Measurement and Analysis of Sport Climbing using Vision and Force Information

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K11468
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 59020:Sports sciences-related
• Research Institution: Kyushu University
• Principal Investigator: Kawamura Akihiro 九州大学, システム情報科学研究院, 准教授 (60706555)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: 運動計測 / スポーツクライミング / 姿勢推定 / RGBDセンサ / ICP

Outline of Final Research Achievements

In this study, we conducted motion measurement using single viewpoint RGBD images and force measurement using force sensors. For the person pose estimation, we proposed a highly accurate and robust 3D person pose estimation method from a single viewpoint by combining 2D posture estimation using RGB images and model fitting using ICP technique between distance images and the human shape model.
Using this method and a force sensor, we conducted an experiment to simultaneously measure the posture of a climber and the force information applied to holds in an actual climbing gym, and confirmed the effectiveness of the system.

Free Research Field

スポーツ科学

Academic Significance and Societal Importance of the Research Achievements

スポーツクライミングにおける従来の動作計測では，複数台のカメラを用いた非常に高価なモーションキャプチャシステムによる計測が主であった．これに対して本研究では，一台のRGBDカメラによる単視点画像を用いた動作計測手法を提案し，省スペースかつ安価な動作計測システムを実現した．この成果によって，動作計測システムを設置できる壁の形状，クライミングジムの幅が広がり，将来的に多くの計測データの獲得や多様な動作の解析につながることが期待できる．