Advanced

Detection of fixations and smooth pursuit movements in high-speed eye-tracking data

Larsson, Linnéa LU ; Nyström, Marcus LU ; Andersson, Richard LU and Stridh, Martin LU (2015) In Biomedical Signal Processing and Control 18. p.145-152
Abstract
A novel algorithm for the detection of fixations and smooth pursuit movements in high-speed eye-tracking data is proposed, which uses a three-stage procedure to divide the intersaccadic intervals intoa sequence of fixation and smooth pursuit events. The first stage performs a preliminary segmentationwhile the latter two stages evaluate the characteristics of each such segment and reorganize the pre-liminary segments into fixations and smooth pursuit events. Five different performance measures arecalculated to investigate different aspects of the algorithm’s behavior. The algorithm is compared to thecurrent state-of-the-art (I-VDT and the algorithm in [11]), as well as to annotations by two experts. Theproposed algorithm performs... (More)
A novel algorithm for the detection of fixations and smooth pursuit movements in high-speed eye-tracking data is proposed, which uses a three-stage procedure to divide the intersaccadic intervals intoa sequence of fixation and smooth pursuit events. The first stage performs a preliminary segmentationwhile the latter two stages evaluate the characteristics of each such segment and reorganize the pre-liminary segments into fixations and smooth pursuit events. Five different performance measures arecalculated to investigate different aspects of the algorithm’s behavior. The algorithm is compared to thecurrent state-of-the-art (I-VDT and the algorithm in [11]), as well as to annotations by two experts. Theproposed algorithm performs considerably better (average Cohen’s kappa 0.42) than the I-VDT algorithm(average Cohen’s kappa 0.20) and the algorithm in [11] (average Cohen’s kappa 0.16), when comparedto the experts’ annotations. (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
smooth pursuit, eye-tracking, Signal processing
in
Biomedical Signal Processing and Control
volume
18
pages
145 - 152
publisher
Elsevier
external identifiers
  • wos:000354150400018
  • scopus:84921693206
ISSN
1746-8094
DOI
10.1016/j.bspc.2014.12.008
language
English
LU publication?
yes
id
6587326f-96da-4b17-a279-59bb4656c873 (old id 4941066)
date added to LUP
2015-01-27 11:32:28
date last changed
2017-10-22 04:19:10
@article{6587326f-96da-4b17-a279-59bb4656c873,
  abstract     = {A novel algorithm for the detection of fixations and smooth pursuit movements in high-speed eye-tracking data is proposed, which uses a three-stage procedure to divide the intersaccadic intervals intoa sequence of fixation and smooth pursuit events. The first stage performs a preliminary segmentationwhile the latter two stages evaluate the characteristics of each such segment and reorganize the pre-liminary segments into fixations and smooth pursuit events. Five different performance measures arecalculated to investigate different aspects of the algorithm’s behavior. The algorithm is compared to thecurrent state-of-the-art (I-VDT and the algorithm in [11]), as well as to annotations by two experts. Theproposed algorithm performs considerably better (average Cohen’s kappa 0.42) than the I-VDT algorithm(average Cohen’s kappa 0.20) and the algorithm in [11] (average Cohen’s kappa 0.16), when comparedto the experts’ annotations.},
  author       = {Larsson, Linnéa and Nyström, Marcus and Andersson, Richard and Stridh, Martin},
  issn         = {1746-8094},
  keyword      = {smooth pursuit,eye-tracking,Signal processing},
  language     = {eng},
  pages        = {145--152},
  publisher    = {Elsevier},
  series       = {Biomedical Signal Processing and Control},
  title        = {Detection of fixations and smooth pursuit movements in high-speed eye-tracking data},
  url          = {http://dx.doi.org/10.1016/j.bspc.2014.12.008},
  volume       = {18},
  year         = {2015},
}