Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals
Telerehabilitation systems leveraging depth video analysis provide an effective solution for remote physiotherapy, particularly for individuals with physical disabilities. This study presents an advanced exercise classification framework that integrates multi-modal feature extraction and attention-b...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10979369/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849322402114174976 |
|---|---|
| author | Aleena Kamal Shaheryar Najam Mohammed Alshehri Yahya AlQahtani Abdulmonem Alshahrani Bayan Alabdullah Jeongmin Park |
| author_facet | Aleena Kamal Shaheryar Najam Mohammed Alshehri Yahya AlQahtani Abdulmonem Alshahrani Bayan Alabdullah Jeongmin Park |
| author_sort | Aleena Kamal |
| collection | DOAJ |
| description | Telerehabilitation systems leveraging depth video analysis provide an effective solution for remote physiotherapy, particularly for individuals with physical disabilities. This study presents an advanced exercise classification framework that integrates multi-modal feature extraction and attention-based transformation to enhance rehabilitation monitoring. The proposed pipeline begins with depth image preprocessing, followed by human detection using a pre-trained Histogram of Oriented Gradients (HOG)-Support Vector Machine (SVM) model. The human silhouette is segmented using the GrabCut algorithm, enabling robust region-of-interest extraction. We propose a novel Lightweight Two-tier Key Body Point Detection (LT-KBPD) algorithm to efficiently and accurately identify key skeletal points, which are then used to extract both static and dynamic kinematic features. In parallel, silhouette-based analysis is performed, where shape descriptors, dense optical flow, Gaussian Mixture Model (GMM)-based body part segmentation, and contour analysis extract spatial and motion-related features. The extracted feature sets are fused into a comprehensive feature vector and further refined using an attention-based transformation mechanism to highlight salient features relevant to exercise classification. Finally, a Long Short-Term Memory (LSTM) network is employed to model temporal dependencies and classify exercises with high accuracy. The proposed approach is validated on three benchmark depth-video datasets: Kimore, K3DA and MEx - Multi-modal Exercise Dataset, achieving classification accuracies of 92.19%, 91.35%, and 85.51%, respectively. These results demonstrate the system’s effectiveness in accurately recognizing rehabilitation exercises for individuals with physical disabilities. Future work aims to enhance the adaptability of the system through personalized rehabilitation feedback and improved temporal modeling techniques. |
| format | Article |
| id | doaj-art-e39b3c05efb84fd1a310efdcbb59b3f9 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-e39b3c05efb84fd1a310efdcbb59b3f92025-08-20T03:49:22ZengIEEEIEEE Access2169-35362025-01-0113812798129710.1109/ACCESS.2025.356502410979369Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled IndividualsAleena Kamal0https://orcid.org/0009-0004-2666-307XShaheryar Najam1https://orcid.org/0000-0002-2186-2342Mohammed Alshehri2https://orcid.org/0009-0005-5795-3309Yahya AlQahtani3Abdulmonem Alshahrani4https://orcid.org/0000-0003-2984-0612Bayan Alabdullah5https://orcid.org/0000-0002-6252-1800Jeongmin Park6https://orcid.org/0000-0001-8027-0876Department of Biomedical Engineering, Riphah International University, Islamabad, PakistanDepartment of Electrical Engineering, Bahria University, Islamabad, PakistanDepartment of Computer Science, King Khalid University, Abha, Saudi ArabiaDepartment of Informatics and Computer Systems, King Khalid University, Abha, Saudi ArabiaDepartment of Informatics and Computer Systems, King Khalid University, Abha, Saudi ArabiaDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi ArabiaDepartment of Computer Engineering, Tech University of Korea, Siheung-si, Gyeonggi-do, South KoreaTelerehabilitation systems leveraging depth video analysis provide an effective solution for remote physiotherapy, particularly for individuals with physical disabilities. This study presents an advanced exercise classification framework that integrates multi-modal feature extraction and attention-based transformation to enhance rehabilitation monitoring. The proposed pipeline begins with depth image preprocessing, followed by human detection using a pre-trained Histogram of Oriented Gradients (HOG)-Support Vector Machine (SVM) model. The human silhouette is segmented using the GrabCut algorithm, enabling robust region-of-interest extraction. We propose a novel Lightweight Two-tier Key Body Point Detection (LT-KBPD) algorithm to efficiently and accurately identify key skeletal points, which are then used to extract both static and dynamic kinematic features. In parallel, silhouette-based analysis is performed, where shape descriptors, dense optical flow, Gaussian Mixture Model (GMM)-based body part segmentation, and contour analysis extract spatial and motion-related features. The extracted feature sets are fused into a comprehensive feature vector and further refined using an attention-based transformation mechanism to highlight salient features relevant to exercise classification. Finally, a Long Short-Term Memory (LSTM) network is employed to model temporal dependencies and classify exercises with high accuracy. The proposed approach is validated on three benchmark depth-video datasets: Kimore, K3DA and MEx - Multi-modal Exercise Dataset, achieving classification accuracies of 92.19%, 91.35%, and 85.51%, respectively. These results demonstrate the system’s effectiveness in accurately recognizing rehabilitation exercises for individuals with physical disabilities. Future work aims to enhance the adaptability of the system through personalized rehabilitation feedback and improved temporal modeling techniques.https://ieeexplore.ieee.org/document/10979369/Depth video analysistelerehabilitationhuman pose estimationexercise recognitionmotion analysisdense optical flow |
| spellingShingle | Aleena Kamal Shaheryar Najam Mohammed Alshehri Yahya AlQahtani Abdulmonem Alshahrani Bayan Alabdullah Jeongmin Park Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals IEEE Access Depth video analysis telerehabilitation human pose estimation exercise recognition motion analysis dense optical flow |
| title | Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals |
| title_full | Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals |
| title_fullStr | Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals |
| title_full_unstemmed | Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals |
| title_short | Holistic Pose Estimation and Dynamic Motion Analysis for Telerehabilitation of Physically Disabled Individuals |
| title_sort | holistic pose estimation and dynamic motion analysis for telerehabilitation of physically disabled individuals |
| topic | Depth video analysis telerehabilitation human pose estimation exercise recognition motion analysis dense optical flow |
| url | https://ieeexplore.ieee.org/document/10979369/ |
| work_keys_str_mv | AT aleenakamal holisticposeestimationanddynamicmotionanalysisfortelerehabilitationofphysicallydisabledindividuals AT shaheryarnajam holisticposeestimationanddynamicmotionanalysisfortelerehabilitationofphysicallydisabledindividuals AT mohammedalshehri holisticposeestimationanddynamicmotionanalysisfortelerehabilitationofphysicallydisabledindividuals AT yahyaalqahtani holisticposeestimationanddynamicmotionanalysisfortelerehabilitationofphysicallydisabledindividuals AT abdulmonemalshahrani holisticposeestimationanddynamicmotionanalysisfortelerehabilitationofphysicallydisabledindividuals AT bayanalabdullah holisticposeestimationanddynamicmotionanalysisfortelerehabilitationofphysicallydisabledindividuals AT jeongminpark holisticposeestimationanddynamicmotionanalysisfortelerehabilitationofphysicallydisabledindividuals |