1. INTRODUCTION
One of the central topics in computer vision is the recognition of human postures and gestures. A major goal is to go
beyond traditional human-computer interaction (like mouse or keyboard) and find a more natural means of interaction
with computers. Not only natural communication but also the movement and action of a person are highly relevant.
Examples include surveillance systems that detect and track a person and recognize special actions (e.g., theft). Smart
interfaces or smart rooms1 recognize motion and gestures and can react to and communicate with a person. An example
is the KidsRoom,2, 3 a fully automated and interactive play space for children. The human-computer interaction is based
solely on computational perception.