An evidential fusion architecture for people surveillance in wide open areas

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.