Preventing the players health using Device free method as Full body Interactive Game Controller through OpenCV and MediaPipe

Nowadays , children were exposed to multiple games for long time which leads to several healthcomplication. In order to manage those challenges, many game application requires gestures and motions of the humanbody to play the game which minimize the health deterioration of the children with increased accuracy. Especiallysignificant advancement has been made in game application through device free method on using various pose of theplayer for controlling the game in recent years without any devices to recognize it. However those application werefocused only to the specific poses even those advancement could not able to give complete health benefit. In order toprovide complete health benefits to the children playing games, entire body poses has to be gathered for the gamecontrolling using device free methods. In this paper, a new deep learning model is designed for full body posedetection has been designed towards real time tracking of the children on utilizing their body posture and bodylandmarks to control game operations through opencv and MediaPipe. MediaPipe pose detection model on processingthe acquired videos without devices. Video were processed using openCV and MediaPipe. MediaPipe performmachine learning task like pose estimation which is able to extract the human movement like arm gestures, leg lifts ,squats and jumps on relative difference between body parts as feature points. These feature points are classified toprovide input for game controlling . Particular specific movements such as arm and leg extension provides effectivecontrolling operations. Finally key mapping for different games enhances game play through full body interaction.The controller supports single and multi-player setups, offering a unique and immersive gaming experience throughbody movement-based inputs. Experimental analysis of the proposed model proves that pose detection based fullybody game controllers represents immense potential in generating interest in the applications. Furthermore, the fullbody engagement aspect of these games could also play a role in promoting physical activity as a regular habit.

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2025-08-10
DOI
https://doi.org/10.5281/zenodo.16788744
Primary Topic
Human Pose and Action Recognition
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Preventing the players health using Device free method as Full body Interactive Game Controller through OpenCV and MediaPipe

Zenodo (CERN European Organization for Nuclear Research)
Human Pose and Action Recognition
article

Preventing the players health using Device free method as Full body Interactive Game Controller through OpenCV and MediaPipe

article en

Abstract

Nowadays , children were exposed to multiple games for long time which leads to several healthcomplication. In order to manage those challenges, many game application requires gestures and motions of the humanbody to play the game which minimize the health deterioration of the children with increased accuracy. Especiallysignificant advancement has been made in game application through device free method on using various pose of theplayer for controlling the game in recent years without any devices to recognize it. However those application werefocused only to the specific poses even those advancement could not able to give complete health benefit. In order toprovide complete health benefits to the children playing games, entire body poses has to be gathered for the gamecontrolling using device free methods. In this paper, a new deep learning model is designed for full body posedetection has been designed towards real time tracking of the children on utilizing their body posture and bodylandmarks to control game operations through opencv and MediaPipe. MediaPipe pose detection model on processingthe acquired videos without devices. Video were processed using openCV and MediaPipe. MediaPipe performmachine learning task like pose estimation which is able to extract the human movement like arm gestures, leg lifts ,squats and jumps on relative difference between body parts as feature points. These feature points are classified toprovide input for game controlling . Particular specific movements such as arm and leg extension provides effectivecontrolling operations. Finally key mapping for different games enhances game play through full body interaction.The controller supports single and multi-player setups, offering a unique and immersive gaming experience throughbody movement-based inputs. Experimental analysis of the proposed model proves that pose detection based fullybody game controllers represents immense potential in generating interest in the applications. Furthermore, the fullbody engagement aspect of these games could also play a role in promoting physical activity as a regular habit.

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 56%
Human Pose and Action Recognition
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.