Advanced

Smooth pursuit detection in binocular eye-tracking data with automatic video-based performance evaluation

Larsson, Linnéa LU ; Nyström, Marcus LU ; Ardö, Håkan LU ; Åström, Karl LU and Stridh, Martin LU (2016) In Journal of Vision 16(15).
Abstract

An increasing number of researchers record binocular eye-tracking signals from participants viewing moving stimuli, but the majority of event-detection algorithms are monocular and do not consider smooth pursuit movements. The purposes of the present study are to develop an algorithm that discriminates between fixations and smooth pursuit movements in binocular eye-tracking signals and to evaluate its performance using an automated video-based strategy. The proposed algorithm uses a clustering approach that takes both spatial and temporal aspects of the binocular eyetracking signal into account, and is evaluated using a novel video-based evaluation strategy based on automatically detected moving objects in the video stimuli. The... (More)

An increasing number of researchers record binocular eye-tracking signals from participants viewing moving stimuli, but the majority of event-detection algorithms are monocular and do not consider smooth pursuit movements. The purposes of the present study are to develop an algorithm that discriminates between fixations and smooth pursuit movements in binocular eye-tracking signals and to evaluate its performance using an automated video-based strategy. The proposed algorithm uses a clustering approach that takes both spatial and temporal aspects of the binocular eyetracking signal into account, and is evaluated using a novel video-based evaluation strategy based on automatically detected moving objects in the video stimuli. The binocular algorithm detects 98% of fixations in image stimuli compared to 95% when only one eye is used, while for video stimuli, both the binocular and monocular algorithms detect around 40% of smooth pursuit movements. The present article shows that using binocular information for discrimination of fixations and smooth pursuit movements is advantageous in static stimuli, without impairing the algorithm's ability to detect smooth pursuit movements in video and movingdot stimuli. With an automated evaluation strategy, time-consuming manual annotations are avoided and a larger amount of data can be used in the evaluation process.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Eye tracking, Signal processing, Smooth pursuit
in
Journal of Vision
volume
16
issue
15
publisher
Association for Research in Vision and Ophthalmology
external identifiers
  • Scopus:85010404640
  • Scopus:85010404640
ISSN
1534-7362
DOI
10.1167/16.15.20
language
English
LU publication?
yes
id
fb6df82b-965b-436b-9c20-38fa6d2bd6a2
date added to LUP
2016-09-21 18:53:36
date last changed
2017-02-10 13:52:58
@article{fb6df82b-965b-436b-9c20-38fa6d2bd6a2,
  abstract     = {<p>An increasing number of researchers record binocular eye-tracking signals from participants viewing moving stimuli, but the majority of event-detection algorithms are monocular and do not consider smooth pursuit movements. The purposes of the present study are to develop an algorithm that discriminates between fixations and smooth pursuit movements in binocular eye-tracking signals and to evaluate its performance using an automated video-based strategy. The proposed algorithm uses a clustering approach that takes both spatial and temporal aspects of the binocular eyetracking signal into account, and is evaluated using a novel video-based evaluation strategy based on automatically detected moving objects in the video stimuli. The binocular algorithm detects 98% of fixations in image stimuli compared to 95% when only one eye is used, while for video stimuli, both the binocular and monocular algorithms detect around 40% of smooth pursuit movements. The present article shows that using binocular information for discrimination of fixations and smooth pursuit movements is advantageous in static stimuli, without impairing the algorithm's ability to detect smooth pursuit movements in video and movingdot stimuli. With an automated evaluation strategy, time-consuming manual annotations are avoided and a larger amount of data can be used in the evaluation process.</p>},
  articleno    = {20},
  author       = {Larsson, Linnéa and Nyström, Marcus and Ardö, Håkan and Åström, Karl and Stridh, Martin},
  issn         = {1534-7362},
  keyword      = {Eye tracking,Signal processing,Smooth pursuit},
  language     = {eng},
  number       = {15},
  publisher    = {Association for Research in Vision and Ophthalmology},
  series       = {Journal of Vision},
  title        = {Smooth pursuit detection in binocular eye-tracking data with automatic video-based performance evaluation},
  url          = {http://dx.doi.org/10.1167/16.15.20},
  volume       = {16},
  year         = {2016},
}