A peer-to-peer collaboration framework for multi-sensor data fusion

A peer-to-peer collaboration framework for multisensor data fusion in resource-rich radar networks is presented. In the multi-sensor data fusion, data needs to be combined in such a manner that the real-time requirement of the sensor application is met. In addition, the desired accuracy in the result of the multi-sensor fusion has to be obtained by selecting a proper set of data from multiple radar sensors. A mechanism for selecting a set of data for data fusion is provided considering application-specific needs. We also present a dynamic peer-selection algorithm, called Best Peer Selection (BPS) that chooses a set of peers based on their computation and communication capabilities to minimize the execution time required for processing data per integration algorithm. Simulationbased results show that BPS can deliver a significant improvement in execution time for multi-radar data fusion.