Jamcen: A Gamified Fitness System Using Real-Time MediaPipe Pose Estimation with Rule-Based Movement Recognition and User Evaluation
Document Types
Poster Presentation
Research Theme (for Paper Presentation and Poster Presentation submissions only)
Computer and Software Technology, and Robotics (CSR)
School Name
Signal Village National High School
Track or Strand
Science, Technology, Engineering, and Mathematics (STEM)
Research Advisor (Last Name, First Name, Middle Initial)
Sevilleno, Jayven Ocray
Start Date
25-6-2026 10:30 AM
End Date
25-6-2026 12:00 PM
Zoom Link/ Room Assignment
DLSU Laguna Campus (In-person) - John Gokongwei, Jr. Innovation Center (JGIC)
Abstract/Executive Summary
The increasing demand for engaging and accessible fitness solutions has driven the integration of digital technologies with physical activity. However, many existing systems rely on complex machine learning models or specialized hardware, limiting their accessibility and interpretability. This study presents Jamcen, a gamified fitness system and framework that utilizes real-time MediaPipe pose estimation and rule-based movement recognition to transform physical exercises into interactive gameplay. The objective of this study is to develop and evaluate a system capable of accurately detecting user movements while sustaining engagement through gamification without relying on computationally intensive models. The system was implemented as a mobile and web-based application integrating camera-based pose estimation, threshold-based movement interpretation, and game-driven interaction. Two exercise-based games, ZomJack and Splashy Fish, were developed to represent full-body and upper-body movement paradigms. A mixed-method evaluation was conducted, including quantitative assessment of movement detection accuracy and user-based evaluation of usability and engagement. Results show that the system achieved high detection accuracy of 99.26% for jumping jacks and 99.31% for lateral arms raise movements. User evaluation yielded strong ratings in ease of use (5.0/5.0), engagement (4.6/5.0), clarity of feedback (4.6/5.0), and responsiveness (4.5/5.0). Gameplay performance metrics further indicate consistent user interaction and sustained participation. These findings demonstrate that real-time pose estimation combined with rule-based logic and gamification provides an effective, interpretable, and accessible approach to promoting physical activity. The Jamcen system contributes to the development of user-centered, AI-assisted interactive fitness applications that bridge physical exercise and digital engagement.
Keywords
gamified fitness; pose estimation; MediaPipe; rule-based movement recognition; human-computer interaction
Initial Consent for Publication
yes
Statement of Originality
yes
Jamcen: A Gamified Fitness System Using Real-Time MediaPipe Pose Estimation with Rule-Based Movement Recognition and User Evaluation
The increasing demand for engaging and accessible fitness solutions has driven the integration of digital technologies with physical activity. However, many existing systems rely on complex machine learning models or specialized hardware, limiting their accessibility and interpretability. This study presents Jamcen, a gamified fitness system and framework that utilizes real-time MediaPipe pose estimation and rule-based movement recognition to transform physical exercises into interactive gameplay. The objective of this study is to develop and evaluate a system capable of accurately detecting user movements while sustaining engagement through gamification without relying on computationally intensive models. The system was implemented as a mobile and web-based application integrating camera-based pose estimation, threshold-based movement interpretation, and game-driven interaction. Two exercise-based games, ZomJack and Splashy Fish, were developed to represent full-body and upper-body movement paradigms. A mixed-method evaluation was conducted, including quantitative assessment of movement detection accuracy and user-based evaluation of usability and engagement. Results show that the system achieved high detection accuracy of 99.26% for jumping jacks and 99.31% for lateral arms raise movements. User evaluation yielded strong ratings in ease of use (5.0/5.0), engagement (4.6/5.0), clarity of feedback (4.6/5.0), and responsiveness (4.5/5.0). Gameplay performance metrics further indicate consistent user interaction and sustained participation. These findings demonstrate that real-time pose estimation combined with rule-based logic and gamification provides an effective, interpretable, and accessible approach to promoting physical activity. The Jamcen system contributes to the development of user-centered, AI-assisted interactive fitness applications that bridge physical exercise and digital engagement.
https://animorepository.dlsu.edu.ph/conf_shsrescon/2026/BoA_Poster_CSR/1