Information Technology Reference
In-Depth Information
SUNAR
Surveillance Network Augmented by Retrieval
Petr Chmelar, Ales Lanik, and Jozef Mlich
Brno University of Technology, Faculty of Information Technology,
Bozetechova 2, 612 66 Brno, Czech Republic
{chmelarp,ilanik,imlich}@fit.vutbr.cz
http://www.fit.vutbr.cz
Abstract. The paper deals with Surveillance Network Augmented by
Retrieval (SUNAR) system - an information retrieval based wide area
(video) surveillance system being developed as a free software at FIT,
Brno University of Technology. It contains both standard and experi-
mental techniques evaluated by NIST at the AVSS 2009 Multi-Camera
Tracking Challenge and SUNAR performed comparably well.
In brief, SUNAR is composed of three basic modules - video process-
ing, retrieval and the monitoring interface. Computer Vision Modules are
based on the OpenCV Library for object tracking extended by feature
extraction and network communication capability similar to MPEG-7.
Information about objects and the area under surveillance is cleaned,
integrated, indexed and stored in Video Retrieval Modules. They are
based on the PostgreSQL database extended to be capable of similarity
and spatio-temporal information retrieval, which is necessary for both
non-overlapping surveillance camera system as well as information anal-
ysis and mining in a global context.
Keywords: SUNAR, wide area, surveillance, video analytics, retrieval,
similarity, tracking, trajectory, integration.
1
Introduction
Nowadays, there is a lot of data produced by wide area surveillance networks.
This data is a potential source of useful information both for on-line monitoring
and crime scene investigation. Machine vision techniques have dramatically in-
creased in quantity and quality over the past decade. However, the state of the
art still doesn't provide the satisfactory knowledge, except some simple problems
such as people counting and left luggage or litter detection.
Justin Davenport in Evening Standard [6] showed statistics of crime-fighting
CCTV cameras in Great Britain. The country's more than 4.2 million CCTV
cameras caught (in 2007) each British resident as many as 300 times each day.
BBC News [1] informed that half a million pounds a year was spent on talking
cameras helping to pick up litter. Yet 80% of crime is unsolved. Well, we agree
that high quality crime investigation is the best prevention.
 
Search WWH ::




Custom Search