摘 要:针对标准容积卡尔曼滤波(CKF)在目标跟踪中出现的问题,根据系统噪声统计特性不准确或未知的特点,提出一种基于协方差匹配原则的自适应容积卡尔曼滤波算法。该算法通过利用新息序列与残差序列来实现对观测噪声协方差和过程噪声协方差矩阵的实时跟踪,进而进行在线调整噪声统计特性,能够有效的改善由于噪声特性未知所引起的滤波发散相关问题。将该算法应用在目标跟踪仿真实验中,结果表明,与标准CKF 算法相比,在系统噪声统计特性未知的情况下,该算法具有更好的实时性,不仅抑制了滤波器的发散问题,而且提高了对目标的跟踪精度。
关键词:容积卡尔曼滤波算法;协方差匹配;自适应滤波;目标跟踪
中图分类号:TN713;TN953;V557 文献标识码:A 文章编号:2096-4706(2018)02-0062-05
New Adaptive Cubature Kalman Filter Algorithm and Its Application in Target Tracking
HUANG Shuo,LI Guannan,JING Tao,CAO Jie
(Department of Information Engineering,Army Armored Military Academy,Beijing 100072,China)
Abstract:In view of the problem of standard volume Calman filter (CKF) in target tracking,an adaptive volume Calman filtering algorithm based on covariance matching principle is proposed in the light of the inaccurate or unknown characteristics of the statistical characteristics of the system noise.The algorithm realizes the real-time tracking of the covariance of the observed noise and the covariance matrix of the process noise by using the new interest sequence and the residual sequence,and then adjusts the statistical characteristics of the noise on line,and can effectively improve the filtering and divergence problem caused by the unknown noise characteristics.The algorithm is applied to the target tracking simulation experiment. The results show that,compared with the standard CKF algorithm,the algorithm has better real-time performance in the case of unknown noise statistical characteristics of the system,which not only inhibits the divergence of the filter, but also improves the tracking precision of the target.
Keywords:cubature Kalman filter;covariance matching;adaptive filter;target tracking
参考文献:
[1] Einicke G A,White L B. Robust extended Kalman filtering [J].Signal Processing IEEE Transactions on,1999,47 (9):2596-2599.
[2] Julier S,Uhlmann J,Durrant-whyte F H. A new method for the nonlinear transformation of means and covariances in filters and estimators [J].IEEE Trans.on Automat.contr,2000,45(3):477-482.
[3] Julier S J,Uhlmann J K. Unscented filtering and nonlinear estimation [J]. Proceedings of the IEEE,2004,92(3):401-422.
[4] Arasaratnam I,Haykin S. Cubature Kalman Filters [J]. IEEE Transactions on Automatic Control,2009,54(6):1254-1269.
[5] Nielsen R O. Accuracy of angle estimation with monopulse processing using two beams [J].Aerospace & Electronic Systems IEEE Transactions on,2001,37(4):1419-1423.
[6] 于浛,魏喜庆,宋申民,等. 基于自适应容积卡尔曼滤波的非合作航天器相对运动估计 [J]. 航空学报,2014,35(8):2251-2260.
[7] 丁家琳,肖建. 基于极大后验估计的自适应容积卡尔曼滤波器 [J]. 控制与决策,2014,29(2):327-334.
[8] Salahshoor K,Mosallaei M,Bayat M. Centralized and decentralized process and sensor fault monitoring using data fusion based on adaptive extended Kalman filter algorithm [J].Measurement,2008,41(10):1059-1076.
[9] 石勇,韩崇昭. 自适应UKF 算法在目标跟踪中的应用 [J].自动化学报,2011,37(6):755-759.
[10] 易令. 高速高机动目标跟踪算法研究 [D]. 成都:电子科技大学,2006.
作者简介:黄硕,男,辽宁辽中人,陆军装甲兵学院,硕士研究生,本科,研究方向:信号与信息处理。