信息融合理论研究进展:基于变分贝叶斯的联合优化

Information Fusion Progress: Joint Optimization Based on Variational Bayesian Theory

通过梳理近年信息融合理论的发展,分析了复杂目标跟踪系统中存在的非线性、多模式、深耦合、网络化、高维数和未知扰动输入等问题,指出现阶段目标跟踪系统中联合优化的必要性.继而,讨论了解决联合优化问题的主要方法,包括联合检测与估计,联合聚类与估计,联合关联与估计及联合决策与估计等.同时,着重介绍了变分贝叶斯辨识、估计和优化的统一框架和以其为基础的目标跟踪联合一体优化方法,并以天波超视距雷达为应用背景,给出在多路径多模式多目标跟踪场景下算法的一般性描述.最后,讨论了变分贝叶斯理论在目标跟踪领域的开放问题和未来研究方向.

By reviewing the development of information fusion theory in recent years,this paper analyzes the problems of target tracking systems,such as nonlinearity,multi-mode,deep coupling,networking,high-dimensionality and unknown disturbance input,and points out the necessity of joint optimization in target tracking system.Furthermore,several joint optimization methods,including the joint detection and estimation,joint clustering and estimation,joint association and estimation,joint decision and estimation are discussed.Meanwhile,we emphatically introduce the integrated optimization method based on the variational Bayesian theory that provides a unified framework of joint identification and estimation.Taking over-the-horizon radar as an application background,we give a general joint optimization method for the multipath multi-mode multi-target tracking system in this paper.In addition,future research directions of the variational Bayesian theory in the field of target tracking are discussed.