An intelligent surveillance video analysis service in cloud environment

Nowadays, digital surveillance systems are ubiquitously installed and continuously generating huge amount of video data. More often than not, it requires human to identify potential threats. To address that problem, we propose a Platform-as-a-Service (PaaS) architecture to conduct large scale video analysis in more systematic and efficient ways. In addition, the video analysis application implemented on the proposed PaaS platform provides a more user friendly interface for analyzing video footage. In this paper, we present the construction and implementation steps of a real-world video analysis service based on our previous work for a citywide security service. We successfully integrated over 25 thousands of surveillance devices throughout the city. The integrations of the NVR/DVRs, license plate number recognition engine, and the camera health monitoring engine will be demonstrated. Finally, we conclude with discussions on why we believe the proposed solution has the potential to become the standard for deploying intelligent video surveillance network.