摘要
从D-S证据理论的基本概念和证据的融合推理方法出发,建立了多目标特征信息融合识别框架,并提出一种符合目标识别特点的基本可信度分配构造方法。该方法把识别对象看作一个信息系统,运行过程中不断产生各种信息,并将信息加工成目标特征。通过特定的识别决策规则,得出识别结论。给出了一个多目标信息进行识别的实例,结果表明该方法能够有效地提高目标识别可信度,减小识别的不确定性。
Starting with the basic conception and evidential fusion reasoning method of Dempster-Shafer evidential theory, multi-target characteristic information fusion recognition frame is constructed, A new approach to target recognition based on multi-information fusion of target characteristic, Dempster-Shafer evidential theory and basic probability assignment contribution method is proposed, An example is present, It is shown that the method is good to improve the reliability of the recognition and decrease the uncertainty markedly.
出处
《弹箭与制导学报》
CSCD
北大核心
2006年第4期276-278,共3页
Journal of Projectiles,Rockets,Missiles and Guidance
关键词
信息融合
证据理论
目标识别
基本可信度分配
information fusion
evidential theory
target recognition
basic possibility assignment
