Combining Object and Feature Dynamics in Probabilistic Tracking
Objects can exhibit different dynamics at different scales, a property that isoftenexploited by visual tracking algorithms. A local dynamicmodel is typically used to extract image features that are then used as inputsto a system for tracking the entire object using a global dynamic model.Approximate local dynamicsmay be brittle---point trackers drift due to image noise and adaptivebackground models adapt to foreground objects that becomestationary---but constraints from the global model can make them more robust.We propose a probabilistic framework for incorporating globaldynamics knowledge into the local feature extraction processes.A global tracking algorithm can beformulated as a generative model and used to predict feature values thatinfluence the observation process of thefeature extractor. We combine such models in a multichain graphicalmodel framework.We show the utility of our framework for improving feature tracking and thusshapeand motion estimates in a batch factorization algorithm.We also propose an approximate filtering algorithm appropriate for onlineapplications, and demonstrate its application to problems such as backgroundsubtraction, structure from motion and articulated body tracking.