Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/70300
DC FieldValue
dc.titleFast detection of frequent change in focus of human attention
dc.contributor.authorHu, N.
dc.contributor.authorHuang, W.
dc.contributor.authorRanganath, S.
dc.date.accessioned2014-06-19T03:10:32Z
dc.date.available2014-06-19T03:10:32Z
dc.date.issued2005
dc.identifier.citationHu, N.,Huang, W.,Ranganath, S. (2005). Fast detection of frequent change in focus of human attention. Lecture Notes in Computer Science 3368 : 216-230. ScholarBank@NUS Repository.
dc.identifier.issn03029743
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/70300
dc.description.abstractWe present an algorithm to detect the attentive behavior of persons with frequent change in focus of attention (FCFA) from a static video camera. This behavior can be easily perceived by people as temporal changes of human head pose. Here, we propose to use features extracted by analyzing a similarity matrix of head pose by using a self-similarity measure of the head image sequence. Further, we present a fast algorithm which uses an image vector sequence represented in the principal components subspace instead of the original image sequence to measure the self-similarity. An important feature of the behavior of FCFA is its cyclic pattern where the head pose repeats its position from time to time. A frequency analysis scheme is proposed to find the dynamic characteristics of persons with frequent change of attention or focused attention. A nonparametric classifier is used to classify these two kinds of behaviors (FCFA and focused attention). The fast algorithm discussed in this paper yields real-time performance as well as good accuracy. © Springer-Verlag Berlin Heidelberg 2005.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.sourcetitleLecture Notes in Computer Science
dc.description.volume3368
dc.description.page216-230
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.