Estimation of a focused object using a corneal surface image for eye-based interaction

Researchers are considering the use of eye tracking in head-mounted camera systems, such as Google’s Project Glass. Typical methods require detailed calibration in advance, but long periods of use disrupt the calibration record between the eye and the scene camera. In addition, the focused object mi...

Full description

Saved in:
Bibliographic Details
Main Authors: Kentaro Takemura, Tomohisa Yamakawa, Jun Takamatsu, Tsukasa Ogasawara
Format: Article
Language:English
Published: MDPI AG 2014-03-01
Series:Journal of Eye Movement Research
Subjects:
Online Access:https://bop.unibe.ch/JEMR/article/view/2382
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849413309207412736
author Kentaro Takemura
Tomohisa Yamakawa
Jun Takamatsu
Tsukasa Ogasawara
author_facet Kentaro Takemura
Tomohisa Yamakawa
Jun Takamatsu
Tsukasa Ogasawara
author_sort Kentaro Takemura
collection DOAJ
description Researchers are considering the use of eye tracking in head-mounted camera systems, such as Google’s Project Glass. Typical methods require detailed calibration in advance, but long periods of use disrupt the calibration record between the eye and the scene camera. In addition, the focused object might not be estimated even if the point-of-regard is estimated using a portable eye-tracker. Therefore, we propose a novel method for estimating the object that a user is focused upon, where an eye camera captures the reflection on the corneal surface. Eye and environment information can be extracted from the corneal surface image simultaneously. We use inverse ray tracing to rectify the reflected image and a scale-invariant feature transform to estimate the object where the point-of-regard is located. Unwarped images can also be generated continuously from corneal surface images. We consider that our proposed method could be applied to a guidance system and we confirmed the feasibility of this application in experiments that estimated the object focused upon and the point-of-regard.
format Article
id doaj-art-6ededb00d26145a39bcd2851733772ae
institution Kabale University
issn 1995-8692
language English
publishDate 2014-03-01
publisher MDPI AG
record_format Article
series Journal of Eye Movement Research
spelling doaj-art-6ededb00d26145a39bcd2851733772ae2025-08-20T03:34:09ZengMDPI AGJournal of Eye Movement Research1995-86922014-03-017310.16910/jemr.7.3.4Estimation of a focused object using a corneal surface image for eye-based interactionKentaro Takemura0Tomohisa Yamakawa1Jun Takamatsu2Tsukasa Ogasawara3Tokai University, JapanNara Institute of Science and Technology, JapanNara Institute of Science and Technology, JapanNara Institute of Science and Technology, JapanResearchers are considering the use of eye tracking in head-mounted camera systems, such as Google’s Project Glass. Typical methods require detailed calibration in advance, but long periods of use disrupt the calibration record between the eye and the scene camera. In addition, the focused object might not be estimated even if the point-of-regard is estimated using a portable eye-tracker. Therefore, we propose a novel method for estimating the object that a user is focused upon, where an eye camera captures the reflection on the corneal surface. Eye and environment information can be extracted from the corneal surface image simultaneously. We use inverse ray tracing to rectify the reflected image and a scale-invariant feature transform to estimate the object where the point-of-regard is located. Unwarped images can also be generated continuously from corneal surface images. We consider that our proposed method could be applied to a guidance system and we confirmed the feasibility of this application in experiments that estimated the object focused upon and the point-of-regard.https://bop.unibe.ch/JEMR/article/view/2382corneal surface imagefocused objectpoint of regard
spellingShingle Kentaro Takemura
Tomohisa Yamakawa
Jun Takamatsu
Tsukasa Ogasawara
Estimation of a focused object using a corneal surface image for eye-based interaction
Journal of Eye Movement Research
corneal surface image
focused object
point of regard
title Estimation of a focused object using a corneal surface image for eye-based interaction
title_full Estimation of a focused object using a corneal surface image for eye-based interaction
title_fullStr Estimation of a focused object using a corneal surface image for eye-based interaction
title_full_unstemmed Estimation of a focused object using a corneal surface image for eye-based interaction
title_short Estimation of a focused object using a corneal surface image for eye-based interaction
title_sort estimation of a focused object using a corneal surface image for eye based interaction
topic corneal surface image
focused object
point of regard
url https://bop.unibe.ch/JEMR/article/view/2382
work_keys_str_mv AT kentarotakemura estimationofafocusedobjectusingacornealsurfaceimageforeyebasedinteraction
AT tomohisayamakawa estimationofafocusedobjectusingacornealsurfaceimageforeyebasedinteraction
AT juntakamatsu estimationofafocusedobjectusingacornealsurfaceimageforeyebasedinteraction
AT tsukasaogasawara estimationofafocusedobjectusingacornealsurfaceimageforeyebasedinteraction