A generic approach and process architecture for task-oriented sensor data processing is presented. Hereby, we focus on the application of video surveillance in large camera networks. Firstly, advantages of the proposed task-oriented video processing, compared to today´s (sensor-oriented) video surveillance systems, are described. Secondly, a generic process framework is presented, which has been designed for task-oriented video processing. Finally, system components of the task-oriented framework needed for the task of multi-camera person tracking are introduced.