An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions

Second order polynomials are commonly used for estimating the point-of-gaze in head-mounted eye trackers. Studies in remote (desktop) eye trackers show that although some non-standard 3rd order polynomial models could provide better accuracy, high-order polynomials do not necessarily provide better...

Full description

Saved in:
Bibliographic Details
Main Authors: Diako Mardanbegi, Andrew T. N. Kurauchi, Carlos H. Morimoto
Format: Article
Language:English
Published: MDPI AG 2018-06-01
Series:Journal of Eye Movement Research
Subjects:
Online Access:https://bop.unibe.ch/JEMR/article/view/4183
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850178004179746816
author Diako Mardanbegi
Andrew T. N. Kurauchi
Carlos H. Morimoto
author_facet Diako Mardanbegi
Andrew T. N. Kurauchi
Carlos H. Morimoto
author_sort Diako Mardanbegi
collection DOAJ
description Second order polynomials are commonly used for estimating the point-of-gaze in head-mounted eye trackers. Studies in remote (desktop) eye trackers show that although some non-standard 3rd order polynomial models could provide better accuracy, high-order polynomials do not necessarily provide better results. Different than remote setups though, where gaze is estimated over a relatively narrow field-of-view surface (e.g. less than 30x20 degrees on typical computer displays), head-mounted gaze trackers (HMGT) are often desired to cover a relatively wider field-of-view to make sure that the gaze is detected in the scene image even for extreme eye angles. In this paper we investigate the behavior of the gaze estimation error distribution throughout the image of the scene camera when using polynomial functions. Using simulated scenarios, we describe effects of four different sources of error: interpolation, extrapolation, parallax, and radial distortion. We show that the use of third order polynomials result in more accurate gaze estimates in HMGT, and that the use of wide angle lenses might be beneficial in terms of error reduction.
format Article
id doaj-art-bb5db216d0694e7396e930ce3242328b
institution OA Journals
issn 1995-8692
language English
publishDate 2018-06-01
publisher MDPI AG
record_format Article
series Journal of Eye Movement Research
spelling doaj-art-bb5db216d0694e7396e930ce3242328b2025-08-20T02:18:50ZengMDPI AGJournal of Eye Movement Research1995-86922018-06-0111310.16910/jemr.11.3.5An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functionsDiako Mardanbegi0Andrew T. N. Kurauchi1Carlos H. Morimoto2Lancaster University, UKDepartment of Computer Science (IME), University of São Paulo, São Paulo, BrazilDepartment of Computer Science (IME), University of São Paulo, São Paulo, BrazilSecond order polynomials are commonly used for estimating the point-of-gaze in head-mounted eye trackers. Studies in remote (desktop) eye trackers show that although some non-standard 3rd order polynomial models could provide better accuracy, high-order polynomials do not necessarily provide better results. Different than remote setups though, where gaze is estimated over a relatively narrow field-of-view surface (e.g. less than 30x20 degrees on typical computer displays), head-mounted gaze trackers (HMGT) are often desired to cover a relatively wider field-of-view to make sure that the gaze is detected in the scene image even for extreme eye angles. In this paper we investigate the behavior of the gaze estimation error distribution throughout the image of the scene camera when using polynomial functions. Using simulated scenarios, we describe effects of four different sources of error: interpolation, extrapolation, parallax, and radial distortion. We show that the use of third order polynomials result in more accurate gaze estimates in HMGT, and that the use of wide angle lenses might be beneficial in terms of error reduction.https://bop.unibe.ch/JEMR/article/view/4183eye trackinggaze estimationHead-mounted eye trackingpolynomial map- pingerror distribution
spellingShingle Diako Mardanbegi
Andrew T. N. Kurauchi
Carlos H. Morimoto
An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions
Journal of Eye Movement Research
eye tracking
gaze estimation
Head-mounted eye tracking
polynomial map- ping
error distribution
title An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions
title_full An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions
title_fullStr An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions
title_full_unstemmed An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions
title_short An investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions
title_sort investigation of the distribution of gaze estimation errors in head mounted gaze trackers using polynomial functions
topic eye tracking
gaze estimation
Head-mounted eye tracking
polynomial map- ping
error distribution
url https://bop.unibe.ch/JEMR/article/view/4183
work_keys_str_mv AT diakomardanbegi aninvestigationofthedistributionofgazeestimationerrorsinheadmountedgazetrackersusingpolynomialfunctions
AT andrewtnkurauchi aninvestigationofthedistributionofgazeestimationerrorsinheadmountedgazetrackersusingpolynomialfunctions
AT carloshmorimoto aninvestigationofthedistributionofgazeestimationerrorsinheadmountedgazetrackersusingpolynomialfunctions
AT diakomardanbegi investigationofthedistributionofgazeestimationerrorsinheadmountedgazetrackersusingpolynomialfunctions
AT andrewtnkurauchi investigationofthedistributionofgazeestimationerrorsinheadmountedgazetrackersusingpolynomialfunctions
AT carloshmorimoto investigationofthedistributionofgazeestimationerrorsinheadmountedgazetrackersusingpolynomialfunctions