Domain-Shift Manifold Online Learning and Tracking of Video Objects

This paper describes a novel Grassmann manifoldobject tracking scheme that includes the modules ofmanifold online learning and occlusion handling. Whenobjects contain significant out-of-plane pose changes, thedomain where object appearances lying is shifting withtime, hence a single vector space is no longer suitable fordynamic object representation.Motivated by this, we presenta manifold-based scheme for tracking large out-of-planeobjects (i.e. camera is close to the object) in video withonline learning and long-term partial occlusion modules.The tracker uses Bayesian formulation on the manifold, performing posterior state estimation based on nonlinear state space modeling. One particle filter is applied for manifold online learning, another is for tracking. Occlusion handling is applied during the online learning to prevent learning occluding object/clutter. Tests on videos have shown very robust tracking performance when objects contain significant out-of-plane pose changes accompanied with long-term partial occlusions. Comparisons with two existing methods provide further support to the proposed method