Modeling and Recognition of Human Actions Using a Stochastic Approach

This paper describes a self-learning prototype system for the real-time detection of unusual motion patterns. The proposed surveillance system uses a three-step approach consisting of a tracking, a learning and a recognition part. In the first step, an arbitrary, changing number of objects are tracked with an extension of the Condensation algorithm. Prom the history of the tracked object states, temporal trajectories are formed which describe the motion paths of these objects. Secondly, characteristic motion patterns are learned by clustering these trajectories into prototype curves. In the final step, motion recognition is then tackled by tracking the position within these prototype curves based on the same method, the extended Condensation algorithm, used for the object tracking.