Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States

Corfu, Greece September 20-September 25

RSS feed for this publication

DOI Bookmark:

http://doi.ieeecomputersociety.org/10.1109/ICCV.1999.791212

Seventh International Conference on C ...

	This Article
	PURCHASE ARTICLE: $19 PDF HTML IEEE Xplore Subscribers
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Shaogang Gong Articles by Michael Walter Articles by Alexandra Psarrou

	ASCII Text	x
	Shaogang Gong, Michael Walter, Alexandra Psarrou, "Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States," Computer Vision, IEEE International Conference on, vol. 1, pp. 157, Seventh International Conference on Computer Vision (ICCV'99) - Volume 1, 1999.

	BibTex	x
	@article{ 10.1109/ICCV.1999.791212, author = {Shaogang Gong and Michael Walter and Alexandra Psarrou}, title = {Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States}, journal ={Computer Vision, IEEE International Conference on}, volume = {1}, year = {1999}, isbn = {0-7695-0164-8}, pages = {157}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICCV.1999.791212}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Computer Vision, IEEE International Conference on TI - Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States SN - 0-7695-0164-8 SP EP A1 - Shaogang Gong, A1 - Michael Walter, A1 - Alexandra Psarrou, PY - 1999 KW - Modeling temporal structures KW - hidden Markov models KW - CONDENSATION KW - EM algorithm KW - Gesture and behavior recognition VL - 1 JA - Computer Vision, IEEE International Conference on ER -

Shaogang Gong, University of Westminster

Michael Walter, University of Westminster

Alexandra Psarrou, University of Westminster

An algorithm is described for modeling and recognizing temporal structures of visual activities. The method is based on (1) learning prior probabilistic knowledge using Hidden Markov Models, (2) automatic temporal clustering of hidden Markov states based on Expectation Maximization and (3) using observation augmented conditional density distributions to reduce the number of samples required for propagation and therefore improve recognition speed and robustness.

Index Terms:

Modeling temporal structures, hidden Markov models, CONDENSATION, EM algorithm, Gesture and behavior recognition

Citation:

Shaogang Gong, Michael Walter, Alexandra Psarrou, "Recognition of Temporal Structures: Learning Prior and Propagating Observation Augmented Densities via Hidden Markov States," iccv, vol. 1, pp.157, Seventh International Conference on Computer Vision (ICCV'99) - Volume 1, 1999

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.