A Bayesian solution to multi-target tracking problems with mixed labelling

E.H. Aoki, Y. Boers, Lennart Svensson, Pranab K. Mandal, Arunabha Bagchi

Research output: Book/ReportReportProfessional

35 Downloads (Pure)

Abstract

In Multi-Target Tracking (MTT), the problem of assigning labels to tracks (track labelling) is vastly covered in literature and has been previously formulated using Bayesian recursion. However, the existing literature lacks an appropriate measure of uncertainty related to the assigned labels which has sound mathematical basis and clear practical meaning (to the user). This is especially important in a situation where targets move in close proximity with each other and thereafter separate again. Because, in such a situation it is well-known that there will be confusion on target identities, also known as “mixed labelling‿. In this paper, we provide a mathematical characterization of the labelling uncertainties present in Bayesian multi-target tracking and labelling (MTTL) problems and define measures of labelling uncertainties with clear physical interpretation. The introduced uncertainty measures can be used to find the optimal track label assignment, and evaluate track labelling performance. We also analyze in details the mixed labelling phenomenon in the presence of two targets. In addition, we propose a new Sequential Monte Carlo (SMC) algorithm, the Labelling Uncertainty Aware Particle Filter (LUA-PF), for the multi target tracking and labelling problem that can provide good estimates of the uncertainty measures. We validate this using simulation and show that the proposed method performs much better when compared with the performance of the SIR multi-target SMC filter.
Original languageUndefined
Place of PublicationEnschede
PublisherUniversity of Twente, Department of Applied Mathematics
Number of pages22
Publication statusPublished - Jul 2014

Publication series

NameMemorandum of the Department of Applied Mathematics
No.2036
ISSN (Print)1874-4850

Keywords

  • Labelling error
  • EWI-24915
  • Multi-target tracking
  • IR-91442
  • METIS-305948
  • Track labelling
  • Sequential Monte Carlo methods

Cite this

Aoki, E. H., Boers, Y., Svensson, L., Mandal, P. K., & Bagchi, A. (2014). A Bayesian solution to multi-target tracking problems with mixed labelling. (Memorandum of the Department of Applied Mathematics; No. 2036). Enschede: University of Twente, Department of Applied Mathematics.
Aoki, E.H. ; Boers, Y. ; Svensson, Lennart ; Mandal, Pranab K. ; Bagchi, Arunabha. / A Bayesian solution to multi-target tracking problems with mixed labelling. Enschede : University of Twente, Department of Applied Mathematics, 2014. 22 p. (Memorandum of the Department of Applied Mathematics; 2036).
@book{6b91a1c7183844bf8f4f58650a75a89e,
title = "A Bayesian solution to multi-target tracking problems with mixed labelling",
abstract = "In Multi-Target Tracking (MTT), the problem of assigning labels to tracks (track labelling) is vastly covered in literature and has been previously formulated using Bayesian recursion. However, the existing literature lacks an appropriate measure of uncertainty related to the assigned labels which has sound mathematical basis and clear practical meaning (to the user). This is especially important in a situation where targets move in close proximity with each other and thereafter separate again. Because, in such a situation it is well-known that there will be confusion on target identities, also known as “mixed labelling‿. In this paper, we provide a mathematical characterization of the labelling uncertainties present in Bayesian multi-target tracking and labelling (MTTL) problems and define measures of labelling uncertainties with clear physical interpretation. The introduced uncertainty measures can be used to find the optimal track label assignment, and evaluate track labelling performance. We also analyze in details the mixed labelling phenomenon in the presence of two targets. In addition, we propose a new Sequential Monte Carlo (SMC) algorithm, the Labelling Uncertainty Aware Particle Filter (LUA-PF), for the multi target tracking and labelling problem that can provide good estimates of the uncertainty measures. We validate this using simulation and show that the proposed method performs much better when compared with the performance of the SIR multi-target SMC filter.",
keywords = "Labelling error, EWI-24915, Multi-target tracking, IR-91442, METIS-305948, Track labelling, Sequential Monte Carlo methods",
author = "E.H. Aoki and Y. Boers and Lennart Svensson and Mandal, {Pranab K.} and Arunabha Bagchi",
note = "eemcs-eprint-24915",
year = "2014",
month = "7",
language = "Undefined",
series = "Memorandum of the Department of Applied Mathematics",
publisher = "University of Twente, Department of Applied Mathematics",
number = "2036",

}

Aoki, EH, Boers, Y, Svensson, L, Mandal, PK & Bagchi, A 2014, A Bayesian solution to multi-target tracking problems with mixed labelling. Memorandum of the Department of Applied Mathematics, no. 2036, University of Twente, Department of Applied Mathematics, Enschede.

