基于模糊集合的证据理论信息融合方法  

Evidence theory information fusion method based on fuzzy set

作　　者：韩峰[1] 杨万海[1] 袁晓光[1] 

机构地区：[1]西安电子科技大学电子工程学院,西安710071

出　　处：《控制与决策》2010年第3期449-452,共4页Control and Decision

基　　金：陕西省教育厅专项基金项目(06JK281)

摘　　要：针对证据理论应用中基本概率分配函数(mass函数)和多传感器信息融合中各传感器测量数据的可靠程度均难以确定的问题,提出了一种基于模糊集合的证据理论信息融合方法.该方法首先利用模糊理论中的相关性函数来计算多传感器的相互支持程度;然后由隶属函数得到每个传感器提供信息的可信度;再将各传感器的支持度和可信度转化成基本概率分配函数即mass函数;最后利用证据理论对多传感器信息进行融合.仿真结果表明,该方法获得的结果具有更高的精度和可靠性.Focused on the problem that it is difficult to set up the basic probability assignment function （mass function） in the evidence theory and determine the reliability of each sensor in the process of the multi-sensors data fusion,an information fusion method based on fuzzy set and evidence theory is proposed. The mutual supportability of multiple sensors is obtained from the correlation function. Then by using the membership function,the reliability of information provide by each sensor is gained. The supposed fusion result can be produced on the basis of evidence theory. The method is simple computationally and can objectively reflect the reliability of each sensor and interrelationship between these sensors. Finally,the simulation result shows that the fusion results have higher precision and reliability compared with other methods.

关 键 词：多传感器 证据理论 模糊集合 信息融合 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]