多传感器目标跟踪的实时剔野方法

考虑了目标跟踪和航天测控中测量数据的实时剔野问题，测量数据集合中严重偏离大部分数据所呈现趋势的小部分数据点被称为野值点，野值的剔除对提高目标跟踪精度有十分重要的意义，己有的剔野方法从工程应用角度看，存在不适宜成串出现的野值。需要人工干顾、计算量大，不适宜在线快速处理等缺点，多传感器目标跟踪系统可以通过合理利用传感器的互补与冗余信息来能提高系统的目标跟踪性能，本文在多传感器目标跟踪条件下，综合利用多传感器数据形成的对目标状态参数的正确描述和测量数据集合主体的变化趋势，给出了实时、准确、高效地识别测量数据中野值点的方法。仿真结果表明利用多传感器目标跟踪中航迹融合的分布式融合方法，可以快速、有效地解决野值斑点剔除问题。

Realtime outliers detection in multi-sensor target traching

The problem of real time outliers detection is considered.The minor part data that deviate the tendency showed by the whole measurement data set is called outlier.Outlier detection is significant of the improvement of target tracking accuracy.Existed outlier detection methods have such deficiency as not suitable for processing patchy,operation number is large,needing factitiously interfere,not suitable for on line processing.Multi sensor target tracking system can improve target tracking performance by the mutually reinforced and redundant information from each sensor.The method of combining the exact target state parameter fused by multi sensor tracking data and the tendency of the whole tracking data to detect outliers is proposed.Simulation results show that the distributed multi sensor fusion method can resolve the problem of patchy detection efficiently and quickly.