A new evidential fusion architecture is proposed to build anhybrid articial intelligent system for people surveillance in wide open areas. Authorized people and intruders are identied and localized thanks to the joint employment of cameras and RFID tags. Complex Event Processing and Transferable Belief Model are exploited for handling noisy data and uncertainty propagation. Experimental results on complex synthetic scenarios demonstrate the accuracy of the proposed solution.
A new evidential fusion architecture is proposed to build an hybrid artificial intelligent system for people surveillance in wide open areas. Authorized people and intruders are identified and localized thanks to the joint employment of cameras and RFID tags. Complex Event Processing and Transferable Belief Model are exploited for handling noisy data and uncertainty propagation. Experimental results on complex synthetic scenarios demonstrate the accuracy of the proposed solution. © 2011 Springer-Verlag.
An evidential fusion architecture for people surveillance in wide open areas / Fornaciari, M.; Sottara, D.; Prati, A.; Mello, P.; Cucchiara, R.. - ELETTRONICO. - 6678:1(2011), pp. 239-246. (Intervento presentato al convegno 6th International Conference on Hybrid Artificial Intelligent Systems (HAIS 2011) tenutosi a Wroclaw, Poland nel May 23-25, 2011.) [10.1007/978-3-642-21219-2_31].
An evidential fusion architecture for people surveillance in wide open areas
Fornaciari M.;Cucchiara R.
2011
Abstract
A new evidential fusion architecture is proposed to build an hybrid artificial intelligent system for people surveillance in wide open areas. Authorized people and intruders are identified and localized thanks to the joint employment of cameras and RFID tags. Complex Event Processing and Transferable Belief Model are exploited for handling noisy data and uncertainty propagation. Experimental results on complex synthetic scenarios demonstrate the accuracy of the proposed solution. © 2011 Springer-Verlag.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