KIRAS Security Research

2007

tripleB ID

The goal of the joint research project tripleB-ID is to help preventing, to detect and to support the investigation of crimes committed in security-critical infrastructure

The goal of the joint research project tripleB-ID is to help preventing, to detect and to support the investigation of crimes committed in security-critical infrastructure. The special focus is laid on crime prevention and on investigation support through video analytics starting from the identification and specification of threat scenarios worked out in close cooperation with the end users and the incorporation of socio-economic aspects of video surveillance in banks. By integrating social-scientific aspects from the beginning a close collaboration with the technical content is granted. From a technical point of view the project is based on the developments in the areas of machine vision, pattern recognition and visual sensors and novel computer vision methods are evaluated to cope with crowded indoor scenes. It deals with the development of a system for automatic event recognition or so-called “abnormal behavior” detection in video streams under special consideration of social and cultural aspects. Recognition of certain activities in a scene is achieved through automated analysis of the acquired image sequences with special focus on object tracking in a multi camera setup followed by event detection and completed with optimized data compression with efficient archiving. The methods investigated are evaluated under real-world conditions. Therefore the consumers define certain scenarios in order to install a prototype system: an operational real time processing prototype at the facilities of the end users will be implemented. tripleB ID utilizes off the shelf IP cameras and computing hardware which ensures an easy adoption of the the technologies and algorithm later on. The project is seen as a key enabler for all end-users to utilize their surveillance technology far beyond the existing possibilities of data storage and/or monitoring by human operators.

Project leader:
CogVis Software und Consulting Gmbh,

Project partner:
Technische Universität Wien, Institut 183 (PRIP)
Dr. techn. Dipl. Ing. Martin Kampel
Favoritenstr. 9, 1040 Wien
E-Mail kampel@prip.tuwien.ac.at

sOM Objektmanagement GmbH,
Johann Sattler, Geschäftsführer
Traungasse 12 / 6.Stock
1030 Wien

Institut für höhere Studien,
Stefan Vogtenhuber
Stumpergasse 56
1060 Wien

Bundesministerium für Inneres, Bundeskriminalamt Büro 1.6
Abteilung Kriminalprävention und Opferhilfe
Mag. Herwig Lenz, Abteilungsleiter
Josef Holaubek Platz 1
1090 Wien

Contact:
CogVis Software und Consulting Gmbh,
DI Michael Brandstötter, Geschäftsführer, Pulverturmgasse 3, 1090 Wien
T: 01 997 1594 – 0; F: 01 997 1594 – 91;
E-Mail: brandstoetter@cogvis.at

print