Model-based 3D tracker estimate the position, rotation, and joint angles of a given model from video data of one or multiple cameras. They often rely on image features that are tr...
This paper presents a new technique for the perception of activities using statistical description of spatio-temporal properties. With this approach, the probability of an activit...
Segmentation of motion in an image sequence is one of the most challenging problems in image processing, while at the same time one that finds numerous applications. To date, a wea...
We present an analysis of the spatial covariance structure of an articulated motion prior in which joint angles have a known covariance structure. From this, a well-known, but ofte...
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...