RFID Reader Planning for the Surveillance of Predictable Mobile Objects

Abstract

The surveillance of mobile objects is important for many applications in public security, logistics, traffic control, etc. Multiple RFID (Radio frequency identification) readers can be placed in the given region to fulfill this work. However, due to the mobility of objects and various kinds of RFID collisions, a proper planning of RFID readers is needed. Existing RFID reader planning approaches are designed for stationary scenarios and hence cannot have desirable performance when handling mobile objects. In this paper, we investigate the RFID reader planning problem for the surveillance of mobile objects whose motion can be predicted. We define the evaluation metric for the reader planning by dividing the surveillance time into multiple time slots and compute the successful identification of tags in individual time slot respectively. We further propose several reader planning strategies to handle RFID collisions in the surveillance. Genetic algorithm and particle swarm optimization are used to get the optimal result based on the evaluation metric and the reader planning strategies. We perform extensive simulations for validating the proposed approaches. The results show that our approach can achieve a good accuracy in the surveillance.