Human pose tracking by parametric annealing

Model based methods to marker-free motion capture have a very high computational overhead. In this paper we describe a method that improves on existing global optimization techniques to tracking articulated objects. Our method improves on the state-of-the-art Annealed Particle Filter (APF) by reusing samples across annealing layers and by using an adaptive parametric density for diffusion. We compare the proposed method with APF on a scalable problem and study the effects of dimensionality, multi-modality and the range of search. We perform sensitivity analysis on the parameters of our algorithm and show that it is widely tolerant. We also show results on tracking human pose from the widely-used Human Eva I dataset. Our results show that the proposed method reduces the tracking error despite using less than 50% of the computational resources as APF. The tracked output also shows a significant qualitative improvement over APF.