Efficient communication for large-scale robust image processing with smart camera devices

Large-scale data acquisition and distributed processing of video material requires smart camera devices to collaborate over arbitrary transport networks with no further centralized coordinating instances. Especially in the context of surveillance and security in public transportation networks, the knowledge of spatio-temporal traffic flows can support applications like anomaly detection, smart navigation, or prosecution. Therefore, the problem of autonomously estimating a logical camera topology with respect to scalability, agility and robustness must be solved by efficient communication about distributed detected events. Simple broadcasting or flooding of information does not scale well with the number of nodes and leads to strong requirements on bandwidth and processing power. Thus, a generic system model, describing the process of generating event-based distributed knowledge without making use of flooding, broadcast or multicast, is introduced and evaluated. The results of a conducted simulation study reveal the potential of saving a significant amount of messages on the one hand, and being able to handle poor performance of object recognition algorithms on the other hand.