Eventdriven Video Awareness Providing Physical Se

Authors: Dimitrios Georgakopoulos Donald Baker Marian Nodine Andrzej Cichoki

Publish Date: 2007/03/02

Volume: 10, Issue: 1, Pages: 85-109

PDF Link

Abstract

The Video Event Awareness Workbench VEAW analyzes surveillance video from thousands of video cameras and automatically detects complex events in nearrealtimeat pace with their input video streams For events of interest to security personnel VEAW generates and routes alerts and related video evidence to subscribing security personnel Complex event processing in VEAW is driven by userauthored awareness specifications comprised of interconnected spatiotemporal stream and statistical operators that consume and produce events described in VEAW’s surveillance ontology In this paper we introduce VEAW’s event driven architecture and describe its solutions for automating video surveillance including the orchestration of continuous and tasked video analysis algorithms eg for entity tracking and identification fusion of events from multiple sources in an installationspecific “world” model and proactive information gathering to deal with missing or incomplete information this is done by tasking video analysis algorithms and security personnel to provide it We also discuss how VEAW deals with late arriving information due to outofband video analysis tasks and overhead as well as a related resource optimization aimed at minimizing computation costs We illustrate the benefits of VEAW by illustrating its application on the automation of realworld security policies

Keywords: