Author(s)

Marina Mikami¹, Noriyuki Kida^2*

¹Graduate School of Science and Technology, Kyoto Institute of Technology, Kyoto, Japan.
²Faculty of Arts and Sciences, Kyoto Institute of Technology, Kyoto, Japan.

In this study, we sought to reveal and evaluate the degree of similarity between individuals and within the same group of individuals when they perform the same movement. The methodology used was that of selecting a panel of participants, 38 normal healthy adults ranging in age from 10 to 30 years. Subsequently, we carried out the experiment by performing the movements while capturing videos using a smartphone. The two-dimensional coordinates of each joint were obtained for videos obtained using marker less motion capture software. The results obtained allowed for a cluster analysis using five time series variables: 1) vertical head movement and 2) lateral limb movement. These time series were normalized by a total time, in order to create a typology of jumping movements. 136 series of movies were obtained. After checking the movies, 115 series revealed errors such as misrecognition. These series were excluded from the analysis. The remaining 21 series had data available for analysis. Cluster analysis was performed on the 21 sets of motion data, which could be classified into seven clusters based on the shape of the dendrogram.

Automation, Remote, Cluster Analysis

Mikami, M. and Kida, N. (2023) Categorizing Rhythmic Jumping Motion Using Motion Capture without Markers. Advances in Physical Education, 13, 93-105. doi: 10.4236/ape.2023.132009.