scholarly journals Strong Tracking PHD Filter Based on Variational Bayesian with Inaccurate Process and Measurement Noise Covariance

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1126
Author(s):  
Zhentao Hu ◽  
Linlin Yang ◽  
Yong Jin ◽  
Han Wang ◽  
Shibo Yang
Keyword(s):  
Real Time ◽  
Gaussian Mixture ◽  
Measurement Noise ◽  
Tracking Accuracy ◽  
Process Noise ◽  
Probability Hypothesis Density ◽  
Measurement Noise Covariance ◽  
Multi Target Tracking ◽  
Noise Covariance ◽  
Fading Factor

Assuming that the measurement and process noise covariances are known, the probability hypothesis density (PHD) filter is effective in real-time multi-target tracking; however, noise covariance is often unknown and time-varying for an actual scene. To solve this problem, a strong tracking PHD filter based on Variational Bayes (VB) approximation is proposed in this paper. The measurement noise covariance is described in the linear system by the inverse Wishart (IW) distribution. Then, the fading factor in the strong tracking principle uses the optimal measurement noise covariance at the previous moment to control the state prediction covariance in real-time. The Gaussian IW (GIW) joint distribution adopts the VB approximation to jointly return the measurement noise covariance and the target state covariance. The simulation results show that, compared with the traditional Gaussian mixture PHD (GM-PHD) and the VB-adaptive PHD, the proposed algorithm has higher tracking accuracy and stronger robustness in a more reasonable calculation time.

scholarly journals Multi-Fading Factor and Update Monitoring Strategy Adaptive Kalman Filter Based Variational Bayesian with Inaccurate Time-Varying Process and Measure-Ment Noise Covariance Matrices

2020 ◽  
Author(s):  
Chenghao Shan ◽  
Weidong Zhou ◽  
Yefeng Yang ◽  
Zihao Jiang
Keyword(s):  
Kalman Filter ◽  
Covariance Matrix ◽  
Measurement Noise ◽  
Time Varying ◽  
Monitoring Strategy ◽  
Adaptive Kalman Filter ◽  
Variational Bayesian ◽  
Measurement Noise Covariance ◽  
Noise Covariance ◽  
Fading Factor

Aiming at the problem that the performance of Adaptive Kalman filter estimation will be affected when the statistical characteristics of the process and measurement noise matrix are inaccurate and time-varying in the linear Gaussian state-space model, an algorithm of Multi-fading factor and update monitoring strategy adaptive Kalman filter based variational Bayesian is proposed. Inverse Wishart distribution is selected as the measurement noise model, the system state vector and measurement noise covariance matrix are estimated with the variational Bayesian method. The process noise covariance matrix is estimated by the maximum a posteriori principle, and the update monitoring strategy with adjustment factors is used to maintain the positive semi-definite of the updated matrix. The above optimal estimation results are introduced as time-varying parameters into the multiple fading factors to improve the estimation accuracy of the one-step state predicted covariance matrix. The application of the proposed algorithm in target tracking is simulated. The results show that compared with the current filters, the proposed filtering algorithm has better accuracy and convergence performance, and realizes the simultaneous estimation of inaccurate time-varying process and measurement noise covariance matrices.

scholarly journals DTM-Aided Adaptive EPF Navigation Application in Railways

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3860 ◽  
Author(s):  
Chengming Jin ◽  
Baigen Cai ◽  
Jian Wang ◽  
Allison Kealy
Keyword(s):  
Particle Filter ◽  
Real Time ◽  
Sampling Period ◽  
Adaptive Method ◽  
Measurement Noise ◽  
Filter Method ◽  
Operating Environments ◽  
Measurement Noise Covariance ◽  
Noise Covariance ◽  
Point Positioning

The diverse operating environments change GNSS measurement noise covariance in real time, and different GNSS techniques hold different measurement noise covariance as well. Mismodelling the covariance causes undependable filtering results and even degenerates the GNSS/INS Particle Filter (PF) process, due to the fact that INS error-state noise covariance is much smaller than that of GNSS measurement noise. It also makes the majority of existing methods for adaptively adjusting filter parameters incapable of performing well. In this paper, a feasible Digital Track Map-aided (DTM-aided) adaptive extended Kalman particle filter method is introduced in GNSS/INS integration in order to adjust GNSS measurement noise covariance in real time, and the GNSS down-direction offset is also estimated along with every sampling period through making full use of DTM information. The proposed approach is successfully examined in a railway environment, and the on-site experimental results reveal that the adaptive approach holds better positioning performance in comparison to the methods without adaptive adjustment. Improvements of 62.4% and 14.9% in positioning accuracy are obtained in contrast to Standard Point Positioning (SPP) and Precise Point Positioning (PPP), respectively. The proposed adaptive method takes advantage of DTM information and is able to automatically adapt to complex railway environments and different GNSS techniques.

