Joint detection and estimation fusion in the presence of correlated sensor quantized data

This paper addresses the problem of joint detection and estimation fusion when sensor quantized data are correlated in the distributed system. The traditional methods to handle this joint problem tend to treat the detection and estimation tasks separately, which put more emphasis on the detection part but treat the estimation part sub-optimally. In this work, the joint detection and estimation fusion model is described based on the idea of multi-objective optimization, providing attainable flexibility between the detection and estimation performance. There into, the critical joint likelihood function for multi-sensor correlated data is evaluated based on the Copula theory. Simulation results show that the copula-based joint model outperforms the dependency-ignoring model. Further, the proposed approach is superior to the comparative GLRT (Generalized likelihood ratio test) and NP (Neyman-Pearson) in term of the average estimation cost.