Dynamic Reconfiguration Methods for Active Camera Networks

This thesis presents dynamic reconfiguration methods for Active Camera Networks. Active Camera Networks consist of autonomous vehicles - each one equipped with a visual sensor - communicating wirelessly with each other in order to perform surveillance tasks in a collaborative way. Recent advances in the area of robotics have led to the development of autonomous vehicles and unmanned aerial vehicles that can be used to explore operational environments such as urban areas or unknown building structures. This thesis is devoted to the development of dynamic reconfiguration methods, which allow for distributed control of collaborating cameras in dynamic environments. Thus, they act self-organizing and with the least a priori information in terms of their environment. The focus is on the wide-area target acquisition of moving targets in a surveillance area. It addresses application scenarios where events unfold over a large geographic area and close-up views have to be acquired for biometric tasks such as face detection. The main problem is to coordinate numerous cameras in order to reach a system behavior that only one capture of each target is acquired.