Real-time On-line Learning of Transformed Hidden Markov Models from Video

Abstract

The transformed hidden Markov model is a temporal model that captures three typical causes of variability in video scene/object class, appearance variability within the class, and image motion. In our previous work, we showed that an exact EM algorithm can jointly learn the appearances of multiple objects and/or poses of an object, and track the objects or… (More)

Topics

7 Figures and Tables

Slides referencing similar topics