Enabling technologies on hybrid camera networks for behavioral analysis of unattended indoor environments and their surroundings

Abstract

This paper presents a layered network architecture and the enabling technologies for accomplishing vision-based behavioral analysis of unattended environments. Specifically the vision network covers both the attended environment and its surroundings by means of hybrid cameras. The layer overlooking at the surroundings is laid outdoor and tracks people, monitoring entrance/exit points. It recovers the geometry of the site under surveillance and communicates people positions to a higher level layer. The layer monitoring the unattended environment undertakes similar goals, with the addition of maintaining a global mosaic of the observed scene for further understanding. Moreover, it merges information coming from sensors beyond the vision to deepen the understanding or increase the reliability of the system. The behavioral analysis is demanded to a third layer that merges the information received from the two other layers and infers knowledge about what happened, happens and will be likely happening in the environment. The paper also describes a case study that was implemented in the Engineering Campus of the University of Modena and Reggio Emilia, where our surveillance system has been deployed in a computer laboratory which was often unaccessible due to lack of attendance.

Multi-Camera Coordination and Control in Surveillance Systems

“…Simpler tasks such as object detection are performed in low-tier sensors in order to prompt the upper-tier sensor to perform complex operations such as object tracking and recognition. Later, Gualdi et al [2008] presented a layered network architecture consisting of Perimeter layer, Environment layer and Reasoning layer. It was used for behavior analysis in indoor environments using hybrid camera networks.…”

“…Anomaly detection [Krumm et al 2000;Petrushin et al 2006;Tong et al 2007;Arsic et al 2008;Schreiber et al 2013;Yuan et al 2003] No coordination, only data fusion Human behavior analysis [Gualdi et al 2008] Layered approach Controlling PTZ cameras [Natarajan et al 2014a;Natarajan et al 2012aNatarajan et al , 2012bNatarajan et al 2014bNatarajan et al , 2014c Decision theory [Ding et al 2012b;Lai et al 2010;Ding et al 2012a] Game theory [Krahnstoever et al 2008;Piciarelli et al 2009;Sommerlade and Reid 2010;Ilie and Welch 2011;Pasqualetti et al 2013] Ad-hoc optimization State machine CAVIAR (Context Aware Vision using Image-based Active Recognition), 3DPeS (3D PEople Surveillance Dataset), VIRAT (Video and Image Retrieval and Analysis Tool), i-LIDS (Imagery Library for Intelligent Detection Systems) and many more. A comparative study of these datasets has been presented by Ellis and Ferryman [2011].…”