CPHD Filtering With Unknown Clutter Rate and Detection Profile

In Bayesian multi-target filtering, we have to contend with two notable sources of uncertainty, clutter and detection. Knowledge of parameters such as clutter rate and detection profile are of critical importance in multi-target filters such as the probability hypothesis density (PHD) and cardinaliz...

Full description

Bibliographic Details
Main Authors: Mahler, R., Vo, Ba Tuong, Vo, Ba-Ngu
Format: Journal Article
Published: Institute of Electrical and Electronics Engineers 2011
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/6872
_version_ 1848745202350555136
author Mahler, R.
Vo, Ba Tuong
Vo, Ba-Ngu
author_facet Mahler, R.
Vo, Ba Tuong
Vo, Ba-Ngu
author_sort Mahler, R.
building Curtin Institutional Repository
collection Online Access
description In Bayesian multi-target filtering, we have to contend with two notable sources of uncertainty, clutter and detection. Knowledge of parameters such as clutter rate and detection profile are of critical importance in multi-target filters such as the probability hypothesis density (PHD) and cardinalized PHD (CPHD) filters. Significant mismatches in clutter and detection model parameters result in biased estimates. In practice, these model parameters are often manually tuned or estimated offline from training data. In this paper we propose PHD/CPHD filters that can accommodate model mismatch in clutter rate and detection profile. In particular we devise versions of the PHD/CPHD filters that can adaptively learn the clutter rate and detection profile while filtering. Moreover, closed-form solutions to these filtering recursions are derived using Beta and Gaussian mixtures. Simulations are presented to verify the proposed solutions.
first_indexed 2025-11-14T06:13:36Z
format Journal Article
id curtin-20.500.11937-6872
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:13:36Z
publishDate 2011
publisher Institute of Electrical and Electronics Engineers
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-68722017-09-13T14:35:42Z CPHD Filtering With Unknown Clutter Rate and Detection Profile Mahler, R. Vo, Ba Tuong Vo, Ba-Ngu PHD Finite set statistics parameter estimation robust filtering CPHD multi-target tracking In Bayesian multi-target filtering, we have to contend with two notable sources of uncertainty, clutter and detection. Knowledge of parameters such as clutter rate and detection profile are of critical importance in multi-target filters such as the probability hypothesis density (PHD) and cardinalized PHD (CPHD) filters. Significant mismatches in clutter and detection model parameters result in biased estimates. In practice, these model parameters are often manually tuned or estimated offline from training data. In this paper we propose PHD/CPHD filters that can accommodate model mismatch in clutter rate and detection profile. In particular we devise versions of the PHD/CPHD filters that can adaptively learn the clutter rate and detection profile while filtering. Moreover, closed-form solutions to these filtering recursions are derived using Beta and Gaussian mixtures. Simulations are presented to verify the proposed solutions. 2011 Journal Article http://hdl.handle.net/20.500.11937/6872 10.1109/TSP.2011.2128316 Institute of Electrical and Electronics Engineers restricted
spellingShingle PHD
Finite set statistics
parameter estimation
robust filtering
CPHD
multi-target tracking
Mahler, R.
Vo, Ba Tuong
Vo, Ba-Ngu
CPHD Filtering With Unknown Clutter Rate and Detection Profile
title CPHD Filtering With Unknown Clutter Rate and Detection Profile
title_full CPHD Filtering With Unknown Clutter Rate and Detection Profile
title_fullStr CPHD Filtering With Unknown Clutter Rate and Detection Profile
title_full_unstemmed CPHD Filtering With Unknown Clutter Rate and Detection Profile
title_short CPHD Filtering With Unknown Clutter Rate and Detection Profile
title_sort cphd filtering with unknown clutter rate and detection profile
topic PHD
Finite set statistics
parameter estimation
robust filtering
CPHD
multi-target tracking
url http://hdl.handle.net/20.500.11937/6872