Presentation 2015-01-31
Karate-kata Exercise Assist Method Using Video Image Retrieval Based on 3D Point Cloud Processing
Kazumoto TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is known that sport skill learning is facilitated by observing images of photographs of movements of trainees themselves. However, observation learning of images is not used routinely at ordinary sports practice sites. The main hindrance blocking the wider use of images is that "it is troublesome to detect an objective scene from image files". This study was conducted to establish a technology for the retrieval of objective scenes from images of body action based on three-dimensional point cloud processing and to propose an assist method for observation learning using this technology. In this study, coaching of karate-kata is emphasized, along with automatic retrieval of images of karate-kata and karate-kata practice assistance methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Learning by Observation / Depth Sensor / Three-dimensional Point Cloud / Karate Kata / Momentlinvariants
Paper # ET2014-77
Date of Issue

Conference Information
Committee ET
Conference Date 2015/1/24(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) Karate-kata Exercise Assist Method Using Video Image Retrieval Based on 3D Point Cloud Processing
Sub Title (in English)
Keyword(1) Learning by Observation
Keyword(2) Depth Sensor
Keyword(3) Three-dimensional Point Cloud
Keyword(4) Karate Kata
Keyword(5) Momentlinvariants
1st Author's Name Kazumoto TANAKA
1st Author's Affiliation Faculty of Engineering, Kinki University()
Date 2015-01-31
Paper # ET2014-77
Volume (vol) vol.114
Number (no) 441
Page pp.pp.-
#Pages 4
Date of Issue