Data Fusion for Identity Estimation and Tracking of Centroidusing Imaging Sensor Data

Abstract

Two aspects involved in automatic target recognition namely, (i) Location and identityestimation (LIE) of a target by fusing infrared (IR) and acoustic sensor data, and (ii) centroidtracking for target state estimation using IR sensor data are discussed in this paper. The LIE hasbeen achieved using a combination of Bayesian fusion and one of the three search algorithmsnamely, metropolis hastings (MH), simulated annealing (SA) and gradual greedy (GG). It wasobserved that the performance of the GG search algorithms was better in terms of success ratewhich has been evaluated through Monte Carlo simulations. For tracking of the centroid, analgorithm, where the centroid of the gray level image is tracked using probabilistic data associationfilter, has been implemented. Simulated data results indicate good tracking performance of thisalgorithm. For robust tracking of centroid, the track from the imaging sensor was fused with thetrack from ground-based radar using state vector fusion. It was observed that fusion generatesrobust tracks even when there is data loss in one of the sensors.