Unsupervised clustering of EOG as a viable substitute for optical eye tracking

Nina Flad, Tatiana Fomina, Heinrich Bulthoff, Lewis L. Chuang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Eye-movements are typically measured with video cameras and image recognition algorithms. Unfortunately, these systems are susceptible to changes in illumination during measurements. Electrooculography (EOG) is another approach for measuring eye-movements that does not suffer from the same weakness. Here, we introduce and compare two methods that allow us to extract the dwells of our participants from EOG signals under presentation conditions that are too difficult for optical eye tracking. The first method is unsupervised and utilizes density-based clustering. The second method combines the optical eye-tracker’s methods to determine fixations and saccades with unsupervised clustering. Our results show that EOG can serve as a sufficiently precise and robust substitute for optical eye tracking, especially in studies with changing lighting conditions. Moreover, EOG can be recorded alongside electroencephalography (EEG) without additional effort.

Original languageEnglish
Title of host publicationEye Tracking and Visualization - Foundations, Techniques, and Applications, ETVIS 2015
PublisherSpringer Heidelberg
Pages151-167
Number of pages17
ISBN (Print)9783319470238
DOIs
Publication statusPublished - 2017
Externally publishedYes
Event1st Workshop on Eye Tracking and Visualization, ETVIS 2015 - [state] IL, United States
Duration: 2015 Oct 252015 Oct 25

Publication series

NameMathematics and Visualization
ISSN (Print)16123786
ISSN (Electronic)2197666X

Other

Other1st Workshop on Eye Tracking and Visualization, ETVIS 2015
CountryUnited States
City[state] IL
Period15/10/2515/10/25

Fingerprint

Electrooculography
Unsupervised Clustering
Eye Tracking
Substitute
Eye movements
Eye Movements
Lighting
Saccades
Electroencephalography
Image recognition
Image Recognition
Fixation
Recognition Algorithm
Video cameras
Illumination
Camera
Clustering

ASJC Scopus subject areas

  • Modelling and Simulation
  • Geometry and Topology
  • Computer Graphics and Computer-Aided Design
  • Applied Mathematics

Cite this

Flad, N., Fomina, T., Bulthoff, H., & Chuang, L. L. (2017). Unsupervised clustering of EOG as a viable substitute for optical eye tracking. In Eye Tracking and Visualization - Foundations, Techniques, and Applications, ETVIS 2015 (pp. 151-167). (Mathematics and Visualization). Springer Heidelberg. https://doi.org/10.1007/978-3-319-47024-5_9

Unsupervised clustering of EOG as a viable substitute for optical eye tracking. / Flad, Nina; Fomina, Tatiana; Bulthoff, Heinrich; Chuang, Lewis L.

Eye Tracking and Visualization - Foundations, Techniques, and Applications, ETVIS 2015. Springer Heidelberg, 2017. p. 151-167 (Mathematics and Visualization).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Flad, N, Fomina, T, Bulthoff, H & Chuang, LL 2017, Unsupervised clustering of EOG as a viable substitute for optical eye tracking. in Eye Tracking and Visualization - Foundations, Techniques, and Applications, ETVIS 2015. Mathematics and Visualization, Springer Heidelberg, pp. 151-167, 1st Workshop on Eye Tracking and Visualization, ETVIS 2015, [state] IL, United States, 15/10/25. https://doi.org/10.1007/978-3-319-47024-5_9
Flad N, Fomina T, Bulthoff H, Chuang LL. Unsupervised clustering of EOG as a viable substitute for optical eye tracking. In Eye Tracking and Visualization - Foundations, Techniques, and Applications, ETVIS 2015. Springer Heidelberg. 2017. p. 151-167. (Mathematics and Visualization). https://doi.org/10.1007/978-3-319-47024-5_9
Flad, Nina ; Fomina, Tatiana ; Bulthoff, Heinrich ; Chuang, Lewis L. / Unsupervised clustering of EOG as a viable substitute for optical eye tracking. Eye Tracking and Visualization - Foundations, Techniques, and Applications, ETVIS 2015. Springer Heidelberg, 2017. pp. 151-167 (Mathematics and Visualization).
@inproceedings{21667fe131c243aab630a2ec9715ed9f,
title = "Unsupervised clustering of EOG as a viable substitute for optical eye tracking",
abstract = "Eye-movements are typically measured with video cameras and image recognition algorithms. Unfortunately, these systems are susceptible to changes in illumination during measurements. Electrooculography (EOG) is another approach for measuring eye-movements that does not suffer from the same weakness. Here, we introduce and compare two methods that allow us to extract the dwells of our participants from EOG signals under presentation conditions that are too difficult for optical eye tracking. The first method is unsupervised and utilizes density-based clustering. The second method combines the optical eye-tracker’s methods to determine fixations and saccades with unsupervised clustering. Our results show that EOG can serve as a sufficiently precise and robust substitute for optical eye tracking, especially in studies with changing lighting conditions. Moreover, EOG can be recorded alongside electroencephalography (EEG) without additional effort.",
author = "Nina Flad and Tatiana Fomina and Heinrich Bulthoff and Chuang, {Lewis L.}",
year = "2017",
doi = "10.1007/978-3-319-47024-5_9",
language = "English",
isbn = "9783319470238",
series = "Mathematics and Visualization",
publisher = "Springer Heidelberg",
pages = "151--167",
booktitle = "Eye Tracking and Visualization - Foundations, Techniques, and Applications, ETVIS 2015",

}

TY - GEN

T1 - Unsupervised clustering of EOG as a viable substitute for optical eye tracking

AU - Flad, Nina

AU - Fomina, Tatiana

AU - Bulthoff, Heinrich

AU - Chuang, Lewis L.

PY - 2017

Y1 - 2017

N2 - Eye-movements are typically measured with video cameras and image recognition algorithms. Unfortunately, these systems are susceptible to changes in illumination during measurements. Electrooculography (EOG) is another approach for measuring eye-movements that does not suffer from the same weakness. Here, we introduce and compare two methods that allow us to extract the dwells of our participants from EOG signals under presentation conditions that are too difficult for optical eye tracking. The first method is unsupervised and utilizes density-based clustering. The second method combines the optical eye-tracker’s methods to determine fixations and saccades with unsupervised clustering. Our results show that EOG can serve as a sufficiently precise and robust substitute for optical eye tracking, especially in studies with changing lighting conditions. Moreover, EOG can be recorded alongside electroencephalography (EEG) without additional effort.

AB - Eye-movements are typically measured with video cameras and image recognition algorithms. Unfortunately, these systems are susceptible to changes in illumination during measurements. Electrooculography (EOG) is another approach for measuring eye-movements that does not suffer from the same weakness. Here, we introduce and compare two methods that allow us to extract the dwells of our participants from EOG signals under presentation conditions that are too difficult for optical eye tracking. The first method is unsupervised and utilizes density-based clustering. The second method combines the optical eye-tracker’s methods to determine fixations and saccades with unsupervised clustering. Our results show that EOG can serve as a sufficiently precise and robust substitute for optical eye tracking, especially in studies with changing lighting conditions. Moreover, EOG can be recorded alongside electroencephalography (EEG) without additional effort.

UR - http://www.scopus.com/inward/record.url?scp=85012288970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012288970&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-47024-5_9

DO - 10.1007/978-3-319-47024-5_9

M3 - Conference contribution

AN - SCOPUS:85012288970

SN - 9783319470238

T3 - Mathematics and Visualization

SP - 151

EP - 167

BT - Eye Tracking and Visualization - Foundations, Techniques, and Applications, ETVIS 2015

PB - Springer Heidelberg

ER -