Unimore logo AImageLab

A Reasoning Engine for Intruders' Localization in Wide Open Areas using a Network of Cameras and RFIDs

Abstract: Wide open areas represent challenging scenarios forsurveillance systems, since sensory data can be affected bynoise, uncertainty, and distractors. Therefore, the tasks oflocalizing and identifying targets (e.g., people) in such environmentssuggest to go beyond the use of camera-only deployments.In this paper, we propose an innovative systemrelying on the joint use of cameras and RFIDs, allowing usto “map” RFID tags to people detected by cameras and,thus, highlighting potential intruders. To this end, sophisticatedfiltering techniques preserve the uncertainty of dataand overcome the heterogeneity of sensors, while an evidentialfusion architecture, based on Transferable Belief Model,combines the two sources of information and manages conflictbetween them. The conducted experimental evaluationshows very promising results.


Citation:

Cucchiara, Rita; Fornaciari, Michele; Haider, Razia; Mandreoli, Federica; Martoglia, Riccardo; Prati, Andrea; Sassatelli, Simona "A Reasoning Engine for Intruders' Localization in Wide Open Areas using a Network of Cameras and RFIDs" Proceedings of CVPR 2011 Workshops, Colorado Springs, CO (USA), pp. 1 -40 , 20 June 2010, 2011 DOI: 10.1109/CVPRW.2011.5981728

 not available

Paper download: