智能内窥镜导航中一种新的多传感器融合算法  

A New Algorithm of Multi-sensor Information Fusion for Intelligent Endoscope Navigation

作　　者：张震[1] 王震[1] 章亚男[1] 沈林勇[1] 钱晋武[1] 

机构地区：[1]上海大学机电工程与自动化学院,上海200072

出　　处：《机器人》2008年第3期264-267,272,共5页Robot

基　　金：国家863计划资助项目(2001AA422180);国家自然科学基金资助项目(50075050);教育部高等学校重点学科建设资助项目(BB67);上海市重点学科建设资助项目(Y0102)

摘　　要：首先介绍了智能内窥镜导航中视觉传感器和触觉传感器的导航原理及应用情况;然后通过分析各种传感器的数据,对各种传感器的信息进行可信度分配;最后采用Dempster-Shafer证据理论方法,以各种传感信息作为证据,引导内窥镜.试验证明,在内窥镜导航中使用多传感器融合算法后,可以过滤单个传感器的微小变化,放大单个传感器的显著变化,有利于引导内窥镜的介入,能有效解决内窥镜穿孔问题.First, the principles and application of vision sensors and tactile sensors used in endoscope navigation are introduced. Next, probability is assigned to the information of various sensors by analyzing the data from them. At last, Dempster-Shafer theory of evidence is used and various information of sensors is taken as evidence to navigate the endoscope. Experiment shows that the tiny change of single sensor can be filtrated and the remarkable change can be magnified with the multi-sensor information fusion algorithm for endoscope navigation, which is advantageous to the endoscope＇s insertion and can effectively solve the problem of endoscope perforation.

关 键 词：内窥镜导航 可信度分配 DEMPSTER-SHAFER证据理论 

分 类 号：TH24[机械工程—机械制造及自动化]