| 摘要: |
| 针对目标多特征数据，提出了一种基于简单证据的综合识别算法。首先，利用模糊理论将接收的特征参数与知识库中的特征参数进行比较，匹配求出目标模糊隶属度；然后，根据模糊隶属度和特征参数可信度构造包含“未知”的简单证据；最后，用简单证据组合规则进行证据合成，求出识别结果。经过数字算例验证，该算法既能处理冲突证据又能减少证据合成时间。 |
| 关键词: 目标识别 综合识别 模糊理论 冲突证据 简单证据 |
| DOI： |
|
| 基金项目: |
|
| Target multi-feature integrated recognition based on simple evidences |
| QIN Feng,WANG Qiandong,DU Juan |
| (Southwest China Institute of Electronic Technology，Chengdu 610036，China;Sichuan University of Media and Communications,Chengdu 611745,China) |
| Abstract: |
| For the target multi-feature data,a fast integrated recognition algorithm based on the simple evidences is introduced.First,the fuzzy measure between the received feature parameter and the feature parameter in the database is computed by fuzzy theory.Then,this simple evidence which includes “unknown”is made by the fuzzy measure and the feature parameter reliability.Finally,by the simple evidence combination rule,the recognition result is obtained from the combination evidence.The numerical examples show this method can not only deal with conflict evidences but also reduce the evidence combination time. |
| Key words: target recognition integrated recognition fuzzy theory conflict evidence simple evidence |
