Surveillance camera scheduling: a virtual vision approach

We present a surveillance system, comprising wide field-of-view (FOV) passive cameras and pan/tilt/zoom (PTZ) active cameras, which automatically captures and labels high-resolution videos of pedestrians as they move through a designated area. A wide-FOV stationary camera can track multiple pedestrians, while any PTZ active camera can capture high-quality videos of a single pedestrian at a time. We propose a multi-camera control strategy that combines information gathered by the wide-FOV cameras with weighted round-robin scheduling to guide the available PTZ cameras, such that each pedestrian is viewed by at least one active camera during their stay in the designated area.A distinctive centerpiece of our work is the exploitation of a visually and behaviorally realistic virtual environment simulator for the development and testing of surveillance systems. Our research would be more or less infeasible in the real world given the impediments to deploying and experimenting with an appropriately complex camera sensor network in a large public space the size of, say, a train station. In particular, we demonstrate our surveillance system in a virtual train station environment populated by autonomous, lifelike virtual pedestrians, wherein easily reconfigurable virtual cameras generate synthetic video feeds that emulate those generated by real surveillance cameras monitoring richly populated public spaces.