Skill Analysis with Time Series Image Data

TL;DR

This paper analyzes table tennis skills using time series image data and data mining methods, identifying internal models of skillfulness and discussing skill improvement strategies without relying on body models.

Contribution

It introduces a novel approach to skill analysis using only high-speed video data and data mining, avoiding the need for body modeling.

Findings

Identified internal models for forehand stroke skillfulness.

Analyzed mono and meta-functional skills for skill improvement.

Demonstrated effectiveness of data mining methods on video-derived data.

Abstract

We present a skill analysis with time series image data using data mining methods, focused on table tennis. We do not use body model, but use only hi-speed movies, from which time series data are obtained and analyzed using data mining methods such as C4.5 and so on. We identify internal models for technical skills as evaluation skillfulness for the forehand stroke of table tennis, and discuss mono and meta-functional skills for improving skills.