TY - GEN
T1 - Bayesian online clustering of eye movement data
AU - Tafaj, Enkelejda
AU - Kasneci, Gjergji
AU - Rosenstiel, Wolfgang
AU - Bogdan, Martin
PY - 2012
Y1 - 2012
N2 - The task of automatically tracking the visual attention in dynamic visual scenes is highly challenging. To approach it, we propose a Bayesian online learning algorithm. As the visual scene changes and new objects appear, based on a mixture model, the algorithm can identify and tell visual saccades (transitions) from visual fixation clusters (regions of interest). The approach is evaluated on real-world data, collected from eye-tracking experiments in driving sessions.
AB - The task of automatically tracking the visual attention in dynamic visual scenes is highly challenging. To approach it, we propose a Bayesian online learning algorithm. As the visual scene changes and new objects appear, based on a mixture model, the algorithm can identify and tell visual saccades (transitions) from visual fixation clusters (regions of interest). The approach is evaluated on real-world data, collected from eye-tracking experiments in driving sessions.
KW - Bayesian model
KW - eye movement data
KW - fixation clusters
KW - online clustering
UR - http://www.scopus.com/inward/record.url?scp=84862637483&partnerID=8YFLogxK
U2 - 10.1145/2168556.2168617
DO - 10.1145/2168556.2168617
M3 - Conference contribution
AN - SCOPUS:84862637483
SN - 9781450312257
T3 - Eye Tracking Research and Applications Symposium (ETRA)
SP - 285
EP - 288
BT - Proceedings - ETRA 2012
T2 - 7th Eye Tracking Research and Applications Symposium, ETRA 2012
Y2 - 28 March 2012 through 30 March 2012
ER -