A novel architecture for behavior/event detection in security and safety management systems

Printer-friendly versionSend by email
Conference Proceedings (fully refereed)
17
4
2018
Thanos
Konstantinos-Georgios Thanos, Constandinos Rizogiannis, John M. A. Bothos, Dimitris M. Kyriazanos, Andreas Zalonis, Stelios C. A. Thomopoulos, National Ctr. for Scientific Research Demokritos (Greece)
In this paper the architecture of an autonomous human behavior detection system is presented. The proposed system architecture is intended for Security and Safety surveillance systems that aim to identify adverse events or behaviors which endanger the safety of people or their well-being. Applications include monitoring systems for crowded places (Malls, Mass transport systems, other), critical infrastructures, or border crossing points. The proposed architecture consists of three modules: the event detection module combined with a data fusion component responsible for the fusion of the sensor inputs along with relevant high level metadata, which are pre-defined features that are correlated with a suspicious event; an adaptive learning module which takes inputs from official personnel or healthcare personnel about the correctness of the detected events, and uses it in order to properly parameterise the event detection algorithm; and a statistical and stochastic analysis component.
Integrated Systems Laboratory (ISL)
Conference Short Name: 
SPIE
Conference Full Name: 
SPIE DCS Defense + Security
Conference Country: 
US:United States
Conference City: 
Orlando
Conference Venue: 
Gaylord Palms Resort & Convention Center
Conference Date(s): 
Sun, 15/04/2018 - Thu, 19/04/2018
Conference Level: 
International
Publisher: 
SPIE Signal Processing, Sensor/Information Fusion, and Target Recognition
Publication Series: 
XXVII
Volume: 
10646
Number: 
30
ISBN Code: 
10.1117/12.2307079

© 2019 - Institute of Informatics and Telecommunications | National Centre for Scientific Research "Demokritos"

Terms of Service and Privacy Policy