venkatesh-trackingasrecognition-2007.pdf (566.7 kB)
Tracking-as-recognition for articulated full-body human motion analysis
conference contribution
posted on 2007-01-01, 00:00 authored by P Peursum, Svetha VenkateshSvetha Venkatesh, G WestThis paper addresses the problem of markerless tracking of a human in full 3D with a high-dimensional (29D) body model Most work in this area has been focused on achieving accurate tracking in order to replace marker-based motion capture, but do so at the cost of relying on relatively clean observing conditions. This paper takes a different perspective, proposing a body-tracking model that is explicitly designed to handle real-world conditions such as occlusions by scene objects, failure recovery, long-term tracking, auto-initialisation, generalisation to different people and integration with action recognition. To achieve these goals, an action's motions are modelled with a variant of the hierarchical hidden Markov model The model is quantitatively evaluated with several tests, including comparison to the annealed particle filter, tracking different people and tracking with a reduced resolution and frame rate.
History
Event
Computer Vision and Pattern Recognition. Conference (2007 : Minneapolis, Minn.)Publisher
IEEELocation
Minneapolis, MNPlace of publication
[Piscataway, N.J.]Publisher DOI
Start date
2007-06-17End date
2007-06-22ISBN-13
9781424411801ISBN-10
1424411807Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2007, IEEETitle of proceedings
CVPR 2007 : Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern RecognitionUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC