Multi target tracking from drones by learning from generalized graph differences

Hakan Ardo; Mikael Nilsson

doi:10.1109/ICCVW.2019.00012

Multi target tracking from drones by learning from generalized graph differences

Hakan Ardo, Mikael Nilsson

Centre for Mathematical Sciences

Axis communications AB

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

Abstract

Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. The weights of such network flow problem can be learnt efficiently from training data using a recently introduced concept called Generalized Graph Differences (GGD). This allows a general tracker implementation to be specialized to drone videos by training it on the VisDrone dataset. Two modifications to the original GGD is introduced in this paper and a result with an average precision of 23.09 on the test set of VisDrone 2019 was achieved.

Original language	English
Title of host publication	Proceedings - 2019 International Conference on Computer Vision
Subtitle of host publication	Workshops, ICCVW 2019
Publisher	IEEE - Institute of Electrical and Electronics Engineers Inc.
Pages	46-54
Number of pages	9
ISBN (Electronic)	9781728150239
ISBN (Print)	978-1-7281-5024-6
DOIs	https://doi.org/10.1109/ICCVW.2019.00012
Publication status	Published - 2020 Mar 5
Event	17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of Duration: 2019 Oct 27 → 2019 Oct 28

Conference

Conference	17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
Country/Territory	Korea, Republic of
City	Seoul
Period	2019/10/27 → 2019/10/28

Subject classification (UKÄ)

Computational Mathematics
Computer Systems

Free keywords

Multi target tracking

Access to Document

10.1109/ICCVW.2019.00012

Cite this

@inproceedings{255202ed466940ff974832ea5fdedd69,

title = "Multi target tracking from drones by learning from generalized graph differences",

abstract = "Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. The weights of such network flow problem can be learnt efficiently from training data using a recently introduced concept called Generalized Graph Differences (GGD). This allows a general tracker implementation to be specialized to drone videos by training it on the VisDrone dataset. Two modifications to the original GGD is introduced in this paper and a result with an average precision of 23.09 on the test set of VisDrone 2019 was achieved.",

keywords = "Multi target tracking",

author = "Hakan Ardo and Mikael Nilsson",

year = "2020",

month = mar,

day = "5",

doi = "10.1109/ICCVW.2019.00012",

language = "English",

isbn = "978-1-7281-5024-6",

pages = "46--54",

booktitle = "Proceedings - 2019 International Conference on Computer Vision",

publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 ; Conference date: 27-10-2019 Through 28-10-2019",

}

Ardo, H & Nilsson, M 2020, Multi target tracking from drones by learning from generalized graph differences. in Proceedings - 2019 International Conference on Computer Vision : Workshops, ICCVW 2019. IEEE - Institute of Electrical and Electronics Engineers Inc., pp. 46-54, 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019, Seoul, Korea, Republic of, 2019/10/27. https://doi.org/10.1109/ICCVW.2019.00012

Multi target tracking from drones by learning from generalized graph differences. / Ardo, Hakan ; Nilsson, Mikael.
Proceedings - 2019 International Conference on Computer Vision : Workshops, ICCVW 2019. IEEE - Institute of Electrical and Electronics Engineers Inc., 2020. p. 46-54.

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

TY - GEN

T1 - Multi target tracking from drones by learning from generalized graph differences

AU - Ardo, Hakan

AU - Nilsson, Mikael

PY - 2020/3/5

Y1 - 2020/3/5

N2 - Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. The weights of such network flow problem can be learnt efficiently from training data using a recently introduced concept called Generalized Graph Differences (GGD). This allows a general tracker implementation to be specialized to drone videos by training it on the VisDrone dataset. Two modifications to the original GGD is introduced in this paper and a result with an average precision of 23.09 on the test set of VisDrone 2019 was achieved.

AB - Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. The weights of such network flow problem can be learnt efficiently from training data using a recently introduced concept called Generalized Graph Differences (GGD). This allows a general tracker implementation to be specialized to drone videos by training it on the VisDrone dataset. Two modifications to the original GGD is introduced in this paper and a result with an average precision of 23.09 on the test set of VisDrone 2019 was achieved.

KW - Multi target tracking

UR - https://www.scopus.com/pages/publications/85082448559

U2 - 10.1109/ICCVW.2019.00012

DO - 10.1109/ICCVW.2019.00012

M3 - Paper in conference proceeding

AN - SCOPUS:85082448559

SN - 978-1-7281-5024-6

SP - 46

EP - 54

BT - Proceedings - 2019 International Conference on Computer Vision

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019

Y2 - 27 October 2019 through 28 October 2019

ER -

Multi target tracking from drones by learning from generalized graph differences

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Other files and links

Fingerprint

Cite this