Abstract. In this work, we introduce a model-based approach to extracting the silhouette of people in motion from stereo video sequences. To this end, we extend a purely stereo-bas...
Global motion estimation is an important task for various video processing techniques. The estimation itself has to be robust in presence of arbitrarily moving foreground objects....
Michael Tok, Alexander Glantz, Andreas Krutz, Thom...
We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segm...
Dirk Ormoneit, Hedvig Sidenbladh, Michael J. Black...
This paper describes an ongoing collaborative research program between the Computer Science and the Forestry and Wildlife Management Departments at the University of Massachusetts...
Howard J. Schultz, Dana Slaymaker, Chris Holmes, F...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...