Algorithmic gaze classification for mobile eye-tracking

Daniel Müller; David Mann

doi:10.1145/3450341.3458886

Algorithmic gaze classification for mobile eye-tracking

Daniel Müller^*, David Mann

^*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Mobile eye tracking traditionally requires gaze to be coded manually. We introduce an open-source Python package (GazeClassify) that algorithmically annotates mobile eye tracking data for the study of human interactions. Instead of manually identifying objects and identifying if gaze is directed towards an area of interest, computer vision algorithms are used for the identification and segmentation of human bodies. To validate the algorithm, mobile eye tracking data from short combat sport sequences were analyzed. The performance of the algorithm was compared against three manual raters. The algorithm performed with substantial reliability in comparison to the manual raters when it came to annotating which area of interest gaze was closest to. However, the algorithm was more conservative than the manual raters for classifying if gaze was directed towards an object of interest. The algorithmic approach represents a viable and promising means for automating gaze classification for mobile eye tracking.

Original language	English
Title of host publication	ETRA 2021 Adjunct
Subtitle of host publication	ACM Symposium on Eye Tracking Research and Applications [Proceedings]
Editors	Stephen N. Spencer
Publisher	Association for Computing Machinery
Number of pages	4
ISBN (Electronic)	9781450383578
DOIs	https://doi.org/10.1145/3450341.3458886
Publication status	Published - May 2021
Event	2021 ACM Symposium on Eye Tracking Research and Applications, ETRA 2021 - Virtual, Online, United Kingdom Duration: 24 May 2021 → 27 May 2021

Publication series

Name	Eye Tracking Research and Applications Symposium (ETRA)
Volume	PartF169260

Conference

Conference	2021 ACM Symposium on Eye Tracking Research and Applications, ETRA 2021
Country/Territory	United Kingdom
City	Virtual, Online
Period	24/05/21 → 27/05/21

Bibliographical note

Publisher Copyright:
© 2021 ACM.

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Keywords

algorithmic eye-Tracking
computer vision
image segmentation
open source software

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3450341.3458886

Persistent URL (handle)

Persistent link

Cite this

@inproceedings{5aa517f29b7d43d7ab14c488199c265c,

title = "Algorithmic gaze classification for mobile eye-tracking",

abstract = "Mobile eye tracking traditionally requires gaze to be coded manually. We introduce an open-source Python package (GazeClassify) that algorithmically annotates mobile eye tracking data for the study of human interactions. Instead of manually identifying objects and identifying if gaze is directed towards an area of interest, computer vision algorithms are used for the identification and segmentation of human bodies. To validate the algorithm, mobile eye tracking data from short combat sport sequences were analyzed. The performance of the algorithm was compared against three manual raters. The algorithm performed with substantial reliability in comparison to the manual raters when it came to annotating which area of interest gaze was closest to. However, the algorithm was more conservative than the manual raters for classifying if gaze was directed towards an object of interest. The algorithmic approach represents a viable and promising means for automating gaze classification for mobile eye tracking. ",

keywords = "algorithmic eye-Tracking, computer vision, image segmentation, open source software",

author = "Daniel M{\"u}ller and David Mann",

note = "Publisher Copyright: {\textcopyright} 2021 ACM. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 2021 ACM Symposium on Eye Tracking Research and Applications, ETRA 2021 ; Conference date: 24-05-2021 Through 27-05-2021",

year = "2021",

month = may,

doi = "10.1145/3450341.3458886",

language = "English",

series = "Eye Tracking Research and Applications Symposium (ETRA)",

publisher = "Association for Computing Machinery",

editor = "Spencer, {Stephen N.}",

booktitle = "ETRA 2021 Adjunct",

}

Müller, D & Mann, D 2021, Algorithmic gaze classification for mobile eye-tracking. in SN Spencer (ed.), ETRA 2021 Adjunct: ACM Symposium on Eye Tracking Research and Applications [Proceedings]., 12, Eye Tracking Research and Applications Symposium (ETRA), vol. PartF169260, Association for Computing Machinery, 2021 ACM Symposium on Eye Tracking Research and Applications, ETRA 2021, Virtual, Online, United Kingdom, 24/05/21. https://doi.org/10.1145/3450341.3458886

Algorithmic gaze classification for mobile eye-tracking. / Müller, Daniel ; Mann, David.
ETRA 2021 Adjunct: ACM Symposium on Eye Tracking Research and Applications [Proceedings]. ed. / Stephen N. Spencer. Association for Computing Machinery, 2021. 12 (Eye Tracking Research and Applications Symposium (ETRA); Vol. PartF169260).

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Algorithmic gaze classification for mobile eye-tracking

AU - Müller, Daniel

AU - Mann, David

PY - 2021/5

Y1 - 2021/5

N2 - Mobile eye tracking traditionally requires gaze to be coded manually. We introduce an open-source Python package (GazeClassify) that algorithmically annotates mobile eye tracking data for the study of human interactions. Instead of manually identifying objects and identifying if gaze is directed towards an area of interest, computer vision algorithms are used for the identification and segmentation of human bodies. To validate the algorithm, mobile eye tracking data from short combat sport sequences were analyzed. The performance of the algorithm was compared against three manual raters. The algorithm performed with substantial reliability in comparison to the manual raters when it came to annotating which area of interest gaze was closest to. However, the algorithm was more conservative than the manual raters for classifying if gaze was directed towards an object of interest. The algorithmic approach represents a viable and promising means for automating gaze classification for mobile eye tracking.

AB - Mobile eye tracking traditionally requires gaze to be coded manually. We introduce an open-source Python package (GazeClassify) that algorithmically annotates mobile eye tracking data for the study of human interactions. Instead of manually identifying objects and identifying if gaze is directed towards an area of interest, computer vision algorithms are used for the identification and segmentation of human bodies. To validate the algorithm, mobile eye tracking data from short combat sport sequences were analyzed. The performance of the algorithm was compared against three manual raters. The algorithm performed with substantial reliability in comparison to the manual raters when it came to annotating which area of interest gaze was closest to. However, the algorithm was more conservative than the manual raters for classifying if gaze was directed towards an object of interest. The algorithmic approach represents a viable and promising means for automating gaze classification for mobile eye tracking.

KW - algorithmic eye-Tracking

KW - computer vision

KW - image segmentation

KW - open source software

UR - http://www.scopus.com/inward/record.url?scp=85107965413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85107965413&partnerID=8YFLogxK

U2 - 10.1145/3450341.3458886

DO - 10.1145/3450341.3458886

M3 - Conference contribution

AN - SCOPUS:85107965413

T3 - Eye Tracking Research and Applications Symposium (ETRA)

BT - ETRA 2021 Adjunct

A2 - Spencer, Stephen N.

PB - Association for Computing Machinery

T2 - 2021 ACM Symposium on Eye Tracking Research and Applications, ETRA 2021

Y2 - 24 May 2021 through 27 May 2021

ER -

Algorithmic gaze classification for mobile eye-tracking

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this