一种基于加权DSmT的序列图像目标识别方法  

Target Recognition a Method of Sequential Images based on the Weight-DSmT

作　　者：侯俊[1] 苗壮[1] 潘泉[1] 

机构地区：[1]西北工业大学自动化学院,陕西西安710072

出　　处：《火力与指挥控制》2006年第7期53-56,共4页Fire Control & Command Control

摘　　要：通过对自动目标识别系统研究与分析,将DSmT引入到飞机序列图像识别中,构建基本置信指派及分类规则,提出了一种基于加权DSmT的序列图像目标识别方法,在分析权值选择特点的基础上,根据特征信息的置信指派组合有效权值,并且给出了基于加权DSmT融合规则的序列图像目标识别的流程,仿真结果表明,该方法提高了序列图像目标识别的准确性。With the research and analysis of automatic target recognition, the DSmT is introduced to sequential image recognition for airplanes, in which, the base belief assignment and the rule of classify are built. This paper presents a sequential image recognition algorithm based on the weight-DSmT. On the basis of analysis of the weight values＇ choice, the effective weight values is combined according with the feature information. Also, this method＇s produrese is provided. The simulation results show that this method is effective.

关 键 词：目标识别 序列图像 不变矩 DSMT 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]