Implementation of the Daum-Huang exact-flow particle filter

Ding, Tao; Coates, Mark

doi:10.1109/ssp.2012.6319675

Cited by 46 publications

(32 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such mathematical flourishes and the confident tone of the prose in [1] might easily lead some casual readers to think that Mallick & Sindhu have actually discovered real "problems" with the particle flow theory. If so, there must also be such problems with transport theory [6]- [7] and homotopy continuation methods [35]- [39] and many other papers by competent researchers in Bayesian filtering, including [9], [10], [11], [12], [13], [30], [31], [40], [41], [42] and [43]. For example, the Gibbs flow developed by researchers at Oxford University in [31] uses the idea for Gibbs flow given in [32] and [17], and it uses the log-homotopy defined in all of our papers.…”

Section: Discussionmentioning

confidence: 99%

A friendly rebuttal to Mallick and Sindhu on particle flow for Bayes' rule

Daum

Huang

Noushin

2016

Signal Processing, Sensor/Information Fusion, and Target Recognition XXV

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

A friendly rebuttal to Mallick and Sindhu on particle flow for Bayes' rule

Daum

Huang

Noushin

2016

Signal Processing, Sensor/Information Fusion, and Target Recognition XXV

View full text Add to dashboard Cite

show abstract

“…We refer to this method as the exact Daum-Huang (EDH) filter, and a detailed description of its implementation is provided in [37]. For nonlinear models, a computationally intensive variation of EDH, that computes a separate flow for each particle by performing linearization at the particle location η i λ , was proposed in [16] and is referred to as the localized exact Daum-Huang (LEDH) filter.…”

Section: Background Materials a Sequential Markov Chain Monte Camentioning

confidence: 99%

Invertible Particle-Flow-Based Sequential MCMC With Extension to Gaussian Mixture Noise Models

Pal

Coates

2019

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

Sequential state estimation in non-linear and non-Gaussian state spaces has a wide range of applications in statistics and signal processing. One of the most effective non-linear filtering approaches, particle filtering, suffers from weight degeneracy in high-dimensional filtering scenarios. Several avenues have been pursued to address high-dimensionality. Among these, particle flow particle filters construct effective proposal distributions by using invertible flow to migrate particles continuously from the prior distribution to the posterior, and sequential Markov chain Monte Carlo (SMCMC) methods use a Metropolis-Hastings (MH) accept-reject approach to improve filtering performance. In this paper, we propose to combine the strengths of invertible particle flow and SMCMC by constructing a composite Metropolis-Hastings (MH) kernel within the SMCMC framework using invertible particle flow. In addition, we propose a Gaussian mixture model (GMM)-based particle flow algorithm to construct effective MH kernels for multi-modal distributions. Simulation results show that for high-dimensional state estimation example problems the proposed kernels significantly increase the acceptance rate with minimal additional computational overhead and improve estimation accuracy compared with state-of-the-art filtering algorithms.Y. Li is with the

show abstract

“…The Kalman filter is not applicable to these problems and, in general, closed-form solutions are not possible. A number of approximate filtering algorithms such as the extended Kalman filter (EKF) (12)(13)(14)22,26), unscented Kalman filter (UKF) (27,28), Gaussian sum filter (29), particle filter (18,22,(30)(31)(32)(33)(34), quadrature filter, quasi-Monte Carlo, grid-based filter, cubature Kalman filter (35,36), and particle flow filter (PFF) (37,38) have been proposed.…”

Section: The Kalman Filtermentioning

confidence: 99%

Multitarget Tracking

Mallick²,

Bar‐Shalom

et al. 2015

Wiley Encyclopedia of Electrical and Electronics Engineering

194

150

View full text Add to dashboard Cite

Multitarget tracking (MTT) refers to the problem of jointly estimating the number of targets and their states or trajectories from noisy sensor measurements. MTT has a long history spanning over 50 years, with a plethora of applications in many fields of study. While numerous techniques have been developed, the three most widely used approaches to MTT are the joint probabilistic data association filter (JPDAF), multiple hypothesis tracking (MHT), and random finite set (RFS). The JPDAF and MHT have been widely used for more than two decades, while the RFS‐based MTT algorithms have received a great deal of attention during the last decade. In this article, we provide an overview of MTT and succinct summaries of popular state‐of‐the‐art MTT algorithms.

show abstract

Implementation of the Daum-Huang exact-flow particle filter

Cited by 46 publications

References 5 publications

A friendly rebuttal to Mallick and Sindhu on particle flow for Bayes' rule

A friendly rebuttal to Mallick and Sindhu on particle flow for Bayes' rule

Invertible Particle-Flow-Based Sequential MCMC With Extension to Gaussian Mixture Noise Models

Multitarget Tracking

Contact Info

Product

Resources

About