Message Passing and Hierarchical Models for Simultaneous Tracking and Registration

David Cormack; James R. Hopgood

doi:10.1109/TAES.2020.3046090

Message Passing and Hierarchical Models for Simultaneous Tracking and Registration

David Cormack, James R. Hopgood

School of Engineering & Physical Sciences

Research output: Contribution to journal › Article › peer-review

13 Citations (Scopus)

68 Downloads (Pure)

Abstract

Sensor registration is an important problem that must be considered when attempting to perform any kind of data fusion in multi-modal, multi-sensor target tracking. In this Multiple Target Tracking (MTT) application, any inaccuracies in the registration can lead to false tracks being created, and tracks of true targets being stopped prematurely. This article introduces a method for simultaneously tracking multiple targets in a surveillance region and estimating appropriate sensor registration parameters so that sensor fusion can be performed accurately. The proposed method is based around particle Belief Propagation (BP), a recent but highly efficient framework for tracking multiple targets. The proposed method also uses a hierarchical model which allows for multiple processes to be linked and interact with one another.We present a comprehensive set of simulations and results using differing, asynchronous sensor setups, and compare with a Random Finite Set (RFS) approach, namely the Sequential Monte Carlo (SMC)-Probability Hypothesis Density (PHD) filter. The results show the proposed method is 17% more accurate than the RFS approach on average.

Original language	English
Pages (from-to)	1524-1537
Number of pages	14
Journal	IEEE Transactions on Aerospace and Electronic Systems
Volume	57
Issue number	3
Early online date	5 Jan 2021
DOIs	https://doi.org/10.1109/TAES.2020.3046090
Publication status	Published - Jun 2021

Keywords

Belief propagation (BP)
PHD filter
camera
message passing
multiple target tracking (MTT)
radar
sensor fusion
sensor registration

ASJC Scopus subject areas

Aerospace Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/TAES.2020.3046090

Download pdf
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 1.72 MB

Cite this

@article{d5dcf8feaf9244c4bb249b98c8f8a48a,

title = "Message Passing and Hierarchical Models for Simultaneous Tracking and Registration",

abstract = "Sensor registration is an important problem that must be considered when attempting to perform any kind of data fusion in multi-modal, multi-sensor target tracking. In this Multiple Target Tracking (MTT) application, any inaccuracies in the registration can lead to false tracks being created, and tracks of true targets being stopped prematurely. This article introduces a method for simultaneously tracking multiple targets in a surveillance region and estimating appropriate sensor registration parameters so that sensor fusion can be performed accurately. The proposed method is based around particle Belief Propagation (BP), a recent but highly efficient framework for tracking multiple targets. The proposed method also uses a hierarchical model which allows for multiple processes to be linked and interact with one another.We present a comprehensive set of simulations and results using differing, asynchronous sensor setups, and compare with a Random Finite Set (RFS) approach, namely the Sequential Monte Carlo (SMC)-Probability Hypothesis Density (PHD) filter. The results show the proposed method is 17% more accurate than the RFS approach on average.",

keywords = "Belief propagation (BP), PHD filter, camera, message passing, multiple target tracking (MTT), radar, sensor fusion, sensor registration",

author = "David Cormack and Hopgood, {James R.}",

note = "Funding Information: This work was supported in part by the Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/S000631/1 and in part by the MOD University Defence Research Collaboration (UDRC) in Signal Processing. The work of D. Cormack was supported by Leonardo MW Ltd., Edinburgh, EH5 2XS, U.K. Publisher Copyright: {\textcopyright} 1965-2011 IEEE.",

year = "2021",

month = jun,

doi = "10.1109/TAES.2020.3046090",

language = "English",

volume = "57",

pages = "1524--1537",

journal = "IEEE Transactions on Aerospace and Electronic Systems",

issn = "0018-9251",

publisher = "IEEE",

number = "3",

}

TY - JOUR

T1 - Message Passing and Hierarchical Models for Simultaneous Tracking and Registration

AU - Cormack, David

AU - Hopgood, James R.

N1 - Funding Information: This work was supported in part by the Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/S000631/1 and in part by the MOD University Defence Research Collaboration (UDRC) in Signal Processing. The work of D. Cormack was supported by Leonardo MW Ltd., Edinburgh, EH5 2XS, U.K. Publisher Copyright: © 1965-2011 IEEE.

PY - 2021/6

Y1 - 2021/6

N2 - Sensor registration is an important problem that must be considered when attempting to perform any kind of data fusion in multi-modal, multi-sensor target tracking. In this Multiple Target Tracking (MTT) application, any inaccuracies in the registration can lead to false tracks being created, and tracks of true targets being stopped prematurely. This article introduces a method for simultaneously tracking multiple targets in a surveillance region and estimating appropriate sensor registration parameters so that sensor fusion can be performed accurately. The proposed method is based around particle Belief Propagation (BP), a recent but highly efficient framework for tracking multiple targets. The proposed method also uses a hierarchical model which allows for multiple processes to be linked and interact with one another.We present a comprehensive set of simulations and results using differing, asynchronous sensor setups, and compare with a Random Finite Set (RFS) approach, namely the Sequential Monte Carlo (SMC)-Probability Hypothesis Density (PHD) filter. The results show the proposed method is 17% more accurate than the RFS approach on average.

AB - Sensor registration is an important problem that must be considered when attempting to perform any kind of data fusion in multi-modal, multi-sensor target tracking. In this Multiple Target Tracking (MTT) application, any inaccuracies in the registration can lead to false tracks being created, and tracks of true targets being stopped prematurely. This article introduces a method for simultaneously tracking multiple targets in a surveillance region and estimating appropriate sensor registration parameters so that sensor fusion can be performed accurately. The proposed method is based around particle Belief Propagation (BP), a recent but highly efficient framework for tracking multiple targets. The proposed method also uses a hierarchical model which allows for multiple processes to be linked and interact with one another.We present a comprehensive set of simulations and results using differing, asynchronous sensor setups, and compare with a Random Finite Set (RFS) approach, namely the Sequential Monte Carlo (SMC)-Probability Hypothesis Density (PHD) filter. The results show the proposed method is 17% more accurate than the RFS approach on average.

KW - Belief propagation (BP)

KW - PHD filter

KW - camera

KW - message passing

KW - multiple target tracking (MTT)

KW - radar

KW - sensor fusion

KW - sensor registration

UR - http://www.scopus.com/inward/record.url?scp=85099197868&partnerID=8YFLogxK

U2 - 10.1109/TAES.2020.3046090

DO - 10.1109/TAES.2020.3046090

M3 - Article

AN - SCOPUS:85099197868

SN - 0018-9251

VL - 57

SP - 1524

EP - 1537

JO - IEEE Transactions on Aerospace and Electronic Systems

JF - IEEE Transactions on Aerospace and Electronic Systems

IS - 3

ER -

Message Passing and Hierarchical Models for Simultaneous Tracking and Registration

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this