Cluster-based centralized data fusion for tracking maneuvering targets using interacting multiple model algorithm

Abstract

The interacting multiple model (IMM) algorithm has proved to be useful in tracking maneuvering targets. Tracking accuracy can be further improved using data fusion. Tracking of multiple targets using multiple sensors and fusing them at a central site using centralized architecture involves communication of large volumes of measurements to a common site. This results in heavy processing requirement at the central site. Moreover, track updates have to be obtained in the fusion centre before the next measurement arrives. For solving this computational complexity, a cluster-based parallel processing solution is presented in this paper. In this scheme, measurements are sent to the data fusion centre where the measurements are partitioned and given to the slave processors in the cluster. The slave processors use the IMM algorithm to get accurate updates of the tracks. The master processor collects the updated tracks and performs data fusion using 'weight decision approach'. The improvement in the computation time using clusters in the data fusion centre is presented in this paper.