TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Target tracking via combination of particle filter and optimisation techniques

Tutkimustuotosvertaisarvioitu

Standard

Target tracking via combination of particle filter and optimisation techniques. / Hosseini, Seyyed Soheil Sadat; Jamali, Mohsin M.; Astola, Jaakko; Gorsevski, Peter V.

julkaisussa: International Journal of Mathematical Modelling and Numerical Optimization, Vuosikerta 7, Nro 2, 2016, s. 212-229.

Tutkimustuotosvertaisarvioitu

Harvard

Hosseini, SSS, Jamali, MM, Astola, J & Gorsevski, PV 2016, 'Target tracking via combination of particle filter and optimisation techniques', International Journal of Mathematical Modelling and Numerical Optimization, Vuosikerta. 7, Nro 2, Sivut 212-229. https://doi.org/10.1504/IJMMNO.2016.077068

APA

Hosseini, S. S. S., Jamali, M. M., Astola, J., & Gorsevski, P. V. (2016). Target tracking via combination of particle filter and optimisation techniques. International Journal of Mathematical Modelling and Numerical Optimization, 7(2), 212-229. https://doi.org/10.1504/IJMMNO.2016.077068

Vancouver

Hosseini SSS, Jamali MM, Astola J, Gorsevski PV. Target tracking via combination of particle filter and optimisation techniques. International Journal of Mathematical Modelling and Numerical Optimization. 2016;7(2):212-229. https://doi.org/10.1504/IJMMNO.2016.077068

Author

Hosseini, Seyyed Soheil Sadat ; Jamali, Mohsin M. ; Astola, Jaakko ; Gorsevski, Peter V. / Target tracking via combination of particle filter and optimisation techniques. Julkaisussa: International Journal of Mathematical Modelling and Numerical Optimization. 2016 ; Vuosikerta 7, Nro 2. Sivut 212-229.

Bibtex - Lataa

@article{40de14525aa44faf87343178153d89ea,
title = "Target tracking via combination of particle filter and optimisation techniques",
abstract = "Particle filters (PFs) have been used for the nonlinear estimation for a number of years. However, they suffer from the impoverishment phenomenon. It is brought by resampling which intends to prevent particle degradation, and therefore becomes the inherent weakness of this technique. To solve the problem of sample impoverishment and to improve the performance of the standard particle filter we propose a modification to this method by adding a sampling mechanism inspired by optimisation techniques, namely, the pattern search, particle swarm optimisation, differential evolution and Nelder-Mead algorithms. In the proposed methods, the true state of the target can be better expressed by the optimised particle set and the number of meaningful particles can be grown significantly. The efficiency of the proposed particle filters is supported by a truck-trailer problem. Simulations show that the hybridised particle filter with Nelder-Mead search is better than other optimisation approaches in terms of particle diversity.",
keywords = "Differential evolution, Nelder-Mead, Particle filter, Particle swarm optimisation, Pattern search, PSO, Target tracking",
author = "Hosseini, {Seyyed Soheil Sadat} and Jamali, {Mohsin M.} and Jaakko Astola and Gorsevski, {Peter V.}",
year = "2016",
doi = "10.1504/IJMMNO.2016.077068",
language = "English",
volume = "7",
pages = "212--229",
journal = "International Journal of Mathematical Modelling and Numerical Optimization",
issn = "2040-3607",
publisher = "Inderscience",
number = "2",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Target tracking via combination of particle filter and optimisation techniques

AU - Hosseini, Seyyed Soheil Sadat

AU - Jamali, Mohsin M.

AU - Astola, Jaakko

AU - Gorsevski, Peter V.

PY - 2016

Y1 - 2016

N2 - Particle filters (PFs) have been used for the nonlinear estimation for a number of years. However, they suffer from the impoverishment phenomenon. It is brought by resampling which intends to prevent particle degradation, and therefore becomes the inherent weakness of this technique. To solve the problem of sample impoverishment and to improve the performance of the standard particle filter we propose a modification to this method by adding a sampling mechanism inspired by optimisation techniques, namely, the pattern search, particle swarm optimisation, differential evolution and Nelder-Mead algorithms. In the proposed methods, the true state of the target can be better expressed by the optimised particle set and the number of meaningful particles can be grown significantly. The efficiency of the proposed particle filters is supported by a truck-trailer problem. Simulations show that the hybridised particle filter with Nelder-Mead search is better than other optimisation approaches in terms of particle diversity.

AB - Particle filters (PFs) have been used for the nonlinear estimation for a number of years. However, they suffer from the impoverishment phenomenon. It is brought by resampling which intends to prevent particle degradation, and therefore becomes the inherent weakness of this technique. To solve the problem of sample impoverishment and to improve the performance of the standard particle filter we propose a modification to this method by adding a sampling mechanism inspired by optimisation techniques, namely, the pattern search, particle swarm optimisation, differential evolution and Nelder-Mead algorithms. In the proposed methods, the true state of the target can be better expressed by the optimised particle set and the number of meaningful particles can be grown significantly. The efficiency of the proposed particle filters is supported by a truck-trailer problem. Simulations show that the hybridised particle filter with Nelder-Mead search is better than other optimisation approaches in terms of particle diversity.

KW - Differential evolution

KW - Nelder-Mead

KW - Particle filter

KW - Particle swarm optimisation

KW - Pattern search

KW - PSO

KW - Target tracking

U2 - 10.1504/IJMMNO.2016.077068

DO - 10.1504/IJMMNO.2016.077068

M3 - Article

VL - 7

SP - 212

EP - 229

JO - International Journal of Mathematical Modelling and Numerical Optimization

JF - International Journal of Mathematical Modelling and Numerical Optimization

SN - 2040-3607

IS - 2

ER -