Target Recognition Based on Fuzzy Dempster Data Fusion Method

Defence Science Journal

Qi Li¹  Xiaoyan Su¹  Dong Wang¹  Yong Deng² 

[1] Shanghai Jiao Tong University, Shanghai;southwest university, chongqing

关键词: Evidence theory;    fuzzy sets theory;    multi-sensor fusion;    Target recognition;   

DOI  :  

学科分类：社会科学、人文和艺术（综合）

来源: Defence Scientific Information & Documentation Centre

【 摘 要 】

Data fusion technology is widely used in automatic target recognition system. Problems in data fusion system are complex by nature and can often be characterised by not only randomness but also by fuzziness. To accommodate complex natural problems with both types of uncertainties, it is profitable to construct a data fusion structure based on fuzzy set theory and Dempster Shafer evidence theory. In this paper, after representing both, the individual attribute of target in the model database and the sensor observation or report as fuzzy membership function, a likelihood function was constructed to deal with fuzzy data collected by each sensor. The method to determine basic probability assignments of each sensor report is proposed. Sensor reports are fused through classical Dempster combination rule. A numerical example is illustrated to show the target recognition application of the fuzzy-Dempster approach. Defence Science Journal, 2010, 60(5), pp.525-530 , DOI:http://dx.doi.org/10.14429/dsj.60.576

【 授权许可】

Unknown