Distributed diffusion unscented kalman filtering algorithm with application to object tracking

In this paper, a distributed diffusion unscented Kalman filtering algorithm based on covariance intersection strategy (DDUKF-CI) is proposed for object tracking. By virtue of the pseudo measurement matrix, the standard unscented Kalman filtering (UKF) is transformed to the information form that can be fused by the diffusion strategy. Then, intermediate information from neighbors are fused based on the diffusion framework to attain better estimation performance. Considering the unknown correlations in sensor networks, covariance intersection (CI) strategy is combined with the diffusion algorithm. Moreover, it is proved that the estimation error of the proposed DDUKF-CI is exponentially bounded in mean square using the stochastic stability theory. Finally, the performances of the proposed algorithm and the weighted average consensus unscented Kalman filtering (CUKF) are compared in a target tracking problem with a sensor network.