Large Scale Surveillance, Detection and Alerts Information Management System for Critical Infrastructure

A proof-of-concept system for large scale surveillance, detection and alerts information management (SDAIM) is presented in this paper. Various aspects of building the SDAIM software system for large scale critical infrastructure monitoring and decision support are described. The work is currently developped in the large collaborative ZONeSEC project (www.zonesec.eu). ZONeSEC specializes in the monitoring of so-called Wide-zones. These are large critical infrastructure which require 24/7 monitoring for safety and security. It involves integrated in situ and remote sensing together with large scale stationary sensor networks, that are supported by cross-border communication. In ZONeSEC, the specific deployed sensors around the critical infrastructure may include: Accelerometers that are mounted on perimeter fences; Underground acoustic sensors; Optical, thermal and hyperspectral video cameras or radar systems mounted on strategic areas or on airborne UAVs for mission exploration. The SDAIM system design supports the ingestion of the various types of sensors platform wide-zones’ environmental observations and provide large scale distributed data fusion and reasoning with near-real-time messaging and alerts for critical decision-support. On a functional level, the system design is founded on the JDL/DFIG (Joint Directors of Laboratories/Data Fusion Information Group) data and information fusion model. Further, it is technologically underpinned by proven Big Data technologies for distributed data storage and processing as well as on-demand access to intelligent data analytics modules. The SDAIM system development will be piloted and alidated at various selected ZONeSEC project wide-zones [1]. These include water, oil and transnational gas pipelines and motorway conveyed in six European countries.

[1]  Ehud Rivlin,et al.  Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Antonio Fernández-Caballero,et al.  A survey of video datasets for human action and activity recognition , 2013, Comput. Vis. Image Underst..

[3]  Theodore W. Berger,et al.  APPLICATION OF NON-HOMOGENOUS HMM ON DETECTING SECURITY FENCE BREACHING , 2010, ICASSP 2010.

[4]  Mubarak Shah,et al.  Automated Visual Surveillance in Realistic Scenarios , 2007, IEEE MultiMedia.

[5]  Roland Mörzinger,et al.  Using Gait Features for Improving Walking People Detection , 2010, 2010 20th International Conference on Pattern Recognition.

[6]  Qinfen Zheng,et al.  A temporal variance-based moving target detector , 2005 .

[7]  Jin Young Choi,et al.  Learning with Adaptive Rate for Online Detection of Unusual Appearance , 2014, ISVC.

[8]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Luc Van Gool,et al.  Hunting Nessie - Real-time abnormality detection from webcams , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[10]  Venkatesh Saligrama,et al.  Video anomaly detection based on local statistical aggregates , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Dale A. Lambert,et al.  A blueprint for higher-level fusion systems , 2009, Inf. Fusion.

[12]  Zoheir A. Sabeur,et al.  Agile Data Fusion and Knowledge Base Architecture for Critical Decision Support , 2013, Int. J. Decis. Support Syst. Technol..

[13]  Nicolai Meinshausen,et al.  Quantile Regression Forests , 2006, J. Mach. Learn. Res..

[14]  Bohyung Han,et al.  Efficient extraction of human motion volumes by tracking , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.