SPEED21: Speed Climbing Motion Dataset

D 2021

SPEED21: Speed Climbing Motion Dataset

ELIÁŠ, Petr, Veronika ŠKVARLOVÁ and Pavel ZEZULA

Basic information

Original name

SPEED21: Speed Climbing Motion Dataset

Authors

ELIÁŠ, Petr (203 Czech Republic, belonging to the institution), Veronika ŠKVARLOVÁ (703 Slovakia, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, guarantor, belonging to the institution)

Edition

New York, NY, United States, MMSports'21: Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports, p. 43-50, 8 pp. 2021

Publisher

Association for Computing Machinery

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

References:

URL

RIV identification code

RIV/00216224:14330/21:00129011

Organization unit

Faculty of Informatics

ISBN

978-1-4503-8670-8

DOI

http://dx.doi.org/10.1145/3475722.3482795

Keywords in English

speed climbing; sports dataset; 2d skeleton series; k-nn search; similarity

Abstract

V originále

With the recent advances in computer vision and deep learning, the research interest in video-based and skeleton-based sports analysis is growing. Also, speed climbing as a sport is on the rise, being included as an Olympic sport in Tokyo 2020. This work aims to connect both of these worlds. First, a dataset of 362 speed climbing performances is provided for the community of domain experts and practitioners in human motion understanding and sports analysis. The dataset annotates pre-segmented performances of 55 world elite athletes in the form of 2D skeleton sequences extracted from world competition events videos. Secondly, a high descriptiveness and usability of 2D skeleton data is demonstrated in the search scenario that matches climbers by the similarities in their climbing style with high accuracy. The high k-NN search precision above 90 % is achieved by a synergic combination of suitable representation with a semi-dependent variant of Dynamic Time Warping (DTW). The proposed DTW variant computes distances separately across individual semantic body parts (e.g., hands and feet) whose atoms (joints or angles) are wired together for the temporal alignment.

Links

GA19-02033S, research and development project

Name: Vyhledávání, analytika a anotace datových toků lidských pohybů

Investor: Czech Science Foundation

Citovat

ELIÁŠ, Petr, Veronika ŠKVARLOVÁ and Pavel ZEZULA. SPEED21: Speed Climbing Motion Dataset. Online. In Rainer Lienhart,Thomas B. Moeslund, Hideo Saito. MMSports'21: Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports. New York, NY, United States: Association for Computing Machinery, 2021, p. 43-50. ISBN 978-1-4503-8670-8. Available from: https://dx.doi.org/10.1145/3475722.3482795.

@inproceedings{1808457,
   author = {Eliáš, Petr and Škvarlová, Veronika and Zezula, Pavel},
   address = {New York, NY, United States},
   booktitle = {MMSports'21: Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports},
   doi = {http://dx.doi.org/10.1145/3475722.3482795},
   editor = {Rainer Lienhart,Thomas B. Moeslund, Hideo Saito},
   keywords = {speed climbing; sports dataset; 2d skeleton series; k-nn search; similarity},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {New York, NY, United States},
   isbn = {978-1-4503-8670-8},
   pages = {43-50},
   publisher = {Association for Computing Machinery},
   title = {SPEED21: Speed Climbing Motion Dataset},
   url = {https://dl.acm.org/doi/10.1145/3475722.3482795},
   year = {2021}
}

TY  - JOUR
ID  - 1808457
AU  - Eliáš, Petr - Škvarlová, Veronika - Zezula, Pavel
PY  - 2021
TI  - SPEED21: Speed Climbing Motion Dataset
PB  - Association for Computing Machinery
CY  - New York, NY, United States
SN  - 9781450386708
KW  - speed climbing
KW  - sports dataset
KW  - 2d skeleton series
KW  - k-nn search
KW  - similarity
UR  - https://dl.acm.org/doi/10.1145/3475722.3482795
N2  - With the recent advances in computer vision and deep learning, the research interest in video-based and skeleton-based sports analysis is growing. Also, speed climbing as a sport is on the rise, being included as an Olympic sport in Tokyo 2020. This work aims to connect both of these worlds. First, a dataset of 362 speed climbing performances is provided for the community of domain experts and practitioners in human motion understanding and sports analysis. The dataset annotates pre-segmented performances of 55 world elite athletes in the form of 2D skeleton sequences extracted from world competition events videos. Secondly, a high descriptiveness and usability of 2D skeleton data is demonstrated in the search scenario that matches climbers by the similarities in their climbing style with high accuracy. The high k-NN search precision above 90 % is achieved by a synergic combination of suitable representation with a semi-dependent variant of Dynamic Time Warping (DTW). The proposed DTW variant computes distances separately across individual semantic body parts (e.g., hands and feet) whose atoms (joints or angles) are wired together for the temporal alignment.
ER  -

ELIÁŠ, Petr, Veronika ŠKVARLOVÁ and Pavel ZEZULA. SPEED21: Speed Climbing Motion Dataset. Online. In Rainer Lienhart,Thomas B. Moeslund, Hideo Saito. \textit{MMSports'21: Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports}. New York, NY, United States: Association for Computing Machinery, 2021, p.~43-50. ISBN~978-1-4503-8670-8. Available from: https://dx.doi.org/10.1145/3475722.3482795.

Detailed Information on Publication Record