We derive a probabilistic framework for robust, realtime, visual tracking of multiple previously unseen objects from a moving camera. This framework models the discrete depth orde...
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
Most of behavior recognition methods proposed so far share the limitations of bottom-up analysis, and singleobject assumption; the bottom-up analysis can be confused by erroneous ...
See a PPT file with videos at www.research.microsoft.com/users/jojic/FlexiblesSprites.htm We propose a technique for automatically learning layers of "flexible sprites" ...
In this paper, we present a system for simultaneous tracking of multiple persons in a smartroom using multiple cameras. Robust person tracks are created, continuously adapted, and...
Keni Bernardin, Alexander Elbs, Rainer Stiefelhage...