Kinematic jump processes for monocular 3D human tracking
- 18 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
International audienceA major difficulty for 3D (three-dimensional) human body tracking from monocular image sequences is the near nonobservability of kinematic degrees of freedom that generate motion in depth. For known link (body segment) lengths, the strict nonobservabilities reduce to twofold 'forwards/backwards flipping' ambiguities for each link. These imply 2# links formal inverse kinematics solutions for the full model, and hence linked groups of O(2# links) local minima in the model-image matching cost function. Choosing the wrong minimum leads to rapid mistracking, so for reliable tracking, rapid methods of investigating alternative minima within a group are needed. Previous approaches to this have used generic search methods that do not exploit the specific problem structure. Here, we complement these by using simple kinematic reasoning to enumerate the tree of possible forwards/backwards flips, thus greatly speeding the search within each linked group of minima. Our methods can be used either deterministically, or within stochastic 'jump-diffusion' style search processes. We give experimental results on some challenging monocular human tracking sequences, showing how the new kinematic-flipping based sampling method improves and complements existing onesKeywords
This publication has 8 references indexed in Scilit:
- Articulated body motion capture by annealed particle filteringPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reconstruction of articulated objects from point correspondences in a single uncalibrated imagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Consistency and coupling in human model likelihoodsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Covariance scaled sampling for monocular 3D body trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Real-Time Inverse Kinematics Techniques for Anthropomorphic LimbsGraphical Models, 2000
- Stochastic Tracking of 3D Human Figures Using 2D Image MotionPublished by Springer Nature ,2000
- 3-D model-based tracking of humans in action: a multi-view approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Global and local deformations of solid primitivesACM SIGGRAPH Computer Graphics, 1984