Multi-sensor fusion for robust target tracking in the simultaneous presence of set-membership and stochastic Gaussian uncertainties

This study proposes a novel data fusion algorithm in sensor networks with simultaneous presence of set-membership and stochastic Gaussian measurement uncertainties. The proposed method is grounded in the marriage of ellipsoidal calculus theory and data compression algorithm. The point-valued measurement and the set-valued measurement are compressed into a uniform framework during the estimation. An optimal Kalman gain is obtained that minimises the upper bound of the mean square error of the estimation set. The proposed algorithm is applied to the target tracking problem and the estimation results show that the proposed algorithm improves the tracking performance.