loading...
Bayesian Clustering of Optical Flow Fields
Nice, France October 13-October 16
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICCV.2003.1238470Ninth IEEE International Conference o ...
 This Article 
 
PDF
HTML
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Jesse Hoey, University of British Columbia
James J. Little, University of British Columbia
We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probabilistic fashion, which improves the estimation of the projections by incorporating uncertainties in the flows. We then cluster the projections using a mixture of feature-weighted Gaussians over optical flow fields. The resulting model extracts a concise probabilistic description of the major classes of optical flow present. The method is demonstrated on a video of a person's facial expressions.
Citation:
Jesse Hoey, James J. Little, "Bayesian Clustering of Optical Flow Fields," iccv, vol. 2, pp.1086, Ninth IEEE International Conference on Computer Vision (ICCV'03) - Volume 2, 2003
Usage of this product signifies your acceptance of the Terms of Use.