Home / Current Issue / Paper 1715838
Smart Recovery: A Markerless Computer Vision Platform for Gamified Neuro-Rehabilitation
Subject area: Science,Engineering and Technology · Area of research: Healthcare and Technology
DOI: https://doi.org/10.64388/IREV9I10-1715838
Abstract
Effective neuro-rehabilitation relies on high- repetition, task-oriented exercises, yet traditional clinical interventions are often hindered by poor scalability and a reliance on expensive, specialized hardware that limits home use. To bridge this gap, we developed Smart Recovery, an AI-driven platform that utilizes standard web cameras and real-time pose estimation to provide high-fidelity kinematic tracking without the need for wearable sensors or VR headsets. Our validation within a simulated framework indicates that the system’s gamified biofeedback significantly enhances user motivation, maintaining a precise coordinate error margin of Edist = 3.12±0.45 pixels with engagement metrics reaching statistical significance (p < 0.001).
Keywords
Neuro-rehabilitation, Gamification, Motion Detection, AI-ML Integration, Computer Vision, Motor Analytics
How to cite this paper
@article{1715838,
author = {Shubhangi Kashid, Shravani Kulkarni, Shwetal More, Toshi Jain, Dr. Shashank Joshi},
title = {Smart Recovery: A Markerless Computer Vision Platform for Gamified Neuro-Rehabilitation},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {4392-4399},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1715838.pdf},
abstract = {Effective neuro-rehabilitation relies on high- repetition, task-oriented exercises, yet traditional clinical interventions are often hindered by poor scalability and a reliance on expensive, specialized hardware that limits home use. To bridge this gap, we developed Smart Recovery, an AI-driven platform that utilizes standard web cameras and real-time pose estimation to provide high-fidelity kinematic tracking without the need for wearable sensors or VR headsets. Our validation within a simulated framework indicates that the system’s gamified biofeedback significantly enhances user motivation, maintaining a precise coordinate error margin of Edist = 3.12±0.45 pixels with engagement metrics reaching statistical significance (p < 0.001).},
keywords = {Neuro-rehabilitation, Gamification, Motion Detection, AI-ML Integration, Computer Vision, Motor Analytics},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1715838}
}