Towards pervasive gaze tracking with low-level image features
Yanxia Zhang, Andreas Bulling, Hans Gellersen
Proc. ACM International Symposium on Eye Tracking Research and Applications (ETRA), pp. 261-264, 2012.
Abstract
We contribute a novel gaze estimation technique, which is adaptable for person-independent applications. In a study with 17 participants, using a standard webcam, we recorded the subjects’ left eye images for different gaze locations. From these images, we extracted five types of basic visual features. We then sub-selected a set of features with minimum Redundancy Maximum Relevance (mRMR) for the input of a 2-layer regression neural network for estimating the subjects’ gaze. We investigated the effect of different visual features on the accuracy of gaze estimation. Using machine learning techniques, by combing different features, we achieved average gaze estimation error of 3.44° horizontally and 1.37° vertically for person-dependent.Links
Paper: zhang12_etra.pdf
BibTeX
@inproceedings{zhang12_etra,
author = {Zhang, Yanxia and Bulling, Andreas and Gellersen, Hans},
title = {Towards pervasive gaze tracking with low-level image features},
booktitle = {Proc. ACM International Symposium on Eye Tracking Research and Applications (ETRA)},
year = {2012},
pages = {261-264},
doi = {10.1145/2168556.2168611}
}
