A SYSTEM FOR AUTOMATIC AND FAST GYMNASTICS POSE ESTIMATION AND KEY FRAME IDENTIFICATION

Authors

Ilias Masmoudi, Machine Learning and Data Analytics (MaD) Lab, Faculty of Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, GermanyFollow
Johannes Link, Machine Learning and Data Analytics (MaD) Lab, Faculty of Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
Sebastian Möck, Department of Exercise Science, Olympic Training and Testing Center of Hessen, Otto-Fleck-Schneise 4, Frankfurt, Germany
Petra Nissinen, Department of Exercise Science, Olympic Training and Testing Center of Hessen, Otto-Fleck-Schneise 4, Frankfurt, Germany
Anne Koelewijn, Machine Learning and Data Analytics (MaD) Lab, Faculty of Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany

Category

Sports Performance & Elite Sports

Document Type

Paper

Abstract

In artistic gymnastics, performance analysis tools that provide immediate feedback to athletes and coaches are key to optimizing performance. Therefore, we developed a system that provides direct video feedback and automatically identifies key frames relevant to achieve high performance. This system estimates the gymnast’s two-dimensional (2D) and three-dimensional pose from a single-view video and uses a long short-term memory (LSTM) network to identify key frames, in which contact with the ground or an apparatus starts or ends. We compared three 2D pose estimation algorithms and found that MoveNet yielded the highest accuracy, being able to detect 84% of the joints accurately. The LSTM network detected the key frames with a 97% F1 score. In conclusion, our system provides direct video feedback to gymnasts and coaches relevant performance parameters.

Recommended Citation

Masmoudi, Ilias; Link, Johannes; Möck, Sebastian; Nissinen, Petra; and Koelewijn, Anne (2024) "A SYSTEM FOR AUTOMATIC AND FAST GYMNASTICS POSE ESTIMATION AND KEY FRAME IDENTIFICATION," ISBS Proceedings Archive: Vol. 42: Iss. 1, Article 171.
Available at: https://commons.nmu.edu/isbs/vol42/iss1/171