Sciweavers

Share
EMMCVPR
2011
Springer

Data-Driven Importance Distributions for Articulated Tracking

7 years 6 months ago
Data-Driven Importance Distributions for Articulated Tracking
Abstract. We present two data-driven importance distributions for particle filterbased articulated tracking; one based on background subtraction, another on depth information. In order to keep the algorithms efficient, we represent human poses in terms of spatial joint positions. To ensure constant bone lengths, the joint positions are confined to a non-linear representation manifold embedded in a highdimensional Euclidean space. We define the importance distributions in the embedding space and project them onto the representation manifold. The resulting importance distributions are used in a particle filter, where they improve both accuracy and efficiency of the tracker. In fact, they triple the effective number of samples compared to the most commonly used importance distribution at little extra computational cost. Key words: Articulated tracking · Importance Distributions · Particle Filtering · Spatial Human Motion Models 1 Motivation Articulated tracking is the process of ...
Søren Hauberg, Kim Steenstrup Pedersen
Added 20 Dec 2011
Updated 20 Dec 2011
Type Journal
Year 2011
Where EMMCVPR
Authors Søren Hauberg, Kim Steenstrup Pedersen
Comments (0)
books