Kinematic Jump Processes For Monocular 3D Human Tracking

Cristian Sminchisescu (1) , Bill Triggs (1)

1 MOVI - Modeling, localization, recognition and interpretation in computer vision

A 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 ones.

Mots clés: image sequences; kinematics; object detection; solid modelling; target tracking

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Cristian Sminchisescu, Bill Triggs. Kinematic Jump Processes For Monocular 3D Human Tracking. International Conference on Computer Vision & Pattern Recognition (CVPR '03), Jun 2003, Madison, United States. pp.69--76, ⟨10.1109/CVPR.2003.1211339⟩. ⟨inria-00548223⟩