Gaussian Mixture Fitting Filter for Non-Gaussian Measurement Environment

Haoran Cui; Xiaoxu Wang; Yan Liang; Quan Pan

Gaussian Mixture Fitting Filter for Non-Gaussian Measurement Environment

Haoran Cui, Xiaoxu Wang, Yan Liang, Quan Pan

School of Automation

Northwestern Polytechnical University Xian

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, a novel Gaussian mixture fitting filter (GMFF) is proposed to copy with the nonlinear state estimation problem with non-Gaussian measurement environment. The core of GMFF is to use Gaussian mixture regression model to model the unknown measurement likelihood probability, which represents the combination of Gaussian mixture model and linear regression process. In the variational inference framework, through iteratively and alternatively achieving the fitting of the measurement model and the compensation of linear regression error, the estimation accuracy and adaptiveness can be enhanced gradually. The superior performance of GMFF is demonstrated in the simulations.

Original language	English
Title of host publication	FUSION 2019 - 22nd International Conference on Information Fusion
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9780996452786
State	Published - Jul 2019
Event	22nd International Conference on Information Fusion, FUSION 2019 - Ottawa, Canada Duration: 2 Jul 2019 → 5 Jul 2019

Publication series

Name	FUSION 2019 - 22nd International Conference on Information Fusion

Conference

Conference	22nd International Conference on Information Fusion, FUSION 2019
Country/Territory	Canada
City	Ottawa
Period	2/07/19 → 5/07/19

Keywords

Gaussian mixture model
nonlinear estimation
variational infernece

Cite this

@inproceedings{55fdad546f38474baef1489347726fcd,

title = "Gaussian Mixture Fitting Filter for Non-Gaussian Measurement Environment",

abstract = "In this paper, a novel Gaussian mixture fitting filter (GMFF) is proposed to copy with the nonlinear state estimation problem with non-Gaussian measurement environment. The core of GMFF is to use Gaussian mixture regression model to model the unknown measurement likelihood probability, which represents the combination of Gaussian mixture model and linear regression process. In the variational inference framework, through iteratively and alternatively achieving the fitting of the measurement model and the compensation of linear regression error, the estimation accuracy and adaptiveness can be enhanced gradually. The superior performance of GMFF is demonstrated in the simulations.",

keywords = "Gaussian mixture model, nonlinear estimation, variational infernece",

author = "Haoran Cui and Xiaoxu Wang and Yan Liang and Quan Pan",

note = "Publisher Copyright: {\textcopyright} 2019 ISIF-International Society of Information Fusion.; 22nd International Conference on Information Fusion, FUSION 2019 ; Conference date: 02-07-2019 Through 05-07-2019",

year = "2019",

month = jul,

language = "英语",

series = "FUSION 2019 - 22nd International Conference on Information Fusion",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "FUSION 2019 - 22nd International Conference on Information Fusion",

}

Cui, H, Wang, X , Liang, Y & Pan, Q 2019, Gaussian Mixture Fitting Filter for Non-Gaussian Measurement Environment. in FUSION 2019 - 22nd International Conference on Information Fusion., 9011262, FUSION 2019 - 22nd International Conference on Information Fusion, Institute of Electrical and Electronics Engineers Inc., 22nd International Conference on Information Fusion, FUSION 2019, Ottawa, Canada, 2/07/19.

Gaussian Mixture Fitting Filter for Non-Gaussian Measurement Environment. / Cui, Haoran; Wang, Xiaoxu ; Liang, Yan et al.
FUSION 2019 - 22nd International Conference on Information Fusion. Institute of Electrical and Electronics Engineers Inc., 2019. 9011262 (FUSION 2019 - 22nd International Conference on Information Fusion).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Gaussian Mixture Fitting Filter for Non-Gaussian Measurement Environment

AU - Cui, Haoran

AU - Wang, Xiaoxu

AU - Liang, Yan

AU - Pan, Quan

PY - 2019/7

Y1 - 2019/7

N2 - In this paper, a novel Gaussian mixture fitting filter (GMFF) is proposed to copy with the nonlinear state estimation problem with non-Gaussian measurement environment. The core of GMFF is to use Gaussian mixture regression model to model the unknown measurement likelihood probability, which represents the combination of Gaussian mixture model and linear regression process. In the variational inference framework, through iteratively and alternatively achieving the fitting of the measurement model and the compensation of linear regression error, the estimation accuracy and adaptiveness can be enhanced gradually. The superior performance of GMFF is demonstrated in the simulations.

AB - In this paper, a novel Gaussian mixture fitting filter (GMFF) is proposed to copy with the nonlinear state estimation problem with non-Gaussian measurement environment. The core of GMFF is to use Gaussian mixture regression model to model the unknown measurement likelihood probability, which represents the combination of Gaussian mixture model and linear regression process. In the variational inference framework, through iteratively and alternatively achieving the fitting of the measurement model and the compensation of linear regression error, the estimation accuracy and adaptiveness can be enhanced gradually. The superior performance of GMFF is demonstrated in the simulations.

KW - Gaussian mixture model

KW - nonlinear estimation

KW - variational infernece

UR - http://www.scopus.com/inward/record.url?scp=85081790445&partnerID=8YFLogxK

M3 - 会议稿件

AN - SCOPUS:85081790445

T3 - FUSION 2019 - 22nd International Conference on Information Fusion

BT - FUSION 2019 - 22nd International Conference on Information Fusion

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 22nd International Conference on Information Fusion, FUSION 2019

Y2 - 2 July 2019 through 5 July 2019

ER -

Gaussian Mixture Fitting Filter for Non-Gaussian Measurement Environment

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this