Cargando…

High-Accuracy 3D Gaze Estimation with Efficient Recalibration for Head-Mounted Gaze Tracking Systems

The problem of 3D gaze estimation can be viewed as inferring the visual axes from eye images. It remains a challenge especially for the head-mounted gaze tracker (HMGT) with a simple camera setup due to the complexity of the human visual system. Although the mainstream regression-based methods could...

Descripción completa

Detalles Bibliográficos
Autores principales: Xia, Yang, Liang, Jiejunyi, Li, Quanlin, Xin, Peiyang, Zhang, Ning
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9231356/
https://www.ncbi.nlm.nih.gov/pubmed/35746135
http://dx.doi.org/10.3390/s22124357
_version_ 1784735318655631360
author Xia, Yang
Liang, Jiejunyi
Li, Quanlin
Xin, Peiyang
Zhang, Ning
author_facet Xia, Yang
Liang, Jiejunyi
Li, Quanlin
Xin, Peiyang
Zhang, Ning
author_sort Xia, Yang
collection PubMed
description The problem of 3D gaze estimation can be viewed as inferring the visual axes from eye images. It remains a challenge especially for the head-mounted gaze tracker (HMGT) with a simple camera setup due to the complexity of the human visual system. Although the mainstream regression-based methods could establish the mapping relationship between eye image features and the gaze point to calculate the visual axes, it may lead to inadequate fitting performance and appreciable extrapolation errors. Moreover, regression-based methods suffer from a degraded user experience because of the increased burden in recalibration procedures when slippage occurs between HMGT and head. To address these issues, a high-accuracy 3D gaze estimation method along with an efficient recalibration approach is proposed with head pose tracking in this paper. The two key parameters, eyeball center and camera optical center, are estimated in head frame with geometry-based method, so that a mapping relationship between two direction features is proposed to calculate the direction of the visual axis. As the direction features are formulated with the accurately estimated parameters, the complexity of mapping relationship could be reduced and a better fitting performance can be achieved. To prevent the noticeable extrapolation errors, direction features with uniform angular intervals for fitting the mapping are retrieved over human’s field of view. Additionally, an efficient single-point recalibration method is proposed with an updated eyeball coordinate system, which reduces the burden of calibration procedures significantly. Our experiment results show that the calibration and recalibration methods could improve the gaze estimation accuracy by 35 percent (from a mean error of 2.00 degrees to 1.31 degrees) and 30 percent (from a mean error of 2.00 degrees to 1.41 degrees), respectively, compared with the state-of-the-art methods.
format Online
Article
Text
id pubmed-9231356
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-92313562022-06-25 High-Accuracy 3D Gaze Estimation with Efficient Recalibration for Head-Mounted Gaze Tracking Systems Xia, Yang Liang, Jiejunyi Li, Quanlin Xin, Peiyang Zhang, Ning Sensors (Basel) Article The problem of 3D gaze estimation can be viewed as inferring the visual axes from eye images. It remains a challenge especially for the head-mounted gaze tracker (HMGT) with a simple camera setup due to the complexity of the human visual system. Although the mainstream regression-based methods could establish the mapping relationship between eye image features and the gaze point to calculate the visual axes, it may lead to inadequate fitting performance and appreciable extrapolation errors. Moreover, regression-based methods suffer from a degraded user experience because of the increased burden in recalibration procedures when slippage occurs between HMGT and head. To address these issues, a high-accuracy 3D gaze estimation method along with an efficient recalibration approach is proposed with head pose tracking in this paper. The two key parameters, eyeball center and camera optical center, are estimated in head frame with geometry-based method, so that a mapping relationship between two direction features is proposed to calculate the direction of the visual axis. As the direction features are formulated with the accurately estimated parameters, the complexity of mapping relationship could be reduced and a better fitting performance can be achieved. To prevent the noticeable extrapolation errors, direction features with uniform angular intervals for fitting the mapping are retrieved over human’s field of view. Additionally, an efficient single-point recalibration method is proposed with an updated eyeball coordinate system, which reduces the burden of calibration procedures significantly. Our experiment results show that the calibration and recalibration methods could improve the gaze estimation accuracy by 35 percent (from a mean error of 2.00 degrees to 1.31 degrees) and 30 percent (from a mean error of 2.00 degrees to 1.41 degrees), respectively, compared with the state-of-the-art methods. MDPI 2022-06-08 /pmc/articles/PMC9231356/ /pubmed/35746135 http://dx.doi.org/10.3390/s22124357 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Xia, Yang
Liang, Jiejunyi
Li, Quanlin
Xin, Peiyang
Zhang, Ning
High-Accuracy 3D Gaze Estimation with Efficient Recalibration for Head-Mounted Gaze Tracking Systems
title High-Accuracy 3D Gaze Estimation with Efficient Recalibration for Head-Mounted Gaze Tracking Systems
title_full High-Accuracy 3D Gaze Estimation with Efficient Recalibration for Head-Mounted Gaze Tracking Systems
title_fullStr High-Accuracy 3D Gaze Estimation with Efficient Recalibration for Head-Mounted Gaze Tracking Systems
title_full_unstemmed High-Accuracy 3D Gaze Estimation with Efficient Recalibration for Head-Mounted Gaze Tracking Systems
title_short High-Accuracy 3D Gaze Estimation with Efficient Recalibration for Head-Mounted Gaze Tracking Systems
title_sort high-accuracy 3d gaze estimation with efficient recalibration for head-mounted gaze tracking systems
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9231356/
https://www.ncbi.nlm.nih.gov/pubmed/35746135
http://dx.doi.org/10.3390/s22124357
work_keys_str_mv AT xiayang highaccuracy3dgazeestimationwithefficientrecalibrationforheadmountedgazetrackingsystems
AT liangjiejunyi highaccuracy3dgazeestimationwithefficientrecalibrationforheadmountedgazetrackingsystems
AT liquanlin highaccuracy3dgazeestimationwithefficientrecalibrationforheadmountedgazetrackingsystems
AT xinpeiyang highaccuracy3dgazeestimationwithefficientrecalibrationforheadmountedgazetrackingsystems
AT zhangning highaccuracy3dgazeestimationwithefficientrecalibrationforheadmountedgazetrackingsystems