<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>As Internet technology rapidly evolves, it significantly enhances the informationization of physical education. This paper proposes the implementation of the Openpose bone tracking algorithm to improve how students master movements in badminton training. By leveraging a convolutional neural network (VGG) to create skeleton maps, the algorithm accurately predicts body postures by examining the user’s center of gravity shifts and limb angle differences. These predictions allow for effective comparative correction of movements. To achieve multi-target action recognition, this paper introduces the SLIC algorithm, which is based on the Openpose algorithm and corrects and repairs action nodes that were incorrectly recognized to improve recognition accuracy. In the teaching experiment test for students of badminton elective class in S college, the retention rate of picking skills of the experimental group of students on the 35th day after the technical training was 101%, which indicated that the mastery of the movement skills was more solid. In terms of comprehensive scores, the average score of the experimental group’s attainment was 2.489 points higher than that of the control group, and the average score of the technical evaluation was 5.885 points higher than that of the control group.</p>
</abstract>

As Internet technology rapidly evolves, it significantly enhances the informationization of physical education. This paper proposes the implementation of the Openpose bone tracking algorithm to improve how students master movements in badminton training. By leveraging a convolutional neural network (VGG) to create skeleton maps, the algorithm accurately predicts body postures by examining the user’s center of gravity shifts and limb angle differences. These predictions allow for effective comparative correction of movements. To achieve multi-target action recognition, this paper introduces the SLIC algorithm, which is based on the Openpose algorithm and corrects and repairs action nodes that were incorrectly recognized to improve recognition accuracy. In the teaching experiment test for students of badminton elective class in S college, the retention rate of picking skills of the experimental group of students on the 35th day after the technical training was 101%, which indicated that the mastery of the movement skills was more solid. In terms of comprehensive scores, the average score of the experimental group’s attainment was 2.489 points higher than that of the control group, and the average score of the technical evaluation was 5.885 points higher than that of the control group.

Application and Practice of Motion Capture Technology in Badminton Teaching

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Application and Practice of Motion Capture Technology in Badminton Teaching"}

As Internet technology rapidly evolves, it significantly enhances the informationization of physical education. This paper proposes the implementation of the...

Application and Practice of Motion Capture Technology in Badminton Teaching

Online veröffentlicht: 22. Mai 2024

Seitenbereich: -

Eingereicht: 02. Feb. 2024

Akzeptiert: 03. Apr. 2024

DOI: https://doi.org/10.2478/amns-2024-1150

Schlüsselwörter
Open pose, VGG, SLIC, Motion capture, Badminton teaching

© 2024 Le Yu, et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Application and Practice of Motion Capture Technology in Badminton Teaching

Online veröffentlicht: 22. Mai 2024

Seitenbereich: -

Eingereicht: 02. Feb. 2024

Akzeptiert: 03. Apr. 2024

DOI: https://doi.org/10.2478/amns-2024-1150

SchlüsselwörterOpen pose, VGG, SLIC, Motion capture, Badminton teaching

© 2024 Le Yu, et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Open pose, VGG, SLIC, Motion capture, Badminton teaching