不完全量测下基于后验置信度残差检测的光电跟踪滤波器设计

 不完全量测下残差检测算法的设计是光电跟踪滤波器设计的关键,算法的正确检测概率直接影响到跟踪滤波器的估计性能.为了进一步提升传统残差检测算法的正确检测概率,提出了一种基于后验置信度的残差检测算法.其主要思想是在传统残差检测算法的基础上首先增加一个检测门限,对处于两个门限之间的残差,利用模糊隶属度函数方法进行模糊化,得到残差的似然概率,进而结合跟踪系统的先验探测信息,计算出探测数据的后验置信度,并根据计算结果对跟踪系统的数据探测情况进行判定.进一步,基于后验置信度残差检测算法,在不完全量测下设计了基于无偏转换量测的光电跟踪滤波器,并给出了跟踪系统统计意义下的Cramer-Rao下界(CRLB).Monte-Carlo仿真表明:基于后验置信度残差检测的光电跟踪滤波器,与基于传统残差检测的光电跟踪滤波器相比,估计性能有了进一步提升,特别是当跟踪系统探测概率较低时,估计性能提升更加显著,并且估计误差均方差(RMSE)已逼近跟踪系统统计意义下的CRLB.

Optic-Electric Tracking System Filter Design Based on Posterior Confidence Residual Test with Intermittent Observations

A key step of filter design for optic-electric tracking system with intermittent observations is to design residual test algorithm,and test probability of residual test algorithm influence estimate performance of tracking filter directly.A new residual test algorithm based on posterior confidence is presented in order to improve test probability of traditional residual test algorithm.The new algorithm firstly adds a test threshold based on traditional residual test algorithm,and then the residuals between the two thresholds can be fuzzed by means of fuzzy membership function and the likelihood probability of residuals can be obtained,and combined with the prior detection information,the posterior confidence of detection data can be calculated.Therefore the detection situation of tracking system can be determined based on the calculated posterior confidence.Moreover,with intermittent observations,a target tracking filter of unbiased converted measurement is designed based on the proposed residual test algorithm,and the Cramer-Rao low bounds(CRLB) of tracking system is also presented under the statistic significance.Monte-Carlo simulation results show that,with intermittent observations,the estimate performance of the designed target tracking filter can be significantly improved compared with that of traditional ones,when detection probability of tracking system is low,and the Root Mean Square of estimate Error(RMSE) of the designed tracking filter is close to the average of CRLB of the tracking system.