A Framework For An Event Driven Video Surveillance System

Abstract

In this paper we present an event driven surveillance system that uses multiple cameras. The purpose of this system is to enable thorough exploration of surveillance events. The system uses a client-server web architecture as this provides scalability for further development of the system infrastructure. The system is designed to be accessed by surveillance operators who can review and comment on events generated by our event detection processing modules. We do not just focus on event detection, but are working towards the optimization of event detection. A multiple camera network system that tracks a moving object (or person) and decides if this is an event of interest is also examined. Dynamic switching of the cameras is implemented to aid in human monitoring of the network. The camera displayed in the main view should be the camera with the most interesting activity occurring. Unusual activity is defined as activity occurring that is not of the norm. Normal activity is considered to be everyday repeated activity. Further thought will be given to the extension of this system into a distributed system that would effectively create an event web system. Our contributions are to the development of automated real-time switching of camera views to aid camera operators in the effort of effective video surveillance, and also the detection of events of interest within a surveillance environment, with appropriate alerts and storage of these events. To the best of our knowledge this system provides a novel approach to the technological surveillance paradigm.