Supervised segmentation and tracking of nonrigid objects using a "mixture of histograms" model

Segmentation and tracking of objects in video sequences is important for a number of applications. In the supervised variant, segmentation can be achieved by modelling the probability density of image observations taken from an object for use in a Bayesian classifier, and Gaussian mixture models have been applied to this task by several researchers. Motivated by practical difficulties we have experienced with these models we propose a novel and simple alternative approach which combines a strong shape model with histograms of image features and gives good empirical results on test sequences requiring flexible models.