Abstract. In this paper, we present novel image-derived, invariant features that accurately capture both the geometric and color properties of an imaged object. These features can ...
This paper presents a new automatic approach to building a videorama with shallow depth of field. We stitch the static background of video frames and render the dynamic foreground...
Common movements like reaching, striking, etc. observed during surveillance have highly variable target locations. This puts appearance-based techniques at a disadvantage for model...
Modeling and describing temporal structure in multimedia signals, which are captured simultaneously by multiple sensors, is important for realizing human machine interaction and mo...
The contribution presents an approach for motion capturing (MoCap) of dressed people. A cloth draping method is embedded in a silhouette based MoCap system and an error functional ...
Bodo Rosenhahn, Uwe G. Kersting, Katie Powell, Han...