Object tracking with global and local dynamics model

We present a novel method for object tracking using global and local states of object in video surveillance application. Most traditional object models using global appearance cannot handle partial occlusion effectively. The unoccluded part of partially visible object retains invariable appearance. Therefore, we introduce global and local dynamics model as our object model to overcome partial occlusion using local feature, and apply it to Bayesian tracking problem using motion-based particle filtering. Finally, experiments on some video surveillance sequences demonstrate the effectiveness and robustness of our approach for tracking object motions in video surveillance.