The SfinX Video Surveillance System

Abstract

In a surveillance system, video signals are generated by multiple cameras with or without spatially and temporally overlapping coverage. These signals need to be compressed, fused, stored, indexed, and then summarized as semantic events to allow efficient and effective querying and mining. This paper presents the hardware and software architecture of SfinX, a next-generation video-surveillance system. We analyze each component within the software architecture and identify research issues. Finally, we present preliminary results on the performance of various components of SfinX.