MOTCOM: The Multi-Object Tracking Dataset Complexity Metric

Malte Pedersen; Joakim Bruslund Haurum; Patrick Dendorfer; Thomas B. Moeslund

doi:10.1007/978-3-031-20074-8_2

MOTCOM: The Multi-Object Tracking Dataset Complexity Metric

Malte Pedersen^*, Joakim Bruslund Haurum, Patrick Dendorfer, Thomas B. Moeslund

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

2 Citations (Scopus)

Abstract

There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison of datasets, and reduces the conversation on tracker performance to a matter of leader board position. As a remedy, we present the novel MOT dataset complexity metric (MOTCOM), which is a combination of three sub-metrics inspired by key problems in MOT: occlusion, erratic motion, and visual similarity. The insights of MOTCOM can open nuanced discussions on tracker performance and may lead to a wider acknowledgement of novel contributions developed for either less known datasets or those aimed at solving sub-problems.
We evaluate MOTCOM on the comprehensive MOT17, MOT20, and MOTSynth datasets and show that MOTCOM is far better at describing the complexity of MOT sequences compared to the conventional density and number of tracks. Project page at https://vap.aau.dk/motcom

Original language	English
Title of host publication	Computer Vision –- ECCV 2022 : 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII
Editors	Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, Tal Hassner
Publisher	Springer
Publication date	12 Nov 2022
Pages	20-37
ISBN (Print)	978-3-031-20073-1
ISBN (Electronic)	978-3-031-20074-8
DOIs	https://doi.org/10.1007/978-3-031-20074-8_2
Publication status	Published - 12 Nov 2022
Event	European Conference on Computer Vision 2022 - Tel Aviv, Israel Duration: 23 Oct 2022 → 27 Oct 2022 https://eccv2022.ecva.net/

Conference

Conference	European Conference on Computer Vision 2022
Country/Territory	Israel
City	Tel Aviv
Period	23/10/2022 → 27/10/2022
Internet address	https://eccv2022.ecva.net/

Series	Lecture Notes in Computer Science (LNCS)
Volume	13668
ISSN	0302-9743

Access to Document

10.1007/978-3-031-20074-8_2

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Pedersen, M., Haurum, J. B., Dendorfer, P., & Moeslund, T. B. (2022). MOTCOM: The Multi-Object Tracking Dataset Complexity Metric. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Eds.), Computer Vision –- ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII (pp. 20-37). Springer. https://doi.org/10.1007/978-3-031-20074-8_2

Pedersen, Malte ; Haurum, Joakim Bruslund ; Dendorfer, Patrick et al. / MOTCOM: The Multi-Object Tracking Dataset Complexity Metric. Computer Vision –- ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII. editor / Shai Avidan ; Gabriel Brostow ; Moustapha Cissé ; Giovanni Maria Farinella ; Tal Hassner. Springer, 2022. pp. 20-37 (Lecture Notes in Computer Science (LNCS), Vol. 13668).

@inproceedings{9aba1fd259174b54931696c5ae23542f,

title = "MOTCOM: The Multi-Object Tracking Dataset Complexity Metric",

abstract = "There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison of datasets, and reduces the conversation on tracker performance to a matter of leader board position. As a remedy, we present the novel MOT dataset complexity metric (MOTCOM), which is a combination of three sub-metrics inspired by key problems in MOT: occlusion, erratic motion, and visual similarity. The insights of MOTCOM can open nuanced discussions on tracker performance and may lead to a wider acknowledgement of novel contributions developed for either less known datasets or those aimed at solving sub-problems.We evaluate MOTCOM on the comprehensive MOT17, MOT20, and MOTSynth datasets and show that MOTCOM is far better at describing the complexity of MOT sequences compared to the conventional density and number of tracks. Project page at https://vap.aau.dk/motcom",

author = "Malte Pedersen and Haurum, {Joakim Bruslund} and Patrick Dendorfer and Moeslund, {Thomas B.}",

year = "2022",

month = nov,

day = "12",

doi = "10.1007/978-3-031-20074-8_2",

language = "English",

isbn = "978-3-031-20073-1",

series = "Lecture Notes in Computer Science (LNCS)",

publisher = "Springer",

pages = "20--37",

editor = "Shai Avidan and Gabriel Brostow and Moustapha Ciss{\'e} and Farinella, {Giovanni Maria} and Tal Hassner",

