Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Architecture for and evaluation of situational analysis in the real world

: Münch, David

Volltext urn:nbn:de:0011-n-3158464 (1.1 MByte PDF)
MD5 Fingerprint: 970b68f5e7ebf2c602dd8114e711f838
Erstellt am: 27.11.2014

Thoma, K. (Ed.); Häring, I. (Ed.); Leismann, T. (Ed.) ; Fraunhofer-Institut für Kurzzeitdynamik, Ernst-Mach-Institut -EMI-, Freiburg/Brsg.:
9th Future Security 2014. Security Research Conference : September 16 – 18, 2014, Berlin; Proceedings
Stuttgart: Fraunhofer Verlag, 2014
ISBN: 978-3-8396-0778-7
ISBN: 3-8396-0778-7
Security Research Conference "Future Security" <9, 2014, Berlin>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
video surveillance; situation recognition; real-time system

Automatic situational analysis in video surveillance enables smart and exhaustive observation of what is happening in a scene. In real world applications there arise special challenges concerning imperfect input data and real-time processing requirements. In this paper a hierarchical and distributed architecture tackling situation analysis in the real world is introduced, described, and exemplarily evaluated. The architecture introduced is hierarchically and modularly structured. The low-level data acquisition and processing is encapsulated in self-contained building blocks. These modules include video acquisition, sensor feedback and control, person detection and tracking, and vehicle identification. High level situation analysis is provided with a knowledge based approach using Fuzzy Metric Temporal Logic and Situation Graph Trees. The communication between the modules is realized with a persistence layer serving simultaneously as the knowledge base for the inference engine. Finally, the overall performance of recognizing situations is evaluated.