Pitching motion matching based on pose similarity using dynamic time warping

Ryohei Osawa, Takaaki Ishikawa, Hiroshi Watanabe

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

Abstract

By comparing multiple videos, it is possible to find the differences between the movements by different players or between motions of the same player in separate situations. To compare multiple motions, it is necessary to match the timing of the motions. However, it is difficult to synchronize the timing since the motion speed and usage of the body varying by player and situation. Therefore, in this paper, we propose a matching method for two pitching motions based on pose similarity using Dynamic Time Warping (DTW). This method enables accurate matching of two pitching motions in many cases.

Original languageEnglish
Title of host publication2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages104-108
Number of pages5
ISBN (Electronic)9781728198026
DOIs
Publication statusPublished - 2020 Oct 13
Event9th IEEE Global Conference on Consumer Electronics, GCCE 2020 - Kobe, Japan
Duration: 2020 Oct 132020 Oct 16

Publication series

Name2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

Conference

Conference9th IEEE Global Conference on Consumer Electronics, GCCE 2020
CountryJapan
CityKobe
Period20/10/1320/10/16

Keywords

  • baseball
  • dynamic time warping
  • motion analysis
  • motion matching
  • video analysis

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Media Technology
  • Instrumentation
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Pitching motion matching based on pose similarity using dynamic time warping'. Together they form a unique fingerprint.

Cite this