booktitle = "Computer Vision –- ECCV 2022",

address = "Germany",

note = "European Conference on Computer Vision 2022 ; Conference date: 23-10-2022 Through 27-10-2022",

url = "https://eccv2022.ecva.net/",

}

Pedersen, M , Haurum, JB, Dendorfer, P & Moeslund, TB 2022, MOTCOM: The Multi-Object Tracking Dataset Complexity Metric. in S Avidan, G Brostow, M Cissé, GM Farinella & T Hassner (eds), Computer Vision –- ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII. Springer, Lecture Notes in Computer Science (LNCS), vol. 13668, pp. 20-37, European Conference on Computer Vision 2022, Tel Aviv, Israel, 23/10/2022. https://doi.org/10.1007/978-3-031-20074-8_2

MOTCOM: The Multi-Object Tracking Dataset Complexity Metric. / Pedersen, Malte ; Haurum, Joakim Bruslund; Dendorfer, Patrick et al.
Computer Vision –- ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII. ed. / Shai Avidan; Gabriel Brostow; Moustapha Cissé; Giovanni Maria Farinella; Tal Hassner. Springer, 2022. p. 20-37 (Lecture Notes in Computer Science (LNCS), Vol. 13668).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - MOTCOM: The Multi-Object Tracking Dataset Complexity Metric

AU - Pedersen, Malte

AU - Haurum, Joakim Bruslund

AU - Dendorfer, Patrick

AU - Moeslund, Thomas B.

PY - 2022/11/12

Y1 - 2022/11/12

N2 - There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison of datasets, and reduces the conversation on tracker performance to a matter of leader board position. As a remedy, we present the novel MOT dataset complexity metric (MOTCOM), which is a combination of three sub-metrics inspired by key problems in MOT: occlusion, erratic motion, and visual similarity. The insights of MOTCOM can open nuanced discussions on tracker performance and may lead to a wider acknowledgement of novel contributions developed for either less known datasets or those aimed at solving sub-problems.We evaluate MOTCOM on the comprehensive MOT17, MOT20, and MOTSynth datasets and show that MOTCOM is far better at describing the complexity of MOT sequences compared to the conventional density and number of tracks. Project page at https://vap.aau.dk/motcom

AB - There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison of datasets, and reduces the conversation on tracker performance to a matter of leader board position. As a remedy, we present the novel MOT dataset complexity metric (MOTCOM), which is a combination of three sub-metrics inspired by key problems in MOT: occlusion, erratic motion, and visual similarity. The insights of MOTCOM can open nuanced discussions on tracker performance and may lead to a wider acknowledgement of novel contributions developed for either less known datasets or those aimed at solving sub-problems.We evaluate MOTCOM on the comprehensive MOT17, MOT20, and MOTSynth datasets and show that MOTCOM is far better at describing the complexity of MOT sequences compared to the conventional density and number of tracks. Project page at https://vap.aau.dk/motcom

U2 - 10.1007/978-3-031-20074-8_2

DO - 10.1007/978-3-031-20074-8_2

M3 - Article in proceeding

SN - 978-3-031-20073-1

T3 - Lecture Notes in Computer Science (LNCS)

SP - 20

EP - 37

BT - Computer Vision –- ECCV 2022

A2 - Avidan, Shai

A2 - Brostow, Gabriel

A2 - Cissé, Moustapha

A2 - Farinella, Giovanni Maria

A2 - Hassner, Tal

PB - Springer

T2 - European Conference on Computer Vision 2022

Y2 - 23 October 2022 through 27 October 2022

ER -

Pedersen M , Haurum JB, Dendorfer P, Moeslund TB. MOTCOM: The Multi-Object Tracking Dataset Complexity Metric. In Avidan S, Brostow G, Cissé M, Farinella GM, Hassner T, editors, Computer Vision –- ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII. Springer. 2022. p. 20-37. (Lecture Notes in Computer Science (LNCS), Vol. 13668). doi: 10.1007/978-3-031-20074-8_2

MOTCOM: The Multi-Object Tracking Dataset Complexity Metric

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Cite this