Re-Identification for Multi-Object Tracking Using Triplet Loss

Koung Suk Ko; Woo Jin Ahn; Geon Hee Kim; Myo Taeg Lim; Tae Koo Kang; Dong Sung Pae

doi:10.1109/ICOIN50884.2021.9334017

Re-Identification for Multi-Object Tracking Using Triplet Loss

Koung Suk Ko
, Woo Jin Ahn
, Geon Hee Kim
, Myo Taeg Lim
, Tae Koo Kang
, Dong Sung Pae

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

2 Citations (Scopus)

Abstract

Assigning a consistent identification(ID) number is a chronic problem in the tracking model. However, recent tracking models lose the ID because it focuses only on the previous frame. This paper constructed a tracking deep learning model using triplet loss to give consistent ID to objects detected while tracking. We also show the best way for pre-processing the input for the triplet-tracking model, which inputs various image sizes. The experimental result of 97.76% accuracy on KITTI shows the effectiveness of our result.

Original language	English
Title of host publication	35th International Conference on Information Networking, ICOIN 2021
Publisher	IEEE Computer Society
Pages	525-527
Number of pages	3
ISBN (Electronic)	9781728191003
DOIs	https://doi.org/10.1109/ICOIN50884.2021.9334017
Publication status	Published - 2021 Jan 13
Event	35th International Conference on Information Networking, ICOIN 2021 - Jeju Island, Korea, Republic of Duration: 2021 Jan 13 → 2021 Jan 16

Publication series

Name	International Conference on Information Networking
Volume	2021-January
ISSN (Print)	1976-7684

Conference

Conference	35th International Conference on Information Networking, ICOIN 2021
Country/Territory	Korea, Republic of
City	Jeju Island
Period	21/1/13 → 21/1/16

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Metric Learning
Multi-Object Tracking
Re-Identification
Triplet Loss

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems

Access to Document

10.1109/ICOIN50884.2021.9334017

Cite this

Ko, K. S., Ahn, W. J., Kim, G. H., Lim, M. T., Kang, T. K., & Pae, D. S. (2021). Re-Identification for Multi-Object Tracking Using Triplet Loss. In 35th International Conference on Information Networking, ICOIN 2021 (pp. 525-527). Article 9334017 (International Conference on Information Networking; Vol. 2021-January). IEEE Computer Society. https://doi.org/10.1109/ICOIN50884.2021.9334017

Re-Identification for Multi-Object Tracking Using Triplet Loss. / Ko, Koung Suk; Ahn, Woo Jin; Kim, Geon Hee et al.
35th International Conference on Information Networking, ICOIN 2021. IEEE Computer Society, 2021. p. 525-527 9334017 (International Conference on Information Networking; Vol. 2021-January).

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

Ko, KS, Ahn, WJ, Kim, GH, Lim, MT, Kang, TK & Pae, DS 2021, Re-Identification for Multi-Object Tracking Using Triplet Loss. in 35th International Conference on Information Networking, ICOIN 2021., 9334017, International Conference on Information Networking, vol. 2021-January, IEEE Computer Society, pp. 525-527, 35th International Conference on Information Networking, ICOIN 2021, Jeju Island, Korea, Republic of, 21/1/13. https://doi.org/10.1109/ICOIN50884.2021.9334017

@inproceedings{cb83a8a3b2e0404b88fd8385d0745193,

title = "Re-Identification for Multi-Object Tracking Using Triplet Loss",

abstract = "Assigning a consistent identification(ID) number is a chronic problem in the tracking model. However, recent tracking models lose the ID because it focuses only on the previous frame. This paper constructed a tracking deep learning model using triplet loss to give consistent ID to objects detected while tracking. We also show the best way for pre-processing the input for the triplet-tracking model, which inputs various image sizes. The experimental result of 97.76\% accuracy on KITTI shows the effectiveness of our result.",

keywords = "Metric Learning, Multi-Object Tracking, Re-Identification, Triplet Loss",

author = "Ko, \{Koung Suk\} and Ahn, \{Woo Jin\} and Kim, \{Geon Hee\} and Lim, \{Myo Taeg\} and Kang, \{Tae Koo\} and Pae, \{Dong Sung\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 35th International Conference on Information Networking, ICOIN 2021 ; Conference date: 13-01-2021 Through 16-01-2021",

year = "2021",

month = jan,

day = "13",

doi = "10.1109/ICOIN50884.2021.9334017",

language = "English",

series = "International Conference on Information Networking",

publisher = "IEEE Computer Society",

pages = "525--527",

booktitle = "35th International Conference on Information Networking, ICOIN 2021",

}

TY - GEN

T1 - Re-Identification for Multi-Object Tracking Using Triplet Loss

AU - Ko, Koung Suk

AU - Ahn, Woo Jin

AU - Kim, Geon Hee

AU - Lim, Myo Taeg

AU - Kang, Tae Koo

AU - Pae, Dong Sung

PY - 2021/1/13

Y1 - 2021/1/13

N2 - Assigning a consistent identification(ID) number is a chronic problem in the tracking model. However, recent tracking models lose the ID because it focuses only on the previous frame. This paper constructed a tracking deep learning model using triplet loss to give consistent ID to objects detected while tracking. We also show the best way for pre-processing the input for the triplet-tracking model, which inputs various image sizes. The experimental result of 97.76% accuracy on KITTI shows the effectiveness of our result.

AB - Assigning a consistent identification(ID) number is a chronic problem in the tracking model. However, recent tracking models lose the ID because it focuses only on the previous frame. This paper constructed a tracking deep learning model using triplet loss to give consistent ID to objects detected while tracking. We also show the best way for pre-processing the input for the triplet-tracking model, which inputs various image sizes. The experimental result of 97.76% accuracy on KITTI shows the effectiveness of our result.

KW - Metric Learning

KW - Multi-Object Tracking

KW - Re-Identification

KW - Triplet Loss

UR - https://www.scopus.com/pages/publications/85100793787

U2 - 10.1109/ICOIN50884.2021.9334017

DO - 10.1109/ICOIN50884.2021.9334017

M3 - Conference contribution

AN - SCOPUS:85100793787

T3 - International Conference on Information Networking

SP - 525

EP - 527

BT - 35th International Conference on Information Networking, ICOIN 2021

PB - IEEE Computer Society

T2 - 35th International Conference on Information Networking, ICOIN 2021

Y2 - 13 January 2021 through 16 January 2021

ER -

Re-Identification for Multi-Object Tracking Using Triplet Loss

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this