Parametric annealing: a stochastic search method for human pose tracking
This is an incremental improvement for human pose tracking, addressing computational efficiency in motion capture applications.
The paper tackles the high computational cost of model-based marker-free motion capture by improving the Annealed Particle Filter (APF) with sample reuse and adaptive parametric diffusion, resulting in reduced tracking error while using less than 50% of computational resources on the Human Eva I dataset.
Model based methods to marker-free motion capture have a very high computational overhead that make them unattractive. 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 how the two methods scale with the dimensionality, multi-modality and the range of search. Then we perform sensitivity analysis on the parameters of our algorithm and show that it tolerates a wide range of parameter settings. 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 as demonstrated through image and video results.