Implicit Probabilistic Models of Human Motion for Synthesis and Tracking

Abstract. This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Given the high dimensional nature of human motion, learning an explicit probabilistic model from available training data is currently impractical. Instead we exploit methods from texture synthesis that treat images as representing an implicit empirical distribution. These methods replace the problem of representing the probability of a texture pattern with that of searching the training data for similar instances of that pattern. We extend this idea to temporal data representing 3D human motion with a large database of example motions. To make the method useful in practice, we must address the problem of efficient search in a large training set; efficiency is particularly important for tracking. Towards that end, we learn a low dimensional linear model of human motion that is used to structure the example motion database into a binary tree. An approximate probabilistic t...

• Type: Conference
• Year: 2002
• Where: ECCV
• Authors: Hedvig Sidenbladh, Michael J. Black, Leonid Sigal
• Keywords: Approximate Probabilistic Tree, Computer Vision, ECCV 2002, Example Motion Database, Human Motion, Probabilistic Tree Search, Sample Human Motion