Tracking Loose-Limbed People

We pose the problem of 3D human tracking as one of inference in a graphical model. Unlike traditional kinematic tree representations, our model of the body is a collection of loosely-connected limbs. Conditional probabilities relating the 3D pose of connected limbs are learned from motioncaptured training data. Similarly, we learn probabilistic models for the temporal evolution of each limb (forward and backward in time). Human pose and motion estimation is then solved with non-parametric belief propagation using a variation of particle filtering that can be applied over a general loopy graph. The loose-limbed model and decentralized graph structure facilitate the use of low-level visual cues. We adopt simple limb and head detectors to provide "bottom-up" information that is incorporated into the inference process at every time-step; these detectors permit automatic initialization and aid recovery from transient tracking failures. We illustrate the method by automatically tr...

• Type: Conference
• Year: 2004
• Where: CVPR
• Authors: Leonid Sigal, Sidharth Bhatia, Stefan Roth, Michael J. Black, Michael Isard
• Keywords: Computer Vision, CVPR 2004, General Loopy Graph, Human Pose, Kinematic Tree Representations, Non-parametric Belief Propagation, Transient Tracking Failures