Cargando…

Low-Cost Eye Tracking Calibration: A Knowledge-Based Study †

Subject calibration has been demonstrated to improve the accuracy in high-performance eye trackers. However, the true weight of calibration in off-the-shelf eye tracking solutions is still not addressed. In this work, a theoretical framework to measure the effects of calibration in deep learning-bas...

Descripción completa

Detalles Bibliográficos
Autores principales: Garde, Gonzalo, Larumbe-Bergera, Andoni, Bossavit, Benoît, Porta, Sonia, Cabeza, Rafael, Villanueva, Arantxa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347006/
https://www.ncbi.nlm.nih.gov/pubmed/34372344
http://dx.doi.org/10.3390/s21155109
_version_ 1783734979675553792
author Garde, Gonzalo
Larumbe-Bergera, Andoni
Bossavit, Benoît
Porta, Sonia
Cabeza, Rafael
Villanueva, Arantxa
author_facet Garde, Gonzalo
Larumbe-Bergera, Andoni
Bossavit, Benoît
Porta, Sonia
Cabeza, Rafael
Villanueva, Arantxa
author_sort Garde, Gonzalo
collection PubMed
description Subject calibration has been demonstrated to improve the accuracy in high-performance eye trackers. However, the true weight of calibration in off-the-shelf eye tracking solutions is still not addressed. In this work, a theoretical framework to measure the effects of calibration in deep learning-based gaze estimation is proposed for low-resolution systems. To this end, features extracted from the synthetic U2Eyes dataset are used in a fully connected network in order to isolate the effect of specific user’s features, such as kappa angles. Then, the impact of system calibration in a real setup employing I2Head dataset images is studied. The obtained results show accuracy improvements over 50%, probing that calibration is a key process also in low-resolution gaze estimation scenarios. Furthermore, we show that after calibration accuracy values close to those obtained by high-resolution systems, in the range of 0.7°, could be theoretically obtained if a careful selection of image features was performed, demonstrating significant room for improvement for off-the-shelf eye tracking systems.
format Online
Article
Text
id pubmed-8347006
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83470062021-08-08 Low-Cost Eye Tracking Calibration: A Knowledge-Based Study † Garde, Gonzalo Larumbe-Bergera, Andoni Bossavit, Benoît Porta, Sonia Cabeza, Rafael Villanueva, Arantxa Sensors (Basel) Article Subject calibration has been demonstrated to improve the accuracy in high-performance eye trackers. However, the true weight of calibration in off-the-shelf eye tracking solutions is still not addressed. In this work, a theoretical framework to measure the effects of calibration in deep learning-based gaze estimation is proposed for low-resolution systems. To this end, features extracted from the synthetic U2Eyes dataset are used in a fully connected network in order to isolate the effect of specific user’s features, such as kappa angles. Then, the impact of system calibration in a real setup employing I2Head dataset images is studied. The obtained results show accuracy improvements over 50%, probing that calibration is a key process also in low-resolution gaze estimation scenarios. Furthermore, we show that after calibration accuracy values close to those obtained by high-resolution systems, in the range of 0.7°, could be theoretically obtained if a careful selection of image features was performed, demonstrating significant room for improvement for off-the-shelf eye tracking systems. MDPI 2021-07-28 /pmc/articles/PMC8347006/ /pubmed/34372344 http://dx.doi.org/10.3390/s21155109 Text en © 2021 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
Garde, Gonzalo
Larumbe-Bergera, Andoni
Bossavit, Benoît
Porta, Sonia
Cabeza, Rafael
Villanueva, Arantxa
Low-Cost Eye Tracking Calibration: A Knowledge-Based Study †
title Low-Cost Eye Tracking Calibration: A Knowledge-Based Study †
title_full Low-Cost Eye Tracking Calibration: A Knowledge-Based Study †
title_fullStr Low-Cost Eye Tracking Calibration: A Knowledge-Based Study †
title_full_unstemmed Low-Cost Eye Tracking Calibration: A Knowledge-Based Study †
title_short Low-Cost Eye Tracking Calibration: A Knowledge-Based Study †
title_sort low-cost eye tracking calibration: a knowledge-based study †
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347006/
https://www.ncbi.nlm.nih.gov/pubmed/34372344
http://dx.doi.org/10.3390/s21155109
work_keys_str_mv AT gardegonzalo lowcosteyetrackingcalibrationaknowledgebasedstudy
AT larumbebergeraandoni lowcosteyetrackingcalibrationaknowledgebasedstudy
AT bossavitbenoit lowcosteyetrackingcalibrationaknowledgebasedstudy
AT portasonia lowcosteyetrackingcalibrationaknowledgebasedstudy
AT cabezarafael lowcosteyetrackingcalibrationaknowledgebasedstudy
AT villanuevaarantxa lowcosteyetrackingcalibrationaknowledgebasedstudy