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

<p>In recent years, the deployment of computer vision technology across various applications for recognizing human posture and behavior has significantly advanced the field of sports training research and development. This study introduces the application of the OpenPose algorithm to estimate badminton training postures and identify critical points on the human skeleton. Following the identification of these points, we construct a human posture estimation model, which involves preprocessing the data through steps such as detecting key human points, removing redundant points, establishing a two-dimensional coordinate system, and substituting missing key points. The implementation of this algorithm is hosted on a cloud computing platform. Subsequently, we collect relevant data and execute feature extraction using the coordinate normalization technique. This paper analyzes the training postures and suggests an optimization strategy for the allocation of training resources aimed at enhancing the efficacy of training plans. The application of these optimized training schemes resulted in significant improvements in the players’ badminton skills, particularly in forehand high ball hits and serves. Notably, in the experimental tests of forehand high ball hits and serves, the skill levels were recorded at 16.56 and 15.29, respectively—outperforming the control group’s scores of 14.98 and 13.65.</p>
</abstract>

In recent years, the deployment of computer vision technology across various applications for recognizing human posture and behavior has significantly advanced the field of sports training research and development. This study introduces the application of the OpenPose algorithm to estimate badminton training postures and identify critical points on the human skeleton. Following the identification of these points, we construct a human posture estimation model, which involves preprocessing the data through steps such as detecting key human points, removing redundant points, establishing a two-dimensional coordinate system, and substituting missing key points. The implementation of this algorithm is hosted on a cloud computing platform. Subsequently, we collect relevant data and execute feature extraction using the coordinate normalization technique. This paper analyzes the training postures and suggests an optimization strategy for the allocation of training resources aimed at enhancing the efficacy of training plans. The application of these optimized training schemes resulted in significant improvements in the players’ badminton skills, particularly in forehand high ball hits and serves. Notably, in the experimental tests of forehand high ball hits and serves, the skill levels were recorded at 16.56 and 15.29, respectively—outperforming the control group’s scores of 14.98 and 13.65.

The Role of Cloud Computing Platform in Improving Resource Allocation Efficiency of Training for Male Badminton Players

Applied Mathematics and Nonlinear Sciences

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

In recent years, the deployment of computer vision technology across various applications for recognizing human posture and behavior has significantly advanced...

The Role of Cloud Computing Platform in Improving Resource Allocation Efficiency of Training for Male Badminton Players

Publicado en línea: 05 jul 2024

Páginas: -

Recibido: 22 feb 2024

Aceptado: 17 may 2024

DOI: https://doi.org/10.2478/amns-2024-1597

Palabras clave
Badminton training, OpenPose algorithm, Human posture estimation model, Cloud computing platform

© 2024 Fei Gao et al., published by Sciendo

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

The Role of Cloud Computing Platform in Improving Resource Allocation Efficiency of Training for Male Badminton Players

Publicado en línea: 05 jul 2024

Páginas: -

Recibido: 22 feb 2024

Aceptado: 17 may 2024

DOI: https://doi.org/10.2478/amns-2024-1597

Palabras claveBadminton training, OpenPose algorithm, Human posture estimation model, Cloud computing platform

© 2024 Fei Gao et al., published by Sciendo

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

Palabras clave
Badminton training, OpenPose algorithm, Human posture estimation model, Cloud computing platform