D-S证据理论在多传感器信息融合中的改进  

Improvement of D-S Theory of Evidence in Multi-sensor Information Fusion System

作　　者：李向莉[1] 吕建平[1] 

机构地区：[1]苏州大学电子信息学院,江苏苏州215021

出　　处：《现代电子技术》2005年第16期16-18,共3页Modern Electronics Technique

摘　　要：详细阐明了多传感器信息融合的一种方法——D-S证据理论,他是一种处理不确定性问题的有用方法,但是DS证据理论组合规则的一些不足影响证据理论的应用,通过深入分析,针对该方法的不足提出了一种修正的组合方法,这样不仅能够用于组合冲突比较大的证据,而且能够根据各条证据所包含的不同信息量进行自适应加权组合,改进了基本D-S证据理论的组合准则,提高了其融合性能,并通过实例证明了该方法的有效性。This paper elaborates the multi-sensor information principle about Dempster-Shafer theory of evidence. It＇s an useful method to deal with uncertain problems. But its application is limited by the shortcomings of the combination rules. And an improved combination method is put forward according to shortage of the formula through in depth analysis. Thus we can＇t only make up conflicted evidence like this with different on-line weights, but also carry out adaptive weighting association according to the amount of information that an evidence includes. Thus improving the combination criteria of D-S theory of evidence as well as increasing its fusion capability, and some examples have been done to demonstrate that the new method is efficient.

关 键 词：D-S证据理论 信息融合 多传感器 基本概率赋值函数 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]