论文部分内容阅读
本文针对高干扰环境下测量数据的不确定性,提出了多传感器多目标特征信息融合的数据关联模糊逻辑推理方法。研究了基于最陡下降法构造全模糊模型关联系统的自学习算法,以及多个主传感器数据融合对模糊关联系统性能的改善。其基本思想是通过融合多种特征信息进行模糊逻辑推理,改善数据关联质量的同时,不增加整个目标跟踪系统的复杂性。理论分析和应用举例都证明了模糊逻辑系统融合多种数据形式解决关联问题的能力。
Aiming at the uncertainty of measurement data in high interference environment, this paper proposes a data-related fuzzy logic inference method based on multi-sensor multi-target feature information fusion. The self-learning algorithm based on the steepest descent method to construct the all-fuzzy model association system is studied, and the performance improvement of the fuzzy association system based on data fusion of multiple main sensors is studied. The basic idea is to improve the quality of data association without increasing the complexity of the whole target tracking system by fuzzy logic reasoning by combining a variety of feature information. Theoretical analysis and application examples all prove the ability of fuzzy logic system to solve the correlation problem by combining multiple data forms.