Enhancing Particle Swarm Optimization Based Particle Filter Tracker

Wang, Qicong; Xie, Li; Liu, Jilin; Xiang, Zhiyu

doi:10.1007/978-3-540-37275-2_151

Cited by 22 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…54 Zheng and Meng 54 imbue the generic PF with PSO-with-mutation with the aim of providing a robust,°exible solution to the sample impoverishment problem. The PSO with mutation operator, proposed by Wang et al, 55 addresses the impoverishment problem by applying mutation to keep multiple modes of particle sets. The PSO algorithm is applied to the PF as a dynamic sampling and evolving algorithm, where instead of drawing samples by the importance functions, particles keep in motion after initialization and adjust their location according to PSO rules.…”

Section: Particle Swarm Optimization Particle¯ltersmentioning

confidence: 99%

State Space Modeling & Bayesian Inference with Computational Intelligence

Hanif

Smith

2015

New Math. and Nat. Computation

View full text Add to dashboard Cite

Recursive Bayesian estimation using sequential Monte Carlos methods is a powerful numerical technique to understand latent dynamics of nonlinear non-Gaussian dynamical systems. It enables us to reason under uncertainty and addresses shortcomings underlying deterministic systems and control theories which do not provide su±cient means of performing analysis and design. In addition, parametric techniques such as the Kalman¯lter and its extensions, though they are computationally e±cient, do not reliably compute states and cannot be used to learn stochastic problems. We review recursive Bayesian estimation using sequential Monte Carlo methods highlighting open problems. Primary of these is the weight degeneracy and sample impoverishment problem. We proceed to detail synergistic computational intelligence sequential Monte Carlo methods which address this. We¯nd that imbuing sequential Monte Carlos with computational intelligence has many advantages when applied to many application and problem domains.

show abstract

Section: Particle Swarm Optimization Particle¯ltersmentioning

confidence: 99%

State Space Modeling & Bayesian Inference with Computational Intelligence

Hanif

Smith

2015

New Math. and Nat. Computation

View full text Add to dashboard Cite

show abstract

“…Different from other PSO schemes applied in particle filtering , our PSO‐based suboptimal particle filter has the following features: To choose the personal best particles

{bold-italicp b}_{t}^{j}

as a set of predicted particles. The reason is that

{bold-italicp b}_{t}^{j}

has more dense distribution than particles

θ_{t}^{j}

, thus producing smaller importance weight variance. To select the stopping criterion as the number of propagation steps.…”

Section: Suboptimal Particle Filtersmentioning

confidence: 99%

Suboptimal particle filtering for MIMO flat fading channel estimation

Hoang

Kwan

2011

Int J Communication

View full text Add to dashboard Cite

SUMMARY Particle filters have been successfully employed to track MIMO flat fading channels for wireless communications. However, an optimal importance density cannot be always found to optimize the performance of a particle filter. A suboptimal importance density such as the prior distribution can be used to reduce the complexity of the particle filtering; however, it has a problem of ignoring the current observations. A class of suboptimal particle filters uses the prior distribution as the important density and moves the predicted particles to the low‐error region. In addition, particle filters require knowledge of noise processes to estimate the posterior distribution. This paper presents a suboptimal particle filter that overcomes the drawbacks of the prior importance density and the noise uncertainty by utilizing the swarm behavior in the particle propagation. The presented method will be applied to estimate the channel state information and detect the transmitted symbols of a MIMO wireless communication system under Rayleigh flat fading channel. Computer simulation of a 2 ×2 MIMO system is presented to illustrate the performance of the proposed suboptimal particle filter technique. Copyright © 2011 John Wiley & Sons, Ltd.

show abstract

“…[5] and Wang et allet@tokeneonedot. [6] combined PSO and the particle filter to improve the efficiency of generic particle filters. Similar to the observation combined proposal methods such as Extended particle filter [7] or Unscented particle filter [8], the goal of the PSO combined particle filter is to draw particles by utilizing recent observations.…”

Section: Related Workmentioning

confidence: 99%

Mutiswarm particle filter for robust tracking under observation ambiguity

Lee

2011

2011 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV)

View full text Add to dashboard Cite

Abstract-Particle Filters are a traditional optimization tool for nonlinear, non-Gaussian dynamic-state estimation such as visual tracking. The particle filters, however, suffer from particle degeneracy problem which is caused by the mismatch between the proposal distribution and the target distribution. In this paper, we propose a method for improving the performance of the particle filter via multiswarm-based Particle Swarm Optimization (PSO).We utilize PSO to obtain samples that are well matched with the likelihood distribution , and its converging property is handled with the exclusion between particles. Additionally, we incorporate multiswarm algorithm in the PSO combined particle filter to deal with ambiguities in estimation task. The resulting filter is applied to the object tracking problem with ambiguous observations , and its performance is tested. We present the experimental results that demonstrate improved accuracy with the same or less computational cost.

show abstract

Enhancing Particle Swarm Optimization Based Particle Filter Tracker

Cited by 22 publications

References 12 publications

State Space Modeling & Bayesian Inference with Computational Intelligence

State Space Modeling & Bayesian Inference with Computational Intelligence

Suboptimal particle filtering for MIMO flat fading channel estimation

Mutiswarm particle filter for robust tracking under observation ambiguity

Contact Info

Product

Resources

About