CamInSens - An Intelligent in-situ Security System for Public Spaces

In this paper we present a novel third-generation surveillance system for public spaces. In contrast to analyzing a threat after its occurrence, this systems aims on in-situ detection of salient trajectories and events. We use a network of smart camera nodes, which is capable of detecting and tracking people across an entire camera network. In addition, we developed an analysis framework which uses the extracted trajectory and event information from the smart camera network for autonomous online detection of potential threats in real-time. Finally, we present new visualization and interaction techniques for security control rooms and mobile devices based on an evaluation of existing infrastructures and components.