<p>Accurate measurement of range of motion (ROM) during physical rehabilitation is traditionally achieved using goniometers or multi-camera, marker-based motion capture systems. The latter, while highly accurate, require specialised laboratory infrastructure, are costly, and are unsuitable for home-based use. There is growing interest in markerless, camera-based alternatives that leverage artificial intelligence (AI) for joint angle estimation. This study presents a preliminary proof-of-concept evaluation of a hybrid AI vision system, combining the MediaPipe Pose framework (version 0.8.9.1, Full model variant) with a Mamdani-type fuzzy inference system, for joint angle estimation and exercise repetition counting using a single consumer-grade camera. Fourteen healthy adult rehabilitation staff members performed three exercises (elbow flexion, knee extension, and hip external rotation) simultaneously recorded by the proposed AI system and by a reference optical motion capture system (C-Motion Visual3D™, 14 calibrated infrared cameras, 53 retro-reflective markers). Reliability was assessed using two-way mixed-effects intraclass correlation coefficients (ICC<InlineEquation ID="IEq1"><EquationSource Format="TEX">\(_{2,1}\)</EquationSource></InlineEquation>) with absolute agreement. Individual-measure ICC values ranged from poor to good across joints and conditions (range: 0.005–0.68). The highest reliability was observed for the right hip external rotation ROM (individual ICC <InlineEquation ID="IEq2"><EquationSource Format="TEX">\(=~0.68\)</EquationSource></InlineEquation>; average ICC <InlineEquation ID="IEq3"><EquationSource Format="TEX">\(=~0.81\)</EquationSource></InlineEquation>, 95% CI: 0.63–0.89). Several measures showed poor reliability, including the right elbow flexion ROM (individual ICC <InlineEquation ID="IEq4"><EquationSource Format="TEX">\(=~0.21\)</EquationSource></InlineEquation>) and the minimum angle of the left hip external rotation (individual ICC <InlineEquation ID="IEq5"><EquationSource Format="TEX">\(=~0.005\)</EquationSource></InlineEquation>). Confidence intervals were wide throughout. This proof of concept demonstrates that a single-camera AI system can capture general trends in joint angles during simple rehabilitation exercises in healthy adults under controlled conditions. However, reliability is inconsistent and frequently poor, and the system has not been evaluated in patient populations with pathological movement patterns. These findings do not support clinical deployment at this stage. Substantial further development and validation in patient cohorts are required before clinical or home-based use can be considered.</p>

A hybrid AI vision model for single-camera tracking of rehabilitation exercises: a proof of concept in clinical settings

期刊论文
出版模式：

开放获取
发表日期：

2026年5月29日

查看全文

Utpal Chandra Das,
Ngoc Thien Le,
Timporn Vitoonpong,
Chatkaew Pongmala,
Chalermdej Prapinpairoj,
Kawee Anannub,
Pasu Kaewplung,
Surachai Chaitusaney,
Watit Benjapolakul

摘要

Accurate measurement of range of motion (ROM) during physical rehabilitation is traditionally achieved using goniometers or multi-camera, marker-based motion capture systems. The latter, while highly accurate, require specialised laboratory infrastructure, are costly, and are unsuitable for home-based use. There is growing interest in markerless, camera-based alternatives that leverage artificial intelligence (AI) for joint angle estimation. This study presents a preliminary proof-of-concept evaluation of a hybrid AI vision system, combining the MediaPipe Pose framework (version 0.8.9.1, Full model variant) with a Mamdani-type fuzzy inference system, for joint angle estimation and exercise repetition counting using a single consumer-grade camera. Fourteen healthy adult rehabilitation staff members performed three exercises (elbow flexion, knee extension, and hip external rotation) simultaneously recorded by the proposed AI system and by a reference optical motion capture system (C-Motion Visual3D™, 14 calibrated infrared cameras, 53 retro-reflective markers). Reliability was assessed using two-way mixed-effects intraclass correlation coefficients (ICC\(_{2,1}\)) with absolute agreement. Individual-measure ICC values ranged from poor to good across joints and conditions (range: 0.005–0.68). The highest reliability was observed for the right hip external rotation ROM (individual ICC \(=~0.68\); average ICC \(=~0.81\), 95% CI: 0.63–0.89). Several measures showed poor reliability, including the right elbow flexion ROM (individual ICC \(=~0.21\)) and the minimum angle of the left hip external rotation (individual ICC \(=~0.005\)). Confidence intervals were wide throughout. This proof of concept demonstrates that a single-camera AI system can capture general trends in joint angles during simple rehabilitation exercises in healthy adults under controlled conditions. However, reliability is inconsistent and frequently poor, and the system has not been evaluated in patient populations with pathological movement patterns. These findings do not support clinical deployment at this stage. Substantial further development and validation in patient cohorts are required before clinical or home-based use can be considered.