The Smooth Trajectory Estimator for LMB Filters

This paper proposes a smooth-trajectory estimator for the labelled multi-Bernoulli (LMB) filter by exploiting the special structure of the generalised labelled multi-Bernoulli (GLMB) filter. We devise a simple and intuitive approach to store the best association map when approximating the GLMB rando...

Full description

Bibliographic Details
Main Authors: Nguyen, Hoa Van, Nguyen, Tran Thien Dat, Shim, Changbeom, Anuar, M.
Format: Conference Paper
Published: 2023
Online Access:http://purl.org/au-research/grants/arc/LP200301507
http://hdl.handle.net/20.500.11937/96496
_version_ 1848766158297104384
author Nguyen, Hoa Van
Nguyen, Tran Thien Dat
Shim, Changbeom
Anuar, M.
author_facet Nguyen, Hoa Van
Nguyen, Tran Thien Dat
Shim, Changbeom
Anuar, M.
author_sort Nguyen, Hoa Van
building Curtin Institutional Repository
collection Online Access
description This paper proposes a smooth-trajectory estimator for the labelled multi-Bernoulli (LMB) filter by exploiting the special structure of the generalised labelled multi-Bernoulli (GLMB) filter. We devise a simple and intuitive approach to store the best association map when approximating the GLMB random finite set (RFS) to the LMB RFS. In particular, we construct a smooth-trajectory estimator (i.e., an estimator over the entire trajectories of labelled estimates) for the LMB filter based on the history of the best association map and all of the measurements up to the current time. Experimental results under two challenging scenarios demonstrate significant tracking accuracy improvements with negligible additional computational time compared to the conventional LMB filter.
first_indexed 2025-11-14T11:46:42Z
format Conference Paper
id curtin-20.500.11937-96496
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:46:42Z
publishDate 2023
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-964962025-01-09T06:39:34Z The Smooth Trajectory Estimator for LMB Filters Nguyen, Hoa Van Nguyen, Tran Thien Dat Shim, Changbeom Anuar, M. This paper proposes a smooth-trajectory estimator for the labelled multi-Bernoulli (LMB) filter by exploiting the special structure of the generalised labelled multi-Bernoulli (GLMB) filter. We devise a simple and intuitive approach to store the best association map when approximating the GLMB random finite set (RFS) to the LMB RFS. In particular, we construct a smooth-trajectory estimator (i.e., an estimator over the entire trajectories of labelled estimates) for the LMB filter based on the history of the best association map and all of the measurements up to the current time. Experimental results under two challenging scenarios demonstrate significant tracking accuracy improvements with negligible additional computational time compared to the conventional LMB filter. 2023 Conference Paper http://hdl.handle.net/20.500.11937/96496 10.1109/ICCAIS59597.2023.10382267 http://purl.org/au-research/grants/arc/LP200301507 fulltext
spellingShingle Nguyen, Hoa Van
Nguyen, Tran Thien Dat
Shim, Changbeom
Anuar, M.
The Smooth Trajectory Estimator for LMB Filters
title The Smooth Trajectory Estimator for LMB Filters
title_full The Smooth Trajectory Estimator for LMB Filters
title_fullStr The Smooth Trajectory Estimator for LMB Filters
title_full_unstemmed The Smooth Trajectory Estimator for LMB Filters
title_short The Smooth Trajectory Estimator for LMB Filters
title_sort smooth trajectory estimator for lmb filters
url http://purl.org/au-research/grants/arc/LP200301507
http://hdl.handle.net/20.500.11937/96496