using iteratively reweighted least squares (IRLS). A series of weighted least-squares fits of the data are performed, with the weight of a sample in an iteration being adjusted as a function of its residual error on the previous iteration. By re-weighting samples across iterations, IRLS enables the influence of a sample to vary continuously. The Cauchy loss function is used to reweight each sample between iterations, giving less emphasis to likely outliers in the calibration data. To find the optimal scale parameter for the Cauchy loss function, multiple solutions are generated, and the one with the maximum likelihood under the associated Cauchy distribution is used. The described calibration techniques learn the strongest possible signal given a small, noisy set of support examples and deterministically obtain the optimal user calibration parameters.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS