Simultaneous Tracking and Activity Recognition with Relational Dynamic Bayesian Networks

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Manfredotti, Cristina Elena
dc.contributor.author Fleet, David James
dc.contributor.author Hamilton, Howard John
dc.contributor.author Zilles, Sandra
dc.date.accessioned 2011-04-01T21:00:06Z
dc.date.available 2011-04-01T21:00:06Z
dc.date.issued 2011-03-30
dc.identifier.isbn 978-0-7731-0694-9 en
dc.identifier.uri http://hdl.handle.net/10294/3194
dc.identifier.uri http://www.cs.uregina.ca/Research/reports.html en
dc.description 10 p. en_US
dc.description.abstract Taking into account relationships between interacting objects can improve the understanding of the dynamic model governing their behaviors. Moreover, maintaining a belief about the ongoing activity while tracking allows online activity recognition and improves the tracking task. We investigate the use of Relational Dynamic Bayesian Networks to represent the relationships for the tasks of multi-target tracking and explicitly consider a discrete variable in the state to represent the activity for online activity recognition. We propose a new transition model that accommodates relations and activities and we extend the Particle Filter algorithm to directly track relations between targets while recognizing ongoing activities. en_US
dc.language.iso en en_US
dc.publisher Department of Computer Science, University of Regina en_US
dc.title Simultaneous Tracking and Activity Recognition with Relational Dynamic Bayesian Networks en_US
dc.type Technical Report en_US
dc.description.authorstatus Faculty en_US
dc.description.peerreview yes en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search oURspace


Advanced Search

Browse

My Account

About