Enhanced Human Skeleton Tracking for Improved Joint Position and Depth Accuracy in Rehabilitation Exercises
The objective of this work is to develop a method for tracking human skeletal movements by integrating data from two synchronized video streams. To achieve this, two datasets were created, each consisting of four different rehabilitation exercise videos featuring various individuals in diverse envir...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/906 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589160906489856 |
|---|---|
| author | Vytautas Abromavičius Ervinas Gisleris Kristina Daunoravičienė Jurgita Žižienė Artūras Serackis Rytis Maskeliūnas |
| author_facet | Vytautas Abromavičius Ervinas Gisleris Kristina Daunoravičienė Jurgita Žižienė Artūras Serackis Rytis Maskeliūnas |
| author_sort | Vytautas Abromavičius |
| collection | DOAJ |
| description | The objective of this work is to develop a method for tracking human skeletal movements by integrating data from two synchronized video streams. To achieve this, two datasets were created, each consisting of four different rehabilitation exercise videos featuring various individuals in diverse environments and wearing different clothing. The prediction model is employed to create a dual-image stream system that enables the tracking of joint positions even when a joint is obscured in one of the streams. This system also mitigates depth coordinate errors by using data from both video streams. The final implementation successfully corrects the positions of the right elbow and wrist joints, though some depth error persists in the left hand. The results demonstrate that adding a second video camera, rotated 90° and aimed at the subject, can compensate for depth prediction inaccuracies, reducing errors by up to 0.4 m. By using a dual-camera setup and fusing the predicted human skeletal models, it is possible to construct a complete human model even when one camera does not capture all body parts and to refine depth coordinates through error correction using a linear regression model. |
| format | Article |
| id | doaj-art-01a0ee64cd0744b2babc0e88edb10813 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-01a0ee64cd0744b2babc0e88edb108132025-01-24T13:21:17ZengMDPI AGApplied Sciences2076-34172025-01-0115290610.3390/app15020906Enhanced Human Skeleton Tracking for Improved Joint Position and Depth Accