Interacting multiple model particle filter
Authors:
- 2 October 2003
- journal article
- Published by Institution of Engineering and Technology (IET) in IEE Proceedings - Radar, Sonar and Navigation
- Vol. 150 (5) , 344-349
Abstract
A new method for multiple model particle filtering for Markovian switching systems is presented. This new method is a combination of the interacting multiple model (IMM) filter and a (regularised) particle filter. The mixing and interaction is similar to that in a conventional IMM filter. However, in every mode a regularised particle filter is running. The regularised particle filter probability density is a mixture of Gaussian probability densities. The proposed method is able to deal with nonlinearities and non-Gaussian noise. Furthermore, the new method keeps a fixed number of particles in each mode, and therefore it does not suffer from the potential drawbacks of existing multiple model particle filters for Markovian switching systems.Keywords
This publication has 11 references indexed in Scilit:
- Hybrid state estimation: a target tracking applicationAutomatica, 2002
- Sequential Monte Carlo Methods in Practice2001
- Manoeuvring Target Tracking Using a Multiple-Model Bootstrap Filter2001
- Improving Regularised Particle Filters2001
- Multiple model bootstrap filter for maneuvering target trackingIEEE Transactions on Aerospace and Electronic Systems, 2000
- Expectation maximization algorithms for MAP estimation of jump Markov linear systemsIEEE Transactions on Signal Processing, 1999
- Interacting multiple model methods in target tracking: a surveyIEEE Transactions on Aerospace and Electronic Systems, 1998
- A hybrid bootstrap filter for target tracking in clutterIEEE Transactions on Aerospace and Electronic Systems, 1997
- Novel approach to nonlinear/non-Gaussian Bayesian state estimationIEE Proceedings F Radar and Signal Processing, 1993
- The interacting multiple model algorithm for systems with Markovian switching coefficientsIEEE Transactions on Automatic Control, 1988