Development and implementation of a MediaPipe-based AI teaching-learning model in school physical education for...

Artificial intelligence (AI) technologies are increasingly used in school physical education (PE) to provide real-time feedback and support instruction that promotes youth physical activity and health. However, many AI applications remain top-down and expert-driven, focusing on technical validation in controlled settings and paying little attention to everyday school contexts or the needs of lower-fitness students. This study aimed to develop and implement a MediaPipe-based AI teaching-learning program for health-oriented middle school PE.

A participatory action research (PAR) design with rapid prototyping was conducted over three months in one public middle school. PE teachers and 9th-grade students participated as co-researchers and co-developers. A web-based program using MediaPipe Pose was iteratively designed to recognize selected fitness movements and provide immediate visual and auditory feedback, with QR-code access and automatic logging. Data from semi-structured group interviews, observations, teachers' reflective journals, and student-created artifacts were analyzed using thematic analysis.

Across three PAR cycles, the prototype evolved from a simple elbow-angle counter into a system that incorporated body alignment, tracking for isometric exercises, multimodal feedback, and automatic data recording. Teachers used the program to design lesson-specific recognition rules, monitor students' exercise participation, and support individual growth. Students deepened their understanding of exercise principles and engaged in computational thinking while experimenting with movements and refining feedback conditions.

A participatory, school-based approach enabled MediaPipe-based pose estimation to be reconfigured into a pedagogically meaningful, health-oriented program for middle school PE, suggesting that AI-supported PE can contribute to more inclusive, data-supported school health promotion.