An Object- and Task-Oriented Architecture for Automated Video Surveillance in Distributed Sensor Networks

In this paper, an agent-based software architecture for automated wide area video surveillance systems is presented. The proposed concept is designed for detection and tracking of moving objects across multiple camera views. The surveillance system consists of a decentralized collaborative sensor network with object- and task-oriented architecture. At sensor node level, image processing algorithms are applied for event and object detection. In case of detection (e. g. motion) an agent-based multi-sensor processing cluster is created. Each instantiated cluster is responsible for observation of one object in the scene. Object handover is managed autonomously by the dynamic sensor clusters. The dynamic sensor clustering approach allows adding new sensors without resetting the system parameters, which is a big advantage in large sensor networks. Furthermore, by using the agent-based architecture it is possible to create a framework with an adaptive data and processing load. Additionally, upgrade of system capabilities can be done easily updating or adding new processing agents. The proposed concept has been proved on an experimental video surveillance system at the Fraunhofer IITB.

[1]  Takashi Matsuyama,et al.  Real-time cooperative multi-target tracking by communicating active vision agents , 2002, Object recognition supported by user interaction for service robots.

[2]  Takeo Kanade,et al.  Advances in Cooperative Multi-Sensor Video Surveillance , 1999 .

[3]  D.P. Garg,et al.  A generalized approach for inconsistency detection in data fusion from multiple sensors , 2006, 2006 American Control Conference.

[4]  Atsushi Nakazawa,et al.  Tracking Multiple People using Distributed Vision Systems , 2002, ICRA.

[5]  Pramod K. Varshney,et al.  Automatic camera selection and fusion for outdoor surveillance under changing weather conditions , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[6]  Mubarak Shah,et al.  Tracking across multiple cameras with disjoint views , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Stuart J. Russell,et al.  Object identification in a Bayesian context , 1997, IJCAI 1997.

[8]  M. Shah,et al.  KNIGHT M : A REAL TIME SURVEILLANCE SYSTEM FOR MULTIPLE OVERLAPPING AND NON-OVERLAPPING CAMERAS , 2003 .

[9]  Takeo Kanade,et al.  Algorithms for cooperative multisensor surveillance , 2001, Proc. IEEE.

[10]  A. Kak,et al.  A Look-up Table Based Approach for Solving the Camera Selection Problem in Large Camera Networks , 2006 .

[11]  Leonidas J. Guibas,et al.  Optimal Placement and Selection of Camera Network Nodes for Target Localization , 2006, DCOSS.

[12]  Mohan M. Trivedi,et al.  Intelligent environments and active camera networks , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[13]  M. Prokos,et al.  Cooperative multi-target surveillance using a mutational analysis approach , 2005, Proceedings, 2005 IEEE/ASME International Conference on Advanced Intelligent Mechatronics..

[14]  Jake K. Aggarwal,et al.  Tracking Human Motion in Structured Environments Using a Distributed-Camera System , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Mohan M. Trivedi,et al.  Networked omnivision arrays for intelligent environment , 2001, SPIE Optics + Photonics.

[16]  Lily Lee,et al.  Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame , 2000, IEEE Trans. Pattern Anal. Mach. Intell..