Observable Subspaces for 3D Human Motion Recovery

The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. The true range of motion can therefore be represented by latent variables that span a low-dimensional space. This has often been used to make motion tracking easier. However, learning the latent space in a problem-independent way makes it non trivial to initialize the tracking process by picking appropriate initial values for the latent variables, and thus for the pose. In this paper, we show that by directly using observable quantities as our latent variables, we eliminate this problem and achieve full automation given only modest amounts of training data. More specifically, we exploit the fact that the trajectory of a person's feet or hands strongly constrains body pose in motions such as skating, skiing, or golfing. These trajectories are easy to compute and to parameterize us...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Andrea Fossati (EPFL), Mathieu Salzmann (University of California, Berkeley), Pascal Fua (EPFL)
• Attachments: 1 file(s)
• Keywords: Computer Vision, CVPR 2009, Human Body Tracking