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.
Bayesian clustering of optical flow fields
Proceedings Ninth IEEE International Conference on Computer Vision ; 1086-1093 vol.2
2003-01-01
1477212 byte
Conference paper
Electronic Resource
English
Bayesian Clustering of Optical Flow Fields
British Library Conference Proceedings | 2003
|Towards Bayesian real-time optical flow
British Library Online Contents | 2004
|Recursive Bayesian fire recognition using greedy margin-maximizing clustering
British Library Online Contents | 2013
|Bayesian image classification using Markov random fields
British Library Online Contents | 1996
|