Presentation 2015-03-14
Similarity Evaluation Methods of Sports Form by Using Depth Sensor
Masataka KANEKO, Hiroaki KUDO, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Noboru OHNISHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper shows similarity evaluation methods for detecting the motion difference between individuals to teach sports form. First, we capture time series data of joint positions by using Kinect (which is a motion sensing devices by Microsoft). Motion duration of sports varies from a person to a person. So we use the DP matching to make two motion lengths equal. We calculate correlation coefficients of joints quaternions every one second between quaternions. In the proposed method, we calculate vectors connecting joints (direction vector) at each frame from the time warped data, and evaluate them by using Euclidean distance at the same frame. We have conducted experiments in Karatedo motions and obtained that the proposed method could detect detailed difference between motions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) sports form teaching / DP matching / quaternion correlation coefficient / direction vector
Paper # ET2014-109
Date of Issue

Conference Information
Committee ET
Conference Date 2015/3/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Educational Technology (ET)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Similarity Evaluation Methods of Sports Form by Using Depth Sensor
Sub Title (in English)
Keyword(1) sports form teaching
Keyword(2) DP matching
Keyword(3) quaternion correlation coefficient
Keyword(4) direction vector
1st Author's Name Masataka KANEKO
1st Author's Affiliation ()
2nd Author's Name Hiroaki KUDO
2nd Author's Affiliation Department of Information Science, Nagoya University
3rd Author's Name Tetsuya MATSUMOTO
3rd Author's Affiliation Department of Information Science, Nagoya University
4th Author's Name Yoshinori TAKEUCHI
4th Author's Affiliation Department of Informatics, Daido University
5th Author's Name Noboru OHNISHI
5th Author's Affiliation Department of Information Science, Nagoya University
Date 2015-03-14
Paper # ET2014-109
Volume (vol) vol.114
Number (no) 513
Page pp.pp.-
#Pages 6
Date of Issue