A Linear-Complexity Second-Order Multi-Object Filter via Factorial Cumulants

Daniel E. Clark; Flávio De Melo

doi:10.23919/ICIF.2018.8455331

A Linear-Complexity Second-Order Multi-Object Filter via Factorial Cumulants

Daniel E. Clark, Flávio De Melo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

Abstract

Multi-target tracking solutions with low computational complexity are required in order to address large-scale tracking problems. Solutions based on statistics determined from point processes, such as the PHD filter, CPHD filter, and newer second-order PHD filter are some examples of these algorithms. There are few solutions of linear complexity in the number of targets and number of measurements, with the PHD filter being one exception. However, the trade-off is that it is unable to propagate beyond first-order moment statistics. In this paper, a new filter is proposed with the same complexity as the PHD filter that also propagates second-order information via the second-order factorial cumulant. The results show that the algorithm is more robust than the PHD filter in challenging clutter environments.

Original language	English
Title of host publication	2018 21st International Conference on Information Fusion (FUSION)
Publisher	IEEE
Pages	1250-1259
Number of pages	10
ISBN (Electronic)	9780996452762
DOIs	https://doi.org/10.23919/ICIF.2018.8455331
Publication status	Published - 6 Sept 2018
Event	21st International Conference on Information Fusion 2018 - Cambridge, United Kingdom Duration: 10 Jul 2018 → 13 Jul 2018

Conference

Conference	21st International Conference on Information Fusion 2018
Abbreviated title	FUSION 2018
Country/Territory	United Kingdom
City	Cambridge
Period	10/07/18 → 13/07/18

Keywords

factorial cumulants
Multi-target tracking
point processes

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Signal Processing
Statistics, Probability and Uncertainty
Instrumentation

Access to Document

10.23919/ICIF.2018.8455331

Cite this

@inproceedings{0fb21d98803c4144ab5c196cb07a7196,

title = "A Linear-Complexity Second-Order Multi-Object Filter via Factorial Cumulants",

abstract = "Multi-target tracking solutions with low computational complexity are required in order to address large-scale tracking problems. Solutions based on statistics determined from point processes, such as the PHD filter, CPHD filter, and newer second-order PHD filter are some examples of these algorithms. There are few solutions of linear complexity in the number of targets and number of measurements, with the PHD filter being one exception. However, the trade-off is that it is unable to propagate beyond first-order moment statistics. In this paper, a new filter is proposed with the same complexity as the PHD filter that also propagates second-order information via the second-order factorial cumulant. The results show that the algorithm is more robust than the PHD filter in challenging clutter environments.",

keywords = "factorial cumulants, Multi-target tracking, point processes",

author = "Clark, {Daniel E.} and {De Melo}, Fl{\'a}vio",

year = "2018",

month = sep,

day = "6",

doi = "10.23919/ICIF.2018.8455331",

language = "English",

pages = "1250--1259",

booktitle = "2018 21st International Conference on Information Fusion (FUSION)",

publisher = "IEEE",

address = "United States",

note = "21st International Conference on Information Fusion 2018, FUSION 2018 ; Conference date: 10-07-2018 Through 13-07-2018",

}

TY - GEN

T1 - A Linear-Complexity Second-Order Multi-Object Filter via Factorial Cumulants

AU - Clark, Daniel E.

AU - De Melo, Flávio

PY - 2018/9/6

Y1 - 2018/9/6

N2 - Multi-target tracking solutions with low computational complexity are required in order to address large-scale tracking problems. Solutions based on statistics determined from point processes, such as the PHD filter, CPHD filter, and newer second-order PHD filter are some examples of these algorithms. There are few solutions of linear complexity in the number of targets and number of measurements, with the PHD filter being one exception. However, the trade-off is that it is unable to propagate beyond first-order moment statistics. In this paper, a new filter is proposed with the same complexity as the PHD filter that also propagates second-order information via the second-order factorial cumulant. The results show that the algorithm is more robust than the PHD filter in challenging clutter environments.

AB - Multi-target tracking solutions with low computational complexity are required in order to address large-scale tracking problems. Solutions based on statistics determined from point processes, such as the PHD filter, CPHD filter, and newer second-order PHD filter are some examples of these algorithms. There are few solutions of linear complexity in the number of targets and number of measurements, with the PHD filter being one exception. However, the trade-off is that it is unable to propagate beyond first-order moment statistics. In this paper, a new filter is proposed with the same complexity as the PHD filter that also propagates second-order information via the second-order factorial cumulant. The results show that the algorithm is more robust than the PHD filter in challenging clutter environments.

KW - factorial cumulants

KW - Multi-target tracking

KW - point processes

UR - http://www.scopus.com/inward/record.url?scp=85054065624&partnerID=8YFLogxK

U2 - 10.23919/ICIF.2018.8455331

DO - 10.23919/ICIF.2018.8455331

M3 - Conference contribution

AN - SCOPUS:85054065624

SP - 1250

EP - 1259

BT - 2018 21st International Conference on Information Fusion (FUSION)

PB - IEEE

T2 - 21st International Conference on Information Fusion 2018

Y2 - 10 July 2018 through 13 July 2018

ER -

A Linear-Complexity Second-Order Multi-Object Filter via Factorial Cumulants

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this