基于D-S证据理论的目标属性辨识研究

D—S证据组合理论已经成为不确定性推理的一种重要方法，基于该理论的多传感器决策层信息融合已得到广泛应用。本文在简要介绍D—S证据组合理论框架基础上，阐述了基于D—S证据组合理论的信息融合一般步骤及决策层判决方法；分析了发生证据严重冲突时，Dempster证据组合规则出现的不可靠和不合理的本质原因，介绍了针对D—S证据组合规则进行修正的几种主要方法；最后，提出了需要继续深入探讨的问题。

D-S Evidence Theory-Based Multisensor Information Fusion at Decision Level

The Dempster-Shafer (D-S) evidence theory is an important tool of uncertainty reasoning and multisensor information fusion object identification based on D-S evidence theory is widely used in various information fusion systems. A few concepts of D-S evidence theory and D-S evidence combination rule and decision methods are presented and the program of D-S evidence combination rule on Basic Probability Assignment Function (BPAF) is described. It is analysed that why unreliability and unreasonability about the D-S evidence theory would result from a serious evidence conbination conflict. Some modified D-S evidence combination methods and problems to further address are discussed.