Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems

Ruixin Niu; Pramod K. Varshney; Mark Alford; Adnan Bubalo; Eric Jones; Maria Scalzo

doi:10.1109/ICIF.2008.4632389

Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems

Ruixin Niu, Pramod K. Varshney, Mark Alford, Adnan Bubalo, Eric Jones, Maria Scalzo

Department of Electrical Engineering & Computer Science

Research output: Chapter in Book/Entry/Poem › Conference contribution

26 Scopus citations

Abstract

Several nonlinear filtering techniques are investigated for nonlinear tracking problems. Experimental results show that for a weakly nonlinear tracking problem, the extended Kalman filter and the unscented Kalman filter are good choices, while a particle filter should be used for problems with strong nonlinearity. To quantitatively determine the nonlinearity of a nonlinear tracking problem, we propose two types of measures: one is the differential geometry curvature measure and the other is based on the normalized innovation squared (NIS) of the Kalman filter. Simulation results show that both measures can effectively quantify the nonlinearity of the problem. The NIS is capable of detecting the filter divergence online. The curvature measure is more suitable for quantifying the nonlinearity of a tracking problem as determined via simulations.

Original language	English (US)
Title of host publication	Proceedings of the 11th International Conference on Information Fusion, FUSION 2008
DOIs	https://doi.org/10.1109/ICIF.2008.4632389
State	Published - 2008
Event	11th International Conference on Information Fusion, FUSION 2008 - Cologne, Germany Duration: Jun 30 2008 → Jul 3 2008

Publication series

Name	Proceedings of the 11th International Conference on Information Fusion, FUSION 2008

Other

Other	11th International Conference on Information Fusion, FUSION 2008
Country/Territory	Germany
City	Cologne
Period	6/30/08 → 7/3/08

Keywords

Extended Kalman filter
Nonlinearity measures
Particle filter
Tracking
Unscented Kalman filter

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Access to Document

10.1109/ICIF.2008.4632389

Cite this

Niu, R., Varshney, P. K., Alford, M., Bubalo, A., Jones, E., & Scalzo, M. (2008). Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems. In Proceedings of the 11th International Conference on Information Fusion, FUSION 2008 Article 4632389 (Proceedings of the 11th International Conference on Information Fusion, FUSION 2008). https://doi.org/10.1109/ICIF.2008.4632389

Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems. / Niu, Ruixin; Varshney, Pramod K.; Alford, Mark et al.
Proceedings of the 11th International Conference on Information Fusion, FUSION 2008. 2008. 4632389 (Proceedings of the 11th International Conference on Information Fusion, FUSION 2008).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Niu, R, Varshney, PK, Alford, M, Bubalo, A, Jones, E & Scalzo, M 2008, Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems. in Proceedings of the 11th International Conference on Information Fusion, FUSION 2008., 4632389, Proceedings of the 11th International Conference on Information Fusion, FUSION 2008, 11th International Conference on Information Fusion, FUSION 2008, Cologne, Germany, 6/30/08. https://doi.org/10.1109/ICIF.2008.4632389

Niu R, Varshney PK, Alford M, Bubalo A, Jones E, Scalzo M. Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems. In Proceedings of the 11th International Conference on Information Fusion, FUSION 2008. 2008. 4632389. (Proceedings of the 11th International Conference on Information Fusion, FUSION 2008). doi: 10.1109/ICIF.2008.4632389

@inproceedings{0d9c9372d48547e49b07f1e724d4b25d,

title = "Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems",

abstract = "Several nonlinear filtering techniques are investigated for nonlinear tracking problems. Experimental results show that for a weakly nonlinear tracking problem, the extended Kalman filter and the unscented Kalman filter are good choices, while a particle filter should be used for problems with strong nonlinearity. To quantitatively determine the nonlinearity of a nonlinear tracking problem, we propose two types of measures: one is the differential geometry curvature measure and the other is based on the normalized innovation squared (NIS) of the Kalman filter. Simulation results show that both measures can effectively quantify the nonlinearity of the problem. The NIS is capable of detecting the filter divergence online. The curvature measure is more suitable for quantifying the nonlinearity of a tracking problem as determined via simulations.",

keywords = "Extended Kalman filter, Nonlinearity measures, Particle filter, Tracking, Unscented Kalman filter",

author = "Ruixin Niu and Varshney, {Pramod K.} and Mark Alford and Adnan Bubalo and Eric Jones and Maria Scalzo",

year = "2008",

doi = "10.1109/ICIF.2008.4632389",

language = "English (US)",

isbn = "9783000248832",

series = "Proceedings of the 11th International Conference on Information Fusion, FUSION 2008",

booktitle = "Proceedings of the 11th International Conference on Information Fusion, FUSION 2008",

note = "11th International Conference on Information Fusion, FUSION 2008 ; Conference date: 30-06-2008 Through 03-07-2008",

}

TY - GEN

T1 - Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems

AU - Niu, Ruixin

AU - Varshney, Pramod K.

AU - Alford, Mark

AU - Bubalo, Adnan

AU - Jones, Eric

AU - Scalzo, Maria

PY - 2008

Y1 - 2008

N2 - Several nonlinear filtering techniques are investigated for nonlinear tracking problems. Experimental results show that for a weakly nonlinear tracking problem, the extended Kalman filter and the unscented Kalman filter are good choices, while a particle filter should be used for problems with strong nonlinearity. To quantitatively determine the nonlinearity of a nonlinear tracking problem, we propose two types of measures: one is the differential geometry curvature measure and the other is based on the normalized innovation squared (NIS) of the Kalman filter. Simulation results show that both measures can effectively quantify the nonlinearity of the problem. The NIS is capable of detecting the filter divergence online. The curvature measure is more suitable for quantifying the nonlinearity of a tracking problem as determined via simulations.

AB - Several nonlinear filtering techniques are investigated for nonlinear tracking problems. Experimental results show that for a weakly nonlinear tracking problem, the extended Kalman filter and the unscented Kalman filter are good choices, while a particle filter should be used for problems with strong nonlinearity. To quantitatively determine the nonlinearity of a nonlinear tracking problem, we propose two types of measures: one is the differential geometry curvature measure and the other is based on the normalized innovation squared (NIS) of the Kalman filter. Simulation results show that both measures can effectively quantify the nonlinearity of the problem. The NIS is capable of detecting the filter divergence online. The curvature measure is more suitable for quantifying the nonlinearity of a tracking problem as determined via simulations.

KW - Extended Kalman filter

KW - Nonlinearity measures

KW - Particle filter

KW - Tracking

KW - Unscented Kalman filter

UR - http://www.scopus.com/inward/record.url?scp=56749143853&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56749143853&partnerID=8YFLogxK

U2 - 10.1109/ICIF.2008.4632389

DO - 10.1109/ICIF.2008.4632389

M3 - Conference contribution

AN - SCOPUS:56749143853

SN - 9783000248832

T3 - Proceedings of the 11th International Conference on Information Fusion, FUSION 2008

BT - Proceedings of the 11th International Conference on Information Fusion, FUSION 2008

T2 - 11th International Conference on Information Fusion, FUSION 2008

Y2 - 30 June 2008 through 3 July 2008

ER -

Curvature nonlinearity measure and filter divergence detector for nonlinear tracking problems

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this