A Bayesian solution to multi-target tracking problems with mixed labelling. / Aoki, E.H.; Boers, Y.; Svensson, Lennart; Mandal, Pranab K.; Bagchi, Arunabha.

Enschede : University of Twente, Department of Applied Mathematics, 2014. 22 p. (Memorandum of the Department of Applied Mathematics; No. 2036).

Research output: Book/ReportReportProfessional

TY - BOOK

T1 - A Bayesian solution to multi-target tracking problems with mixed labelling

AU - Aoki, E.H.

AU - Boers, Y.

AU - Svensson, Lennart

AU - Mandal, Pranab K.

AU - Bagchi, Arunabha

N1 - eemcs-eprint-24915

PY - 2014/7

Y1 - 2014/7

N2 - In Multi-Target Tracking (MTT), the problem of assigning labels to tracks (track labelling) is vastly covered in literature and has been previously formulated using Bayesian recursion. However, the existing literature lacks an appropriate measure of uncertainty related to the assigned labels which has sound mathematical basis and clear practical meaning (to the user). This is especially important in a situation where targets move in close proximity with each other and thereafter separate again. Because, in such a situation it is well-known that there will be confusion on target identities, also known as “mixed labelling‿. In this paper, we provide a mathematical characterization of the labelling uncertainties present in Bayesian multi-target tracking and labelling (MTTL) problems and define measures of labelling uncertainties with clear physical interpretation. The introduced uncertainty measures can be used to find the optimal track label assignment, and evaluate track labelling performance. We also analyze in details the mixed labelling phenomenon in the presence of two targets. In addition, we propose a new Sequential Monte Carlo (SMC) algorithm, the Labelling Uncertainty Aware Particle Filter (LUA-PF), for the multi target tracking and labelling problem that can provide good estimates of the uncertainty measures. We validate this using simulation and show that the proposed method performs much better when compared with the performance of the SIR multi-target SMC filter.

AB - In Multi-Target Tracking (MTT), the problem of assigning labels to tracks (track labelling) is vastly covered in literature and has been previously formulated using Bayesian recursion. However, the existing literature lacks an appropriate measure of uncertainty related to the assigned labels which has sound mathematical basis and clear practical meaning (to the user). This is especially important in a situation where targets move in close proximity with each other and thereafter separate again. Because, in such a situation it is well-known that there will be confusion on target identities, also known as “mixed labelling‿. In this paper, we provide a mathematical characterization of the labelling uncertainties present in Bayesian multi-target tracking and labelling (MTTL) problems and define measures of labelling uncertainties with clear physical interpretation. The introduced uncertainty measures can be used to find the optimal track label assignment, and evaluate track labelling performance. We also analyze in details the mixed labelling phenomenon in the presence of two targets. In addition, we propose a new Sequential Monte Carlo (SMC) algorithm, the Labelling Uncertainty Aware Particle Filter (LUA-PF), for the multi target tracking and labelling problem that can provide good estimates of the uncertainty measures. We validate this using simulation and show that the proposed method performs much better when compared with the performance of the SIR multi-target SMC filter.

KW - Labelling error

KW - EWI-24915

KW - Multi-target tracking

KW - IR-91442

KW - METIS-305948

KW - Track labelling

KW - Sequential Monte Carlo methods

M3 - Report

T3 - Memorandum of the Department of Applied Mathematics

BT - A Bayesian solution to multi-target tracking problems with mixed labelling

PB - University of Twente, Department of Applied Mathematics

CY - Enschede

ER -

Aoki EH, Boers Y, Svensson L, Mandal PK, Bagchi A. A Bayesian solution to multi-target tracking problems with mixed labelling. Enschede: University of Twente, Department of Applied Mathematics, 2014. 22 p. (Memorandum of the Department of Applied Mathematics; 2036).