首页 | 本学科首页   官方微博 | 高级检索  
     检索      

A New Approach to Evidence Combination and Its Application to Targets Recognition in Image Sequence
作者姓名:陈良洲  施文康  杜峰
作者单位:[1]Dept. of Instrument Science & Tech. , Huazhong Univ. of Science & Tech. , Wuhan 430074,China [2]School of Electronics & Electrical Eng. , Shanghai Jiaotong Univ. , Shanghai 200030, China
摘    要:The classical Dempster's combination rule is the most popular rule of combinations,but it is a poor solution for the management of the evidence conflict at the normalization step.When deal with high conflict information it can even involve counter-intuitive results.Based on evidence distance,some inherent characters of evidences are extracted,and discount method to combine conflicting evidence was proposed.The discount method can be also used to fuse image sequences to recognize targets.Examples show that the proposed method can provide reasonable results with good convergence efficiency.

关 键 词:显著理论  目标识别  证据冲突  折扣系数
文章编号:1007-1172(2007)02-0143-05
修稿时间:2006-05-08

A New Approach to Evidence Combination and Its Application to Targets Recognition in Image Sequence
CHEN Liang-zhou,SHI Wen-kang,DU Feng.A New Approach to Evidence Combination and Its Application to Targets Recognition in Image Sequence[J].Journal of Shanghai Jiaotong university,2007,12(2):143-147.
Authors:CHEN Liang-zhou  SHI Wen-kang  DU Feng
Abstract:The classical Dempster's combination rule is the most popular rule of combinations,but it is a poor solution for the management of the evidence conflict at the normalization step.When deal with high conflict information it can even involve counter-intuitive results.Based on evidence distance,some inherent characters of evidences are extracted,and discount method to combine conflicting evidence was proposed.The discount method can be also used to fuse image sequences to recognize targets.Examples show that the proposed method can provide reasonable results with good convergence efficiency.
Keywords:evidence theory  conflict evidence  discount coefficient  target recognition
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号