A Multi‐Scan Possibility GLMB Model for Multi‐Target Tracking Under Epistemic Uncertainty
IET Radar, Sonar & Navigation · 2026-01 · 20 (1)
DOI: 10.1049/rsn2.70188 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Radar, Sonar & Navigation, online erschienen am 22.07.2026. Verfasst von Keya Fu und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This work addresses the difficult issue of tracking multiple targets in the presence of epistemic uncertainty. We propose a multiscan possibility‐based generalised labelled multiBernoulli (GLMB) smoothing approach designed to prevent track fragmentation and switching when detection profiles are unknown and vary over time. By incorporating a labelled uncertainty finite set (UFS) derived from possibility theory into the multiscan GLMB framework, the estimation of multitarget states is enhanced, yielding a possibility‐theoretic counterpart to the standard multiscan GLMB smoothing procedure. These multiscan possibility functions can effectively represent epistemic uncertainties that stem from limited knowledge of the detection profile. The prediction and update steps of these possibility functions are expressed using a Gaussian max‐mixture (GMM), which simplifies the execution of the multiscan possibility GLMB recursion. Simulation outcomes indicate that, under epistemic uncertainty, the proposed multiscan possibility GLMB smoothing provides improved estimates of both multitarget trajectories and target cardinality, particularly in practical scenarios.
Zitieren
APA
Fu, K., Zhu, H., Zhang, C., Zhang, J., & Cao, C. (2026). A Multi‐Scan Possibility GLMB Model for Multi‐Target Tracking Under Epistemic Uncertainty. IET Radar, Sonar & Navigation, 20(1). https://doi.org/10.1049/rsn2.70188
Vancouver
Fu K, Zhu H, Zhang C, Zhang J, Cao C. A Multi‐Scan Possibility GLMB Model for Multi‐Target Tracking Under Epistemic Uncertainty. IET Radar, Sonar & Navigation. 2026;20(1). doi:10.1049/rsn2.70188
BibTeX
@article{Fu2026,
author = {Fu, Keya and Zhu, Hai and Zhang, Cheng and Zhang, Ji and Cao, Chenghu},
title = {A Multi‐Scan Possibility GLMB Model for Multi‐Target Tracking Under Epistemic Uncertainty},
journal = {IET Radar, Sonar & Navigation},
year = {2026},
volume = {20},
number = {1},
doi = {10.1049/rsn2.70188}
}
EUVIMED