Multiple object tracking via feature pyramid siamese networks

Sangyun Lee, Euntai Kim

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

When multiple object tracking (MOT) based on the tracking-by-detection paradigm is implemented, the similarity metric between the current detections and existing tracks plays an essential role. Most of the MOT schemes based on a deep neural network learn the similarity metric using a Siamese architecture, but the plain Siamese architecture might not be enough owing to its structural simplicity and lack of motion information. This paper aims to propose a new MOT scheme to overcome the existing problems in the conventional MOTs. Feature pyramid Siamese network (FPSN) is proposed to address the structural simplicity. The FPSN is inspired by a feature pyramid network (FPN) and it extends the Siamese network by applying FPN to the plain Siamese architecture and by developing a new multi-level discriminative feature. A spatiotemporal motion feature is added to the FPSN to overcome the lack of motion information and to enhance the performance in MOT. Thus, FPSN-MOT considers not only the appearance feature but also motion information. Finally, FPSN-MOT is applied to the public MOT challenge benchmark problems and its performance is compared to that of the other state-of-the-art MOT methods.

Original languageEnglish
Article number8587153
Pages (from-to)8181-8194
Number of pages14
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Deep neural networks

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

@article{43d70043a84649638402c5d3dc10a8f0,
title = "Multiple object tracking via feature pyramid siamese networks",
abstract = "When multiple object tracking (MOT) based on the tracking-by-detection paradigm is implemented, the similarity metric between the current detections and existing tracks plays an essential role. Most of the MOT schemes based on a deep neural network learn the similarity metric using a Siamese architecture, but the plain Siamese architecture might not be enough owing to its structural simplicity and lack of motion information. This paper aims to propose a new MOT scheme to overcome the existing problems in the conventional MOTs. Feature pyramid Siamese network (FPSN) is proposed to address the structural simplicity. The FPSN is inspired by a feature pyramid network (FPN) and it extends the Siamese network by applying FPN to the plain Siamese architecture and by developing a new multi-level discriminative feature. A spatiotemporal motion feature is added to the FPSN to overcome the lack of motion information and to enhance the performance in MOT. Thus, FPSN-MOT considers not only the appearance feature but also motion information. Finally, FPSN-MOT is applied to the public MOT challenge benchmark problems and its performance is compared to that of the other state-of-the-art MOT methods.",
author = "Sangyun Lee and Euntai Kim",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2018.2889442",
language = "English",
volume = "7",
pages = "8181--8194",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Multiple object tracking via feature pyramid siamese networks. / Lee, Sangyun; Kim, Euntai.

In: IEEE Access, Vol. 7, 8587153, 01.01.2019, p. 8181-8194.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multiple object tracking via feature pyramid siamese networks

AU - Lee, Sangyun

AU - Kim, Euntai

PY - 2019/1/1

Y1 - 2019/1/1

N2 - When multiple object tracking (MOT) based on the tracking-by-detection paradigm is implemented, the similarity metric between the current detections and existing tracks plays an essential role. Most of the MOT schemes based on a deep neural network learn the similarity metric using a Siamese architecture, but the plain Siamese architecture might not be enough owing to its structural simplicity and lack of motion information. This paper aims to propose a new MOT scheme to overcome the existing problems in the conventional MOTs. Feature pyramid Siamese network (FPSN) is proposed to address the structural simplicity. The FPSN is inspired by a feature pyramid network (FPN) and it extends the Siamese network by applying FPN to the plain Siamese architecture and by developing a new multi-level discriminative feature. A spatiotemporal motion feature is added to the FPSN to overcome the lack of motion information and to enhance the performance in MOT. Thus, FPSN-MOT considers not only the appearance feature but also motion information. Finally, FPSN-MOT is applied to the public MOT challenge benchmark problems and its performance is compared to that of the other state-of-the-art MOT methods.

AB - When multiple object tracking (MOT) based on the tracking-by-detection paradigm is implemented, the similarity metric between the current detections and existing tracks plays an essential role. Most of the MOT schemes based on a deep neural network learn the similarity metric using a Siamese architecture, but the plain Siamese architecture might not be enough owing to its structural simplicity and lack of motion information. This paper aims to propose a new MOT scheme to overcome the existing problems in the conventional MOTs. Feature pyramid Siamese network (FPSN) is proposed to address the structural simplicity. The FPSN is inspired by a feature pyramid network (FPN) and it extends the Siamese network by applying FPN to the plain Siamese architecture and by developing a new multi-level discriminative feature. A spatiotemporal motion feature is added to the FPSN to overcome the lack of motion information and to enhance the performance in MOT. Thus, FPSN-MOT considers not only the appearance feature but also motion information. Finally, FPSN-MOT is applied to the public MOT challenge benchmark problems and its performance is compared to that of the other state-of-the-art MOT methods.

UR - http://www.scopus.com/inward/record.url?scp=85059008939&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059008939&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2889442

DO - 10.1109/ACCESS.2018.2889442

M3 - Article

VL - 7

SP - 8181

EP - 8194

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8587153

ER -