A system is described that tracks moving objects in a video dataset so as to extract a representation of the objects' 3D trajectories. The system then finds hierarchical clus...
Optical flow in monocular video can serve as a key for recognizing and tracking the three-dimensional pose of human subjects. In comparison with prior work using silhouettes as a ...
In this work we present an approach for markerless
motion capture (MoCap) of articulated objects, which are
recorded with multiple unsynchronized moving cameras.
Instead of usin...
Bodo Rosenhahn, Hans-Peter Seidel, Juergen Gall, M...
Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...