Multi-object tracking with an adaptive generalized labeled multi-Bernoulli filter

Cong Thanh Do; Tran Thien Dat Nguyen; Diluka Moratuwage; Changbeom Shim; Yon Dohn Chung

doi:10.1016/j.sigpro.2022.108532

Multi-object tracking with an adaptive generalized labeled multi-Bernoulli filter

Cong Thanh Do, Tran Thien Dat Nguyen, Diluka Moratuwage, Changbeom Shim, Yon Dohn Chung

Department of Computer Science and Engineering

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

15 Citations (Scopus)

Abstract

The challenges in multi-object tracking mainly stem from the random variations in the cardinality and states of objects during the tracking process. Further, the information on locations where the objects appear, their detection probabilities, and the statistics of the sensor's false alarms significantly influence the tracking accuracy of the filter. However, this information is usually assumed to be known and provided by the users. In this paper, we propose an adaptive generalized labeled multi-Bernoulli (GLMB) filter which can track multiple objects without prior knowledge of the aforementioned information. Experimental results show that the performance of the proposed filter is comparable to an ideal GLMB filter supplied with correct information of the tracking scenarios.

Original language	English
Article number	108532
Journal	Signal Processing
Volume	196
DOIs	https://doi.org/10.1016/j.sigpro.2022.108532
Publication status	Published - 2022 Jul

Bibliographical note

Funding Information:
This work was partly supported by the Joint-scholarship between Ministry of Education and Training Vietnam and Curtin International Postgraduate Research Scholarship (MOET-CIPRS), and the Ministry of Science and ICT (MSIT), Korea, under the ICT Creative Consilience program (IITP-2021-2020-0-01819) supervised by the Institute for Information & communications Technology Planning & Evaluation (IITP).

Publisher Copyright:
© 2022 Elsevier B.V.

Keywords

Adaptive birth model
Bootstrapping
GLMB Filter
Multi-object Bayes filter
Unknown clutter rate
Unknown detection probability

ASJC Scopus subject areas

Control and Systems Engineering
Software
Signal Processing
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1016/j.sigpro.2022.108532

Cite this

@article{a2ffc47b57674294ae1052cc706e30c0,

title = "Multi-object tracking with an adaptive generalized labeled multi-Bernoulli filter",

abstract = "The challenges in multi-object tracking mainly stem from the random variations in the cardinality and states of objects during the tracking process. Further, the information on locations where the objects appear, their detection probabilities, and the statistics of the sensor's false alarms significantly influence the tracking accuracy of the filter. However, this information is usually assumed to be known and provided by the users. In this paper, we propose an adaptive generalized labeled multi-Bernoulli (GLMB) filter which can track multiple objects without prior knowledge of the aforementioned information. Experimental results show that the performance of the proposed filter is comparable to an ideal GLMB filter supplied with correct information of the tracking scenarios.",

keywords = "Adaptive birth model, Bootstrapping, GLMB Filter, Multi-object Bayes filter, Unknown clutter rate, Unknown detection probability",

author = "Do, {Cong Thanh} and {Dat Nguyen}, {Tran Thien} and Diluka Moratuwage and Changbeom Shim and Chung, {Yon Dohn}",

note = "Funding Information: This work was partly supported by the Joint-scholarship between Ministry of Education and Training Vietnam and Curtin International Postgraduate Research Scholarship (MOET-CIPRS), and the Ministry of Science and ICT (MSIT), Korea, under the ICT Creative Consilience program (IITP-2021-2020-0-01819) supervised by the Institute for Information & communications Technology Planning & Evaluation (IITP). Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2022",

month = jul,

doi = "10.1016/j.sigpro.2022.108532",

language = "English",

volume = "196",

journal = "Signal Processing",

issn = "0165-1684",

publisher = "Elsevier",

}

TY - JOUR

T1 - Multi-object tracking with an adaptive generalized labeled multi-Bernoulli filter

AU - Do, Cong Thanh

AU - Dat Nguyen, Tran Thien

AU - Moratuwage, Diluka

AU - Shim, Changbeom

AU - Chung, Yon Dohn

N1 - Funding Information: This work was partly supported by the Joint-scholarship between Ministry of Education and Training Vietnam and Curtin International Postgraduate Research Scholarship (MOET-CIPRS), and the Ministry of Science and ICT (MSIT), Korea, under the ICT Creative Consilience program (IITP-2021-2020-0-01819) supervised by the Institute for Information & communications Technology Planning & Evaluation (IITP). Publisher Copyright: © 2022 Elsevier B.V.

PY - 2022/7

Y1 - 2022/7

N2 - The challenges in multi-object tracking mainly stem from the random variations in the cardinality and states of objects during the tracking process. Further, the information on locations where the objects appear, their detection probabilities, and the statistics of the sensor's false alarms significantly influence the tracking accuracy of the filter. However, this information is usually assumed to be known and provided by the users. In this paper, we propose an adaptive generalized labeled multi-Bernoulli (GLMB) filter which can track multiple objects without prior knowledge of the aforementioned information. Experimental results show that the performance of the proposed filter is comparable to an ideal GLMB filter supplied with correct information of the tracking scenarios.

AB - The challenges in multi-object tracking mainly stem from the random variations in the cardinality and states of objects during the tracking process. Further, the information on locations where the objects appear, their detection probabilities, and the statistics of the sensor's false alarms significantly influence the tracking accuracy of the filter. However, this information is usually assumed to be known and provided by the users. In this paper, we propose an adaptive generalized labeled multi-Bernoulli (GLMB) filter which can track multiple objects without prior knowledge of the aforementioned information. Experimental results show that the performance of the proposed filter is comparable to an ideal GLMB filter supplied with correct information of the tracking scenarios.

KW - Adaptive birth model

KW - Bootstrapping

KW - GLMB Filter

KW - Multi-object Bayes filter

KW - Unknown clutter rate

KW - Unknown detection probability

UR - http://www.scopus.com/inward/record.url?scp=85126012764&partnerID=8YFLogxK

U2 - 10.1016/j.sigpro.2022.108532

DO - 10.1016/j.sigpro.2022.108532

M3 - Article

AN - SCOPUS:85126012764

SN - 0165-1684

VL - 196

JO - Signal Processing

JF - Signal Processing

M1 - 108532

ER -

Multi-object tracking with an adaptive generalized labeled multi-Bernoulli filter

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this