Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Towards situational awareness systems based on semi-stationary multi-camera components

 
: Münch, David; Becker, Stefan; Grosselfinger, Ann-Kristin; Hübner, Wolfgang; Arens, Michael

:
Volltext urn:nbn:de:0011-n-2551477 (792 KByte PDF)
MD5 Fingerprint: ee56111e67b51707f4409cc18c5e27b5
Erstellt am: 14.8.2013


Lauster, Michael (Hrsg.) ; Fraunhofer Verbund Verteidigungs- und Sicherheitsforschung; Fraunhofer-Institut für Naturwissenschaftlich-Technische Trendanalysen -INT-, Euskirchen:
8th Future Security 2013. Security Research Conference : Berlin, September 17 - 19, 2013. Proceedings
Stuttgart: Fraunhofer Verlag, 2013
ISBN: 3-8396-0604-7
ISBN: 978-3-8396-0604-9
S.38-44
Security Research Conference "Future Security" <8, 2013, Berlin>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
camera network; weak calibration; situational awareness framework

Abstract
Automatic scene analysis using multiple cameras connected in a network is an important step to enhance the capabilities of future situation awareness tools. In this paper we present a self-adaptive multi-camera component, which can be considered as a single node of a camera network. The network node consists of three cameras: A high definition overview camera (the master) with a large field of view, a pan-tilt-zoom camera (the slave), and a long-wave infrared camera. In order to control the pan-tilt-zoom camera in terms of image coordinates of the master camera, the system learns the relationship between the individual cameras automatically. The incremental learning procedure is based on local image features. The system is a reliable basis for further generic image processing and situational awareness plugins: blob detection and tracking, person detection and identification, car detection and number plate recognition, as well as action recognition. On top of the acquired information a conceptual situation recognition system fuses all available input data and infers potentially interesting situations in the scene leading to comprehensive situational awareness.

: http://publica.fraunhofer.de/dokumente/N-255147.html