摘要
本文提出的点目标状态下卫星及其伴飞锈饵的识别方法是基于BP网络与D-S理论相结合的信息融合方法。该方法采用目标的红外辐射特征,先用BP网络对目标进行粗分类,然后用D-S理论对BP网络的多次识别结果进行融合。仿真实验结果表明,D-S理论的最后输出比BP网络的输出识别率得到很大的改善。
An information fusion method based on the combination of BP neural networks and D S evidence theory to recognize satellite and its companion decoy in the state of point target is proposed in the paper.A BP networks is adopted to recognize the patterns with the characteristics of infrared(IR)radiation at first, then the D S evidence theory is used to fuse the results derived from the BP networks at different time. The result of emulatson shows that the true rate of D S is much higher than BP,and the ability to reject disturbance and noise is raised very much.
出处
《国防科技大学学报》
EI
CAS
CSCD
1997年第2期53-58,共6页
Journal of National University of Defense Technology
基金
国家自然科学基金