The Selection of Process Noise Covariance Q and Measurement Noise Covariance R on Kalman Filter

2014 ◽  
Vol 513-517 ◽  
pp. 4342-4345 ◽  
Author(s):  
Chao Yi Wei ◽  
Shu Jian Ye ◽  
Xu Guang Li ◽  
Mei Zhi Xie ◽  
Feng Yan Yi
Keyword(s):  
Kalman Filter ◽  
Simulation Model ◽  
Dynamic Model ◽  
Measurement Noise ◽  
State Estimator ◽  
Process Noise ◽  
Measurement Noise Covariance ◽  
High Measurement ◽  
Noise Covariance ◽  
Selection Of

At first, a seven degree of freedom dynamic model of tractor semi-trailer was established, and a simulation model with the Matlab/Simulink software was established too. Based on the model, a state estimator based on Kalman theory was designed, using easily measured parameters to estimate the parameters that are difficultly measured or have high measurement cost, after that, compared estimated values and simulation measurements and analyzed the influence with changes of process noise covariance Q and measurement noise covariance R.

scholarly journals Multi-Fading Factor and Updated Monitoring Strategy Adaptive Kalman Filter-Based Variational Bayesian

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 198
Author(s):  
Chenghao Shan ◽  
Weidong Zhou ◽  
Yefeng Yang ◽  
Zihao Jiang
Keyword(s):  
Kalman Filter ◽  
Covariance Matrix ◽  
Measurement Noise ◽  
Time Varying ◽  
Monitoring Strategy ◽  
Adaptive Kalman Filter ◽  
Variational Bayesian ◽  
Measurement Noise Covariance ◽  
Noise Covariance ◽  
Fading Factor

Aiming at the problem that the performance of adaptive Kalman filter estimation will be affected when the statistical characteristics of the process and measurement of the noise matrices are inaccurate and time-varying in the linear Gaussian state-space model, an algorithm of multi-fading factor and an updated monitoring strategy adaptive Kalman filter-based variational Bayesian is proposed. Inverse Wishart distribution is selected as the measurement noise model and the system state vector and measurement noise covariance matrix are estimated with the variational Bayesian method. The process noise covariance matrix is estimated by the maximum a posteriori principle, and the updated monitoring strategy with adjustment factors is used to maintain the positive semi-definite of the updated matrix. The above optimal estimation results are introduced as time-varying parameters into the multiple fading factors to improve the estimation accuracy of the one-step state predicted covariance matrix. The application of the proposed algorithm in target tracking is simulated. The results show that compared with the current filters, the proposed filtering algorithm has better accuracy and convergence performance, and realizes the simultaneous estimation of inaccurate time-varying process and measurement noise covariance matrices.

scholarly journals Adaptive probability hypothesis density filter for multi-target tracking with unknown measurement noise statistics

2021 ◽  
Vol 54 (3-4) ◽  
pp. 279-291
Author(s):  
Weijun Xu
Keyword(s):  
Target Tracking ◽  
Random Noise ◽  
Measurement Model ◽  
Gaussian Mixture ◽  
Measurement Noise ◽  
Probability Hypothesis Density ◽  
Practical Applications ◽  
Multi Target Tracking ◽  
New Formulation ◽  
Noise Statistics

Under the Gaussian noise assumption, the probability hypothesis density (PHD) filter represents a promising tool for tracking a group of moving targets with a time-varying number. However, inaccurate prior statistics of the random noise will degrade the performance of the PHD filter in many practical applications. This paper presents an adaptive Gaussian mixture PHD (AGM-PHD) filter for the multi-target tracking (MTT) problem in the scenario where both the mean and covariance of measurement noise sequences are unknown. The conventional PHD filters are extended to jointly estimate both the multi-target state and the aforementioned measurement noise statistics. In particular, the Normal-inverse-Wishart and Gaussian distributions are first integrated to represent the joint posterior intensity by transforming the measurement model into a new formulation. Then, the updating rule for the hyperparameters of the model is derived in closed form based on variational Bayesian (VB) approximation and Bayesian conjugate prior heuristics. Finally, the dynamic system state and the noise statistics are updated sequentially in an iterative manner. Simulations results with both constant velocity and constant turn model demonstrate that the AGM-PHD filter achieves comparable performance as the ideal PHD filter with true measurement noise statistics.

Robust UKF-based filtering for tracking a maneuvering hypersonic glide vehicle

2021 ◽  
pp. 095441002110511
Author(s):  
Jingshuai Huang ◽  
Hongbo Zhang ◽  
Guojian Tang ◽  
Weimin Bao
Keyword(s):  
Measurement Model ◽  
Model Error ◽  
Model Errors ◽  
Tracking Accuracy ◽  
Measurement Noise Covariance ◽  
Noise Covariance ◽  
Practical Guidance ◽  
Simulation Results ◽  
Fading Factor ◽  
The One

To track a non-cooperative hypersonic glide vehicle (HGV) without any precise information, an approach to the state estimation is presented based on a robust UKF-based filter (RUKFBF) in this paper. The HGV has an uncertain reentry motion because of unknown maneuvers which is a primary factor leading to degradation of tracking accuracy. Aiming at enhancing accuracy, the strong tracking algorithm (STA) is introduced to addressing the model error caused by a bank-reversal maneuver of HGV. Furthermore, the Huber technique is employed to deal with possible measurement model errors. In the RUKFBF, mutual interferences are suppressed between the STA and the Huber technique via two strategies. The one is that the calculation of the fading factor in the STA adopts an unmodified measurement noise covariance, and the other one is that two judgment criteria are proposed to limit large fading factors in the presence of measurement model errors. To simulate real tracking scenarios, the RUKFBF is tested through tracking a HGV trajectory considering a practical guidance strategy. Simulation results demonstrate the effectiveness of the RUKFBF in the presence of model errors and the observability of the estimated state.

Sign in / Sign up

Export Citation Format

Share Document