Nonlinear filtering in unknown measurement noise and target tracking system by variational Bayesian inference

Abstract This paper considers a class of nonlinear filtering algorithms based on variational Bayesian (VB) theory to settle the unknown measurement noise problem in target tracking system. When the unknown measurement noise is conditionally independent of states, based on the variational idea, estimate of probability density function of state is converted into approximation two probability density functions for both unknown noise and nonlinear states. Then, an iterative algorithm is established to jointly estimate the state and the unknown measurement noise using variational Bayesian inference. Thus, the unknown measurement noise could be estimated as hidden state. The convergence result of the proposed nonlinear probability density function approximation algorithm is also given. The simulation results of typical examples show that the proposed VB based methods have superior performance to these classic algorithms in target tracking problems.

[1]  Jian Xu,et al.  Robust adaptive algorithm for nonlinear systems with unknown measurement noise and uncertain parameters by variational Bayesian inference , 2018 .

[2]  Ibrahim Hoteit,et al.  A Variational Bayesian Multiple Particle Filtering Scheme for Large-Dimensional Systems , 2016, IEEE Transactions on Signal Processing.

[3]  Branko Ristic,et al.  Target motion analysis with unknown measurement noise variance , 2017, 2017 20th International Conference on Information Fusion (Fusion).

[4]  Simo Särkkä,et al.  On the L4 convergence of particle filters with general importance distributions , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Zhong Liu,et al.  Bayesian unscented Kalman filter for state estimation of nonlinear and non-Gaussian systems , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

[6]  Aritro Dey,et al.  Adaptive Gauss–Hermite filter for non-linear systems with unknown measurement noise covariance , 2015 .

[7]  Jouko Lampinen,et al.  Rao-Blackwellized particle filter for multiple target tracking , 2007, Inf. Fusion.

[8]  P. Moral,et al.  On the stability of interacting processes with applications to filtering and genetic algorithms , 2001 .

[9]  Václav Smídl,et al.  Variational Bayesian Filtering , 2008, IEEE Transactions on Signal Processing.

[10]  Henry Leung,et al.  State Estimation in Unknown Non-Gaussian Measurement Noise using Variational Bayesian Technique , 2013, IEEE Transactions on Aerospace and Electronic Systems.

[11]  Vaclav Smidl,et al.  The Restricted Variational Bayes Approximation in Bayesian Filtering , 2006, 2006 IEEE Nonlinear Statistical Signal Processing Workshop.

[12]  Henry Leung,et al.  Variational Bayesian Adaptive Cubature Information Filter Based on Wishart Distribution , 2017, IEEE Transactions on Automatic Control.

[13]  Bo Wang,et al.  Lack of Consistency of Mean Field and Variational Bayes Approximations for State Space Models , 2004, Neural Processing Letters.

[14]  Michail D. Vrettas,et al.  Estimating parameters in stochastic systems: A variational Bayesian approach , 2011 .

[15]  Lamine Mili,et al.  A Framework for Robust Hybrid State Estimation With Unknown Measurement Noise Statistics , 2018, IEEE Transactions on Industrial Informatics.

[16]  Zoubin Ghahramani,et al.  Propagation Algorithms for Variational Bayesian Learning , 2000, NIPS.

[17]  Jeffrey K. Uhlmann,et al.  Unscented filtering and nonlinear estimation , 2004, Proceedings of the IEEE.

[18]  Xing Liu,et al.  Kolmogorov superposition theorem and its applications , 2015 .

[19]  Masa-aki Sato,et al.  Online Model Selection Based on the Variational Bayes , 2001, Neural Computation.

[20]  Chen Shen,et al.  A Robust Particle Filtering Algorithm With Non-Gaussian Measurement Noise Using Student-t Distribution , 2014, IEEE Signal Processing Letters.

[21]  Thomas B. Schön,et al.  Marginalized Particle Filters for Nonlinear State-space Models , 2003 .

[22]  Henry Leung,et al.  A variational Bayesian approach to robust sensor fusion based on Student-t distribution , 2013, Inf. Sci..

[23]  Simo Särkkä,et al.  On Gaussian Optimal Smoothing of Non-Linear State Space Models , 2010, IEEE Transactions on Automatic Control.

[24]  V. Šmídl,et al.  The Variational Bayes Method in Signal Processing , 2005 .

[25]  Umut Orguner,et al.  Approximate Bayesian Smoothing with Unknown Process and Measurement Noise Covariances , 2014, IEEE Signal Processing Letters.

[26]  Lawrence Carin,et al.  Variational Bayes for continuous hidden Markov models and its application to active learning , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Pierre Del Moral,et al.  Mean Field Simulation for Monte Carlo Integration , 2013 .

[28]  S. Haykin,et al.  Cubature Kalman Filters , 2009, IEEE Transactions on Automatic Control.

[29]  Zhenyu Huang,et al.  Assessing Gaussian Assumption of PMU Measurement Error Using Field Data , 2018, IEEE Transactions on Power Delivery.

[30]  Yuanxin Wu,et al.  Unscented Kalman filtering for additive noise case: augmented versus nonaugmented , 2005, IEEE Signal Processing Letters.

[31]  Jeffrey K. Uhlmann,et al.  Corrections to "Unscented Filtering and Nonlinear Estimation" , 2004, Proc. IEEE.

[32]  Jun S. Liu,et al.  Sequential Monte Carlo methods for dynamic systems , 1997 .

[33]  Simo Särkkä,et al.  Recursive Noise Adaptive Kalman Filtering by Variational Bayesian Approximations , 2009, IEEE Transactions on Automatic Control.

[34]  Patrick Pérez,et al.  Variational inference for visual tracking , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[35]  R. Douc,et al.  Limit theorems for weighted samples with applications to sequential Monte Carlo methods , 2005, math/0507042.

[36]  Thomas B. Schön,et al.  Marginalized particle filters for mixed linear/nonlinear state-space models , 2005, IEEE Transactions on Signal Processing.

[37]  Thiagalingam Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation , 2001 .

[38]  Dariusz Horla,et al.  Robust particle filter—anti‐zero bias modification , 2016 .

[39]  Jian Xu,et al.  Optimal state estimation for equality‐constrained systems with complex noise , 2018 .

[40]  Simo Särkkä,et al.  Adaptive Metropolis algorithm using variational Bayesian adaptive Kalman filter , 2013, Comput. Stat. Data Anal..

[41]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[42]  Juha Karhunen,et al.  An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models , 2002, Neural Computation.