Prediction of future shot direction using pose and position of tennis player

Tomohiro Shimizu, Ryo Hachiuma, Hideo Saito, Takashi Yoshikawa, Chonho Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a method to predict the future shot direction in a tennis match using pose information and player position. As far as we know, there is no work that deals with such a predictive task, so there is no shot direction dataset as yet. Therefore, using a YouTube tennis match video, we construct an time of impact and shot direction dataset. To reduce annotation costs, we propose a method to automatically label the shot direction. Moreover, we propose a method to predict the future shot direction using the constructed dataset. The shot direction is predicted using LSTM(long short-time memory), from sequential pose information up to the time of impact and the player position. We employ OpenPose to extract the position of skeleton joints. In the experiment, we evaluate the accuracy of shot direction prediction and verify the effectiveness of the proposed method. Since there are no studies that predict future shot direction, we set four baseline methods to evaluate the effectiveness of our proposed method.

Original languageEnglish
Title of host publicationMMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019
PublisherAssociation for Computing Machinery, Inc
Pages59-66
Number of pages8
ISBN (Electronic)9781450369114
DOIs
Publication statusPublished - 2019 Oct 15
Event2nd ACM International Workshop on Multimedia Content Analysis in Sports, MMSports 2019, co-located with ACM Multimedia 2019 - Nice, France
Duration: 2019 Oct 25 → …

Publication series

NameMMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019

Conference

Conference2nd ACM International Workshop on Multimedia Content Analysis in Sports, MMSports 2019, co-located with ACM Multimedia 2019
CountryFrance
CityNice
Period19/10/25 → …

Fingerprint

Labels
Data storage equipment
Costs
Experiments

Keywords

  • Activity recognition in tennis
  • Long short-term memory
  • Shot direction prediction

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software
  • Media Technology

Cite this

Shimizu, T., Hachiuma, R., Saito, H., Yoshikawa, T., & Lee, C. (2019). Prediction of future shot direction using pose and position of tennis player. In MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019 (pp. 59-66). (MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3347318.3355523

Prediction of future shot direction using pose and position of tennis player. / Shimizu, Tomohiro; Hachiuma, Ryo; Saito, Hideo; Yoshikawa, Takashi; Lee, Chonho.

MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019. Association for Computing Machinery, Inc, 2019. p. 59-66 (MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shimizu, T, Hachiuma, R, Saito, H, Yoshikawa, T & Lee, C 2019, Prediction of future shot direction using pose and position of tennis player. in MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019. MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019, Association for Computing Machinery, Inc, pp. 59-66, 2nd ACM International Workshop on Multimedia Content Analysis in Sports, MMSports 2019, co-located with ACM Multimedia 2019, Nice, France, 19/10/25. https://doi.org/10.1145/3347318.3355523
Shimizu T, Hachiuma R, Saito H, Yoshikawa T, Lee C. Prediction of future shot direction using pose and position of tennis player. In MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019. Association for Computing Machinery, Inc. 2019. p. 59-66. (MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019). https://doi.org/10.1145/3347318.3355523
Shimizu, Tomohiro ; Hachiuma, Ryo ; Saito, Hideo ; Yoshikawa, Takashi ; Lee, Chonho. / Prediction of future shot direction using pose and position of tennis player. MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019. Association for Computing Machinery, Inc, 2019. pp. 59-66 (MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019).
@inproceedings{3d92d68fcc204798a89882ac6a8ee315,
title = "Prediction of future shot direction using pose and position of tennis player",
abstract = "In this paper, we propose a method to predict the future shot direction in a tennis match using pose information and player position. As far as we know, there is no work that deals with such a predictive task, so there is no shot direction dataset as yet. Therefore, using a YouTube tennis match video, we construct an time of impact and shot direction dataset. To reduce annotation costs, we propose a method to automatically label the shot direction. Moreover, we propose a method to predict the future shot direction using the constructed dataset. The shot direction is predicted using LSTM(long short-time memory), from sequential pose information up to the time of impact and the player position. We employ OpenPose to extract the position of skeleton joints. In the experiment, we evaluate the accuracy of shot direction prediction and verify the effectiveness of the proposed method. Since there are no studies that predict future shot direction, we set four baseline methods to evaluate the effectiveness of our proposed method.",
keywords = "Activity recognition in tennis, Long short-term memory, Shot direction prediction",
author = "Tomohiro Shimizu and Ryo Hachiuma and Hideo Saito and Takashi Yoshikawa and Chonho Lee",
year = "2019",
month = "10",
day = "15",
doi = "10.1145/3347318.3355523",
language = "English",
series = "MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019",
publisher = "Association for Computing Machinery, Inc",
pages = "59--66",
booktitle = "MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019",

}

TY - GEN

T1 - Prediction of future shot direction using pose and position of tennis player

AU - Shimizu, Tomohiro

AU - Hachiuma, Ryo

AU - Saito, Hideo

AU - Yoshikawa, Takashi

AU - Lee, Chonho

PY - 2019/10/15

Y1 - 2019/10/15

N2 - In this paper, we propose a method to predict the future shot direction in a tennis match using pose information and player position. As far as we know, there is no work that deals with such a predictive task, so there is no shot direction dataset as yet. Therefore, using a YouTube tennis match video, we construct an time of impact and shot direction dataset. To reduce annotation costs, we propose a method to automatically label the shot direction. Moreover, we propose a method to predict the future shot direction using the constructed dataset. The shot direction is predicted using LSTM(long short-time memory), from sequential pose information up to the time of impact and the player position. We employ OpenPose to extract the position of skeleton joints. In the experiment, we evaluate the accuracy of shot direction prediction and verify the effectiveness of the proposed method. Since there are no studies that predict future shot direction, we set four baseline methods to evaluate the effectiveness of our proposed method.

AB - In this paper, we propose a method to predict the future shot direction in a tennis match using pose information and player position. As far as we know, there is no work that deals with such a predictive task, so there is no shot direction dataset as yet. Therefore, using a YouTube tennis match video, we construct an time of impact and shot direction dataset. To reduce annotation costs, we propose a method to automatically label the shot direction. Moreover, we propose a method to predict the future shot direction using the constructed dataset. The shot direction is predicted using LSTM(long short-time memory), from sequential pose information up to the time of impact and the player position. We employ OpenPose to extract the position of skeleton joints. In the experiment, we evaluate the accuracy of shot direction prediction and verify the effectiveness of the proposed method. Since there are no studies that predict future shot direction, we set four baseline methods to evaluate the effectiveness of our proposed method.

KW - Activity recognition in tennis

KW - Long short-term memory

KW - Shot direction prediction

UR - http://www.scopus.com/inward/record.url?scp=85075726640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075726640&partnerID=8YFLogxK

U2 - 10.1145/3347318.3355523

DO - 10.1145/3347318.3355523

M3 - Conference contribution

AN - SCOPUS:85075726640

T3 - MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019

SP - 59

EP - 66

BT - MMSports 2019 - Proceedings of the 2nd International Workshop on Multimedia Content Analysis in Sports, co-located with MM 2019

PB - Association for Computing Machinery, Inc

ER -