Space-variant spatio-temporal filtering of video for gaze visualization and perceptual learning

Michael Dorr; Halszka Jarodzka; Erhardt Barth

doi:10.1145/1743666.1743737

Abstract

We introduce an algorithm for space-variant ﬁltering of video based on a spatio-temporal Laplacian pyramid and use this algorithm to render videos in order to visualize prerecorded eye movements. Spatio-temporal contrast and colour saturation are reduced as a function of distance to the nearest gaze point of regard, i.e. non- ﬁxated, distracting regions are ﬁltered out, whereas ﬁxated image regions remain unchanged. Results of an experiment in which the eye movements of an expert on instructional videos are visualized with this algorithm, so that the gaze of novices is guided to relevant image locations. Results show that this visualization technique facilitates the novices’ perceptual learning.

Original language	English
Title of host publication	ETRA '10: Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications
Place of Publication	New York
Publisher	Association for Computing Machinery (ACM)
Pages	307-314
Number of pages	8
ISBN (Print)	978-1-60558-994-7
DOIs	https://doi.org/10.1145/1743666.1743737
Publication status	Published - 2010
Event	Eye Tracking Research & Applications Symposium 2010 - Austin, United States Duration: 22 Mar 2010 → 24 Mar 2010 Conference number: 6th https://webpages.tuni.fi/utacs_history/cs/etra-2010/

Symposium

Symposium	Eye Tracking Research & Applications Symposium 2010
Abbreviated title	ETRA 2010
Country/Territory	United States
City	Austin
Period	22/03/10 → 24/03/10
Internet address	https://webpages.tuni.fi/utacs_history/cs/etra-2010/

Keywords

eye tracking
image processing

Access to Document

10.1145/1743666.1743737Licence: CC BY-NC-ND

Dorr et alAccepted author manuscript, 227 KBLicence: CC BY-NC-ND

Cite this

@inbook{48f8f7f7a7a746f6a9c8e12f2c48cf81,

title = "Space-variant spatio-temporal filtering of video for gaze visualization and perceptual learning",

abstract = "We introduce an algorithm for space-variant ﬁltering of video based on a spatio-temporal Laplacian pyramid and use this algorithm to render videos in order to visualize prerecorded eye movements. Spatio-temporal contrast and colour saturation are reduced as a function of distance to the nearest gaze point of regard, i.e. non- ﬁxated, distracting regions are ﬁltered out, whereas ﬁxated image regions remain unchanged. Results of an experiment in which the eye movements of an expert on instructional videos are visualized with this algorithm, so that the gaze of novices is guided to relevant image locations. Results show that this visualization technique facilitates the novices{\textquoteright} perceptual learning.",

keywords = "eye tracking, image processing",

author = "Michael Dorr and Halszka Jarodzka and Erhardt Barth",

note = "DS_Description: Dorr, M., Jarodzka, H., & Barth, E. (2010). Space-variant spatio-temporal filtering of video for gaze visualization and perceptual learning. In C. Morimoto & H. Instance (Eds.), Proceedings of the 2010 Symposium on Eye Tracking Research & Applications ETRA {\textquoteright}10 (pp. 307-314). New York, NY: ACM.; Eye Tracking Research & Applications Symposium 2010, ETRA 2010 ; Conference date: 22-03-2010 Through 24-03-2010",

year = "2010",

doi = "10.1145/1743666.1743737",

language = "English",

isbn = "978-1-60558-994-7",

pages = "307--314",

booktitle = "ETRA '10: Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

url = "https://webpages.tuni.fi/utacs_history/cs/etra-2010/",

}

Dorr, M, Jarodzka, H & Barth, E 2010, Space-variant spatio-temporal filtering of video for gaze visualization and perceptual learning. in ETRA '10: Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications. Association for Computing Machinery (ACM), New York, pp. 307-314, Eye Tracking Research & Applications Symposium 2010, Austin, Texas, United States, 22/03/10. https://doi.org/10.1145/1743666.1743737

Space-variant spatio-temporal filtering of video for gaze visualization and perceptual learning. / Dorr, Michael; Jarodzka, Halszka; Barth, Erhardt.
ETRA '10: Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications. New York: Association for Computing Machinery (ACM), 2010. p. 307-314.

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

TY - CHAP

T1 - Space-variant spatio-temporal filtering of video for gaze visualization and perceptual learning

AU - Dorr, Michael

AU - Jarodzka, Halszka

AU - Barth, Erhardt

N1 - Conference code: 6th

PY - 2010

Y1 - 2010

N2 - We introduce an algorithm for space-variant ﬁltering of video based on a spatio-temporal Laplacian pyramid and use this algorithm to render videos in order to visualize prerecorded eye movements. Spatio-temporal contrast and colour saturation are reduced as a function of distance to the nearest gaze point of regard, i.e. non- ﬁxated, distracting regions are ﬁltered out, whereas ﬁxated image regions remain unchanged. Results of an experiment in which the eye movements of an expert on instructional videos are visualized with this algorithm, so that the gaze of novices is guided to relevant image locations. Results show that this visualization technique facilitates the novices’ perceptual learning.

AB - We introduce an algorithm for space-variant ﬁltering of video based on a spatio-temporal Laplacian pyramid and use this algorithm to render videos in order to visualize prerecorded eye movements. Spatio-temporal contrast and colour saturation are reduced as a function of distance to the nearest gaze point of regard, i.e. non- ﬁxated, distracting regions are ﬁltered out, whereas ﬁxated image regions remain unchanged. Results of an experiment in which the eye movements of an expert on instructional videos are visualized with this algorithm, so that the gaze of novices is guided to relevant image locations. Results show that this visualization technique facilitates the novices’ perceptual learning.

KW - eye tracking

KW - image processing

U2 - 10.1145/1743666.1743737

DO - 10.1145/1743666.1743737

M3 - Conference Abstract/Poster in proceeding

SN - 978-1-60558-994-7

SP - 307

EP - 314

BT - ETRA '10: Proceedings of the 2010 Symposium on Eye-Tracking Research & Applications

PB - Association for Computing Machinery (ACM)

CY - New York

T2 - Eye Tracking Research & Applications Symposium 2010

Y2 - 22 March 2010 through 24 March 2010

ER -