Recent methods to automatically calibrate stationary eye trackers were shown to effectively reduce inherent calibration distortion. However, these methods require additional information, such as mouse clicks or on-screen content. We propose the first method that only requires users' eye movements to reduce calibration distortion in the background while users naturally look at an interface. Our method exploits that calibration distortion makes straight saccade trajectories appear curved between the saccadic start and end points. We show that this curving effect is systematic and the result of a distorted gaze projection plane. To mitigate calibration distortion, our method undistorts this plane by straightening saccade trajectories using image warping. We show that this approach improves over the common six-point calibration and is promising for reducing distortion. As such, it provides a non-intrusive solution to alleviating accuracy decrease of eye tracker during long-term use.
Proc. ACM International Symposium on Eye Tracking Research and Applications (ETRA)
year
2019
pages
1--10
teasercaption
Our method corrects the distorted gaze projection plane (black dash lines) to the undistorted gaze projection plane (purple dash lines) by minimizing the curvature of curvedsaccade trajectories (orange). By doing so, gaze points (red) are transformed closer to ground truth locations (green).
%0 Conference Paper
%1 huang19_etra
%A Huang, Michael Xuelin
%A Bulling, Andreas
%B Proc. ACM International Symposium on Eye Tracking Research and Applications (ETRA)
%D 2019
%K hcics vis
%P 1--10
%R 0.1145/3317956.3321553
%T SacCalib: Reducing Calibration Distortion for Stationary Eye Trackers Using Saccadic Eye Movements
%X Recent methods to automatically calibrate stationary eye trackers were shown to effectively reduce inherent calibration distortion. However, these methods require additional information, such as mouse clicks or on-screen content. We propose the first method that only requires users' eye movements to reduce calibration distortion in the background while users naturally look at an interface. Our method exploits that calibration distortion makes straight saccade trajectories appear curved between the saccadic start and end points. We show that this curving effect is systematic and the result of a distorted gaze projection plane. To mitigate calibration distortion, our method undistorts this plane by straightening saccade trajectories using image warping. We show that this approach improves over the common six-point calibration and is promising for reducing distortion. As such, it provides a non-intrusive solution to alleviating accuracy decrease of eye tracker during long-term use.
@inproceedings{huang19_etra,
abstract = {Recent methods to automatically calibrate stationary eye trackers were shown to effectively reduce inherent calibration distortion. However, these methods require additional information, such as mouse clicks or on-screen content. We propose the first method that only requires users' eye movements to reduce calibration distortion in the background while users naturally look at an interface. Our method exploits that calibration distortion makes straight saccade trajectories appear curved between the saccadic start and end points. We show that this curving effect is systematic and the result of a distorted gaze projection plane. To mitigate calibration distortion, our method undistorts this plane by straightening saccade trajectories using image warping. We show that this approach improves over the common six-point calibration and is promising for reducing distortion. As such, it provides a non-intrusive solution to alleviating accuracy decrease of eye tracker during long-term use.},
added-at = {2024-07-11T10:05:52.000+0200},
author = {Huang, Michael Xuelin and Bulling, Andreas},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/21754a3b2a6d1e7da73bb92b0cc13998b/hcics},
booktitle = {Proc. ACM International Symposium on Eye Tracking Research and Applications (ETRA)},
doi = {0.1145/3317956.3321553},
interhash = {8915ae42cf4b4406e41d21da3bd3b2c8},
intrahash = {1754a3b2a6d1e7da73bb92b0cc13998b},
keywords = {hcics vis},
pages = {1--10},
teasercaption = {Our method corrects the distorted gaze projection plane (black dash lines) to the undistorted gaze projection plane (purple dash lines) by minimizing the curvature of curvedsaccade trajectories (orange). By doing so, gaze points (red) are transformed closer to ground truth locations (green).},
timestamp = {2024-07-11T10:11:36.000+0200},
title = {SacCalib: Reducing Calibration Distortion for Stationary Eye Trackers Using Saccadic Eye Movements},
year = 2019
}