CVApr 30, 2012

Parametric annealing: a stochastic search method for human pose tracking

arXiv:1204.6563v215 citations
AI Analysis

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes