Motion Estimation via Belief Propagation

	This Article
	Subscribers, please Login Purchase article: $19 PDF RSS feed
	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 Giuseppe Boccignone Articles by Angelo Marcelli Articles by Paolo Napoletano Articles by Mario Ferraro

14th International Conference on Image Analysis and Processing (ICIAP 2007)

Modena, Italy

September 10-September 14

ISBN: 0-7695-2877-5

	ASCII Text	x
	Giuseppe Boccignone, Angelo Marcelli, Paolo Napoletano, Mario Ferraro, "Motion Estimation via Belief Propagation," Image Analysis and Processing, International Conference on, pp. 55-60, 14th International Conference on Image Analysis and Processing (ICIAP 2007), 2007.

	BibTex	x
	@article{ 10.1109/ICIAP.2007.88, author = {Giuseppe Boccignone and Angelo Marcelli and Paolo Napoletano and Mario Ferraro}, title = {Motion Estimation via Belief Propagation}, journal ={Image Analysis and Processing, International Conference on}, volume = {0}, year = {2007}, isbn = {0-7695-2877-5}, pages = {55-60}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICIAP.2007.88}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Image Analysis and Processing, International Conference on TI - Motion Estimation via Belief Propagation SN - 0-7695-2877-5 SP55 EP60 A1 - Giuseppe Boccignone, A1 - Angelo Marcelli, A1 - Paolo Napoletano, A1 - Mario Ferraro, PY - 2007 KW - null VL - 0 JA - Image Analysis and Processing, International Conference on ER -

Giuseppe Boccignone, University of Salerno, Italy

Angelo Marcelli, University of Salerno, Italy

Paolo Napoletano, University of Salerno, Italy

Mario Ferraro, University of Torino, Italy

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICIAP.2007.88

We present a probabilistic model for motion estimation in which motion characteristics are inferred on the basis of a finite mixture of motion models. The model is graphically represented in the form of a pairwise Markov Random Field network upon which a Loopy Belief Propagation algorithm is exploited to perform inference. Experiments on different video clips are presented and discussed.

Citation:

Giuseppe Boccignone, Angelo Marcelli, Paolo Napoletano, Mario Ferraro, "Motion Estimation via Belief Propagation," iciap, pp.55-60, 14th International Conference on Image Analysis and Processing (ICIAP 2007), 2007

Peer Review Notice | Give Us Feedback

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