An Improved Distributed Data Fusion Method

Abstract

This paper proposes a generalized fusion algorithm that can be used for unknown correlation probability density function in practical distributed data fusion problems. In a distributed sensing environment where rumors propagate due to statistical correlation of signals, the algorithm can perform data fusion with any number of probability density functions. The interoperability requirements of distributed sensing systems define that the system cannot preprocess inputs to ensure statistical independence, while the covariance intersection algorithm and fast covariance intersection algorithm are only suitable for processing independent input signals such as Gaussian signals. In the case of an unknown correlation probability density function, the fusion goal of any number of non-Gaussian inputs can be achieved by minimizing the Chernoff information of the fusion probability density function. The simulation results show that the algorithm has good fusion effect.