基于Choquet模糊积分的决策层信息融合目标识别
Decision-level information fusion for target recognition based on choquet fuzzy integral
-
摘要: 引入模糊测度和 Choquet模糊积分的概念后,信息融合目标识别可转化为各信源识别结果关于信源重要程度的广义 Lebesgue积分。该文给出了 Choquet模糊积分应用于决策层信息融合目标识别的通用技术路线,并提供了信源重要程度的度量方法。算法实用于红外/毫米波融合目标识别系统,融合识别结果与 D-S 证据理论方法作了比较,证明了基于 Choquet模糊积分方法的有效性。Abstract: After introducing the concept of fuzzy measures and Choquet fuzzy integral, infor-mation fusion for target recognition can turn into generalized Lebesgue integral of recognition result with respect to the degree of importance of source. This paper presents a generalized recognition flow in decision-level information fusion based on Choquet fuzzy integral, and pro-vides a method for measuring the degree of importance of source. The algorithm is proved in the real IR/MMW fusion recognition system, the fusion result of recognition which compares with that of D-S evidence theory shows the efficiency of the method based on Choquet fuzzy integral.
-
H. Tahani, J. Keller, Information fusion in computer vision using the fuzzy integral, IEEE Trans.on SMC., 1990, SMC-20(3), 733-741.[2]P.D. Gader, M. A. Mohanmed, J. M. Keller, Dynamic-programming-based handwritten word recognition using the Choquet fuzzy integral as the match function, Journal of Electronic Imaging,1996, 5(1), 15-24.[3]M. Sugeno, Fuzzy measure and fuzzy integrals, a survey, Fuzzy Automata and Decision Processes.New York, North-Holland, 1997, 89-102.[4]T. Murofushi, M. Sugeno, A theory of fuzzy measures, representations, the Choquet integral, and null sets, Journal of Math. Analysis and Applications, 1991, 32(2), 532-549.[5]W Runsheng, Quality analysis of information to be fused, Proceedings of the Int. Conf. on multisource-multisensor information fusion, Las Vegas, USA,1998, 635-641.[6]刘永祥,黎湘,庄钊文,谈判式时空整体决策信息融合方法研究,电子与信息学报,2001,23(11),1225-1230.[7]黎湘,刘永祥,庄钊文,等,基于D-S证据理论的修正融合目标识别模型,自然科学进展,2000,10(11),1040-1042. -
计量
- 文章访问数: 2292
- HTML全文浏览量: 110
- PDF下载量: 901
- 被引次数: 0
下载:
