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.
A Reasoning Engine for Intruders' Localization in Wide Open Areas using a Network of Cameras and RFIDs / Cucchiara, Rita; Fornaciari, Michele; Haider, Razia; Mandreoli, Federica; Martoglia, Riccardo; Prati, Andrea; Sassatelli, Simona. - ELETTRONICO. - (2011), pp. 33-40. (Intervento presentato al convegno 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011 tenutosi a Colorado Springs, CO, usa nel 20 June 2010) [10.1109/CVPRW.2011.5981728].
A Reasoning Engine for Intruders' Localization in Wide Open Areas using a Network of Cameras and RFIDs
CUCCHIARA, Rita;FORNACIARI, Michele;HAIDER, RAZIA;MANDREOLI, Federica;MARTOGLIA, Riccardo;PRATI, Andrea;SASSATELLI, Simona
2011
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.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
