Articulated body motion capture by annealed particle filtering

TLDR

Articulated body motion tracking faces a high‑dimensional search space (~30 degrees of freedom) that leads to exponential computational complexity, and existing methods rely on constraints such as markers, colour coding, prior motion assumptions, or independent limb tracking. This study seeks to develop a general tracking method that does not require special object preparation or restrictive assumptions. The authors propose a modified particle filter that employs an annealing continuation principle to gradually incorporate the influence of narrow peaks in the fitness function during high‑dimensional search. The resulting annealed particle filtering algorithm efficiently recovers full articulated body motion.

Abstract

The main challenge in articulated body motion tracking is the large number of degrees of freedom (around 30) to be recovered. Search algorithms, either deterministic or stochastic, that search such a space without constraint, fall foul of exponential computational complexity. One approach is to introduce constraints: either labelling using markers or colour coding, prior assumptions about motion trajectories or view restrictions. Another is to relax constraints arising from articulation, and track limbs as if their motions were independent. In contrast, we aim for general tracking without special preparation of objects or restrictive assumptions. The principal contribution of the paper is the development of a modified particle filter for search in high dimensional configuration spaces. It uses a continuation principle based on annealing to introduce the influence of narrow peaks in the fitness function, gradually. The new algorithm, termed annealed particle filtering, is shown to be capable of recovering full articulated body motion efficiently.