We present a novel method for tracking objects by combining density matching with shape priors. Density matching is a tracking method which operates by maximizing the Bhattacharyya similarity measure between the photometric distribution from an estimated image region and a model photometric distribution. Such trackers can be expressed as PDE-based curve evolutions, which can be implemented using level sets. Shape priors can be combined with this level-set implementation of density matching by representing the shape priors as a series of level sets; a variational approach allows for a natural, parametrization-independent shape term to be derived. Experimental results on real image sequences are shown.
Tracking objects using density matching and shape priors
Proceedings Ninth IEEE International Conference on Computer Vision ; 1056-1062 vol.2
01.01.2003
757411 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Tracking Objects Using Density Matching and Shape Priors
British Library Conference Proceedings | 2003
|On using priors in affine matching
British Library Online Contents | 2004
|Multiregion Level Set Tracking with Transformation Invariant Shape Priors
British Library Conference Proceedings | 2006
|Modelling Convex Shape Priors and Matching Based on the Gromov-Wasserstein Distance
British Library Online Contents | 2013
|Objects matching combining color and shape
IEEE | 2003
|