Head tracking by active particle filtering

Particle filtering has attracted much attention due to its robust tracking performance in clutter. However, a price to pay for its robustness is the computational cost. Active particle filtering is proposed in this paper. Unlike traditional particle filtering, every particle in active particle filtering is first driven to its local maximum of the likelihood before it is weighted. In this case, the efficiency of every particle is improved and the number of required particles is greatly reduced. Actually, the number of particles in the active particle filtering is based more on the cluttered degree of the environment and the fitting range of every particle than on the size of the model´s configuration space. Extensive experimental results show that the tracker is efficient and robust in tracking a head undergoing translation and full 360° out-of-plane rotation with partial occlusion in cluttered environments