Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments

Romain Delabeye; Hyo Sang Shin; Gokhan Inalhan

doi:10.1007/978-3-030-97672-9_31

Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments

Romain Delabeye^*, Hyo Sang Shin, Gokhan Inalhan

^*Corresponding author for this work

Cranfield University

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

1 Citation (Scopus)

Abstract

The Sequential Monte Carlo Probability Hypothesis Density (SMC-PHD) filter is a permissive multi-target tracker, performing state estimation through particle filtering with implicit data association. This filter is thus effective even in presence of clutter and nonlinear dynamics, while remaining tractable for real-time applications due to its computationally efficient data association process. Sensors are sometimes capable of sensing target features, which add up to kinematic measurements, e.g. range and bearing. In this paper, the adaptive Feature-Aided-SMC-PHD filter is designed, making use of feature information to increase the SMC-PHD’s estimation performance with respect to clutter, detection probability and location precision. As suspected, further differentiating targets from clutter led to greater sample degeneracy, especially as the detection probability drops. An adaptive sampling scheme was hence developed in order to relax this phenomenon. A radar application is considered in this study to validate this paper’s approach using Monte Carlo simulations.

Original language	English
Title of host publication	Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications
Editors	Jinwhan Kim, Brendan Englot, Hae-Won Park, Han-Lim Choi, Hyun Myung, Junmo Kim, Jong-Hwan Kim
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	351-362
Number of pages	12
ISBN (Print)	9783030976712
DOIs	https://doi.org/10.1007/978-3-030-97672-9_31
Publication status	Published - 2022
Externally published	Yes
Event	9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021 - Daejeon, Korea, Democratic People's Republic of Duration: 16 Dec 2021 → 17 Dec 2021

Publication series

Name	Lecture Notes in Networks and Systems
Volume	429 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021
Country/Territory	Korea, Democratic People's Republic of
City	Daejeon
Period	16/12/21 → 17/12/21

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Degeneracy
Feature-aided tracking
Multi-target tracking
Particle filter
Probability hypothesis density
SMC-PHD

Access to Document

10.1007/978-3-030-97672-9_31

Cite this

Delabeye, R., Shin, H. S., & Inalhan, G. (2022). Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments. In J. Kim, B. Englot, H.-W. Park, H.-L. Choi, H. Myung, J. Kim, & J.-H. Kim (Eds.), Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications (pp. 351-362). (Lecture Notes in Networks and Systems; Vol. 429 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-97672-9_31

Delabeye, Romain ; Shin, Hyo Sang ; Inalhan, Gokhan. / Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments. Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications. editor / Jinwhan Kim ; Brendan Englot ; Hae-Won Park ; Han-Lim Choi ; Hyun Myung ; Junmo Kim ; Jong-Hwan Kim. Springer Science and Business Media Deutschland GmbH, 2022. pp. 351-362 (Lecture Notes in Networks and Systems).

@inproceedings{b74321c285cb4803ad0afd9e3a4a6102,

title = "Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments",

abstract = "The Sequential Monte Carlo Probability Hypothesis Density (SMC-PHD) filter is a permissive multi-target tracker, performing state estimation through particle filtering with implicit data association. This filter is thus effective even in presence of clutter and nonlinear dynamics, while remaining tractable for real-time applications due to its computationally efficient data association process. Sensors are sometimes capable of sensing target features, which add up to kinematic measurements, e.g. range and bearing. In this paper, the adaptive Feature-Aided-SMC-PHD filter is designed, making use of feature information to increase the SMC-PHD{\textquoteright}s estimation performance with respect to clutter, detection probability and location precision. As suspected, further differentiating targets from clutter led to greater sample degeneracy, especially as the detection probability drops. An adaptive sampling scheme was hence developed in order to relax this phenomenon. A radar application is considered in this study to validate this paper{\textquoteright}s approach using Monte Carlo simulations.",

keywords = "Degeneracy, Feature-aided tracking, Multi-target tracking, Particle filter, Probability hypothesis density, SMC-PHD",

author = "Romain Delabeye and Shin, {Hyo Sang} and Gokhan Inalhan",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021 ; Conference date: 16-12-2021 Through 17-12-2021",

year = "2022",

doi = "10.1007/978-3-030-97672-9_31",

language = "English",

isbn = "9783030976712",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "351--362",

editor = "Jinwhan Kim and Brendan Englot and Hae-Won Park and Han-Lim Choi and Hyun Myung and Junmo Kim and Jong-Hwan Kim",

booktitle = "Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications",

address = "Germany",

}

Delabeye, R, Shin, HS & Inalhan, G 2022, Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments. in J Kim, B Englot, H-W Park, H-L Choi, H Myung, J Kim & J-H Kim (eds), Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications. Lecture Notes in Networks and Systems, vol. 429 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 351-362, 9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021, Daejeon, Korea, Democratic People's Republic of, 16/12/21. https://doi.org/10.1007/978-3-030-97672-9_31

Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments. / Delabeye, Romain; Shin, Hyo Sang; Inalhan, Gokhan.
Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications. ed. / Jinwhan Kim; Brendan Englot; Hae-Won Park; Han-Lim Choi; Hyun Myung; Junmo Kim; Jong-Hwan Kim. Springer Science and Business Media Deutschland GmbH, 2022. p. 351-362 (Lecture Notes in Networks and Systems; Vol. 429 LNNS).

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

TY - GEN

T1 - Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments

AU - Delabeye, Romain

AU - Shin, Hyo Sang

AU - Inalhan, Gokhan

PY - 2022

Y1 - 2022

N2 - The Sequential Monte Carlo Probability Hypothesis Density (SMC-PHD) filter is a permissive multi-target tracker, performing state estimation through particle filtering with implicit data association. This filter is thus effective even in presence of clutter and nonlinear dynamics, while remaining tractable for real-time applications due to its computationally efficient data association process. Sensors are sometimes capable of sensing target features, which add up to kinematic measurements, e.g. range and bearing. In this paper, the adaptive Feature-Aided-SMC-PHD filter is designed, making use of feature information to increase the SMC-PHD’s estimation performance with respect to clutter, detection probability and location precision. As suspected, further differentiating targets from clutter led to greater sample degeneracy, especially as the detection probability drops. An adaptive sampling scheme was hence developed in order to relax this phenomenon. A radar application is considered in this study to validate this paper’s approach using Monte Carlo simulations.

AB - The Sequential Monte Carlo Probability Hypothesis Density (SMC-PHD) filter is a permissive multi-target tracker, performing state estimation through particle filtering with implicit data association. This filter is thus effective even in presence of clutter and nonlinear dynamics, while remaining tractable for real-time applications due to its computationally efficient data association process. Sensors are sometimes capable of sensing target features, which add up to kinematic measurements, e.g. range and bearing. In this paper, the adaptive Feature-Aided-SMC-PHD filter is designed, making use of feature information to increase the SMC-PHD’s estimation performance with respect to clutter, detection probability and location precision. As suspected, further differentiating targets from clutter led to greater sample degeneracy, especially as the detection probability drops. An adaptive sampling scheme was hence developed in order to relax this phenomenon. A radar application is considered in this study to validate this paper’s approach using Monte Carlo simulations.

KW - Degeneracy

KW - Feature-aided tracking

KW - Multi-target tracking

KW - Particle filter

KW - Probability hypothesis density

KW - SMC-PHD

UR - http://www.scopus.com/inward/record.url?scp=85128473803&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-97672-9_31

DO - 10.1007/978-3-030-97672-9_31

M3 - Conference contribution

AN - SCOPUS:85128473803

SN - 9783030976712

T3 - Lecture Notes in Networks and Systems

SP - 351

EP - 362

BT - Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications

A2 - Kim, Jinwhan

A2 - Englot, Brendan

A2 - Park, Hae-Won

A2 - Choi, Han-Lim

A2 - Myung, Hyun

A2 - Kim, Junmo

A2 - Kim, Jong-Hwan

PB - Springer Science and Business Media Deutschland GmbH

T2 - 9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021

Y2 - 16 December 2021 through 17 December 2021

ER -

Delabeye R, Shin HS, Inalhan G. Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments. In Kim J, Englot B, Park HW, Choi HL, Myung H, Kim J, Kim JH, editors, Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications. Springer Science and Business Media Deutschland GmbH. 2022. p. 351-362. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-030-97672-9_31

Feature-Aided SMC-PHD Filter for Nonlinear Multi-target Tracking in Cluttered Environments

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this