Cloud-Based Video Surveillance System Using EFD-GMM for Object Detection

摘要

Nowadays, new generation of video surveillance systems integrates lots of heterogeneous cameras to collect, process, and analyze video for detecting the objects of potential security threats. The existing systems tend to reach the limit in terms of scalability, data access anywhere, video processing overhead, and massive storage requirements. A novel cloud computing can provide scalable and powerful techniques for large-scale storage, processing, and dissemination of video data. Furthermore, the integration of cloud computing and video processing technology offers more possibilities for efficient deployment of surveillance systems. This paper deploys the framework of a cloud-based video surveillance system and proposes an EFD-GMM approach for object detection in the overhead video processing. A prototype surveillance system is also designed to validate the proposed approach. It finally shows that the proposed approach is more efficient than GMM in video processing of cloud-based system.