Bernoulli merging for the Poisson multi-Bernoulli mixture filter



Fontana, Marco ORCID: 0000-0003-0703-6535, Garcia-Fenandez, Angel F and Maskell, Simon ORCID: 0000-0003-1917-2913
(2020) Bernoulli merging for the Poisson multi-Bernoulli mixture filter. In: 2020 IEEE 23rd International Conference on Information Fusion (FUSION), 2020-7-6 - 2020-7-9.

[img] Text
MergingPMBM-Fusion_paper_v14.pdf - Author Accepted Manuscript

Download (336kB) | Preview

Abstract

Under the standard multiple target tracking models and a Poisson point process birth model, the Poisson multi-Bernoulli mixture (PMBM) filter provides the closed-form recursion to computing the posterior density over the set of targets. Without approximations, the PMBM computational complexity rapidly rises in time due to the increasing number of data association hypotheses. This paper presents innovative strategies for merging Bernoulli components for the same potential target reducing the number of single-target hypotheses in the PMBM filter, aiming to lower its computational complexity while keeping its performance high. We use several measures to compute the similarity between different Bernoulli components. Simulation results show that the proposed algorithms show performance close to the PMBM filter without Bernoulli merging, as measured by the generalized optimal sub-pattern assignment (GOSPA) metric, with a significantly reduced execution time.

Item Type: Conference or Workshop Item (Unspecified)
Uncontrolled Keywords: Pediatric
Depositing User: Symplectic Admin
Date Deposited: 05 Oct 2020 08:31
Last Modified: 15 Mar 2024 08:52
DOI: 10.23919/fusion45008.2020.9190443
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3103219