摘要
DS证据组合规则可以在没有先验信息的情况下进行融合,这一优点使得DS证据理论在多传感器融合系统中应用非常广泛。但是各个证据的基本概率指派如何生成仍然是一个有待解决的问题。本文基于模糊匹配,提出了一种基本概率指派生成方法,并应用到多传感器目标识别中。用一个多传感器目标识别的实验表明:所提出的方法可以合理地生成基本概率指派,能够准确的识别目标。
In the framework of evidence theory, information fusion relies on the use of combination rule allowing the belief functions for the different propositions to be combined. A crucial role in evidence theory is played by Dempster's combination rule that has several interesting mathematical properties such as commutativity and associativity and can be combined without prior information, which make it widely used in many data fusion systems. However, how to construct basic probability assignment (BPA) is still an open issue. A fuzzy method to obtain basic probability assignment is proposed. A numerical example for target recognition is used to illustrated the efficiency of the proposed method.
出处
《传感技术学报》
CAS
CSCD
北大核心
2008年第10期1717-1720,共4页
Chinese Journal of Sensors and Actuators
基金
高校博士点基金资助(20060699026)
关键词
多传感器融合
证据理论
基本概率指派
模糊匹配
目标识别
multi-sensor data fusion
evidence theory
basic probability assignment
fuzzy match
target recognition