Real-time video content analysis applications for surveillance become more and more demanding. The need for load distribution, remote management and reusability calls for a component framework specialized in networked video streaming applications. Whereas lots of component frameworks exist nowadays, frameworks targeted at networked video streaming are scarce. Added requirements imposed by video surveillance applications include real-time computing and quick failover. The framework proposed in this paper meets these demands by enabling the distributed execution of video streaming applications in an efficient and resource-aware fashion. In this paper, we present the design of the proposed framework and evaluate a prototype implementation. The results of this evaluation show that this implementation is efficient and can successfully perform fail over handling, making it suitable for distributing surveillance applications.
|Title of host publication||Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA 2011, Las Vegas, Nevada, USA, July 18-21, 2011)|
|Editors||Hamid R. Arabnia|
|Publication status||Published - 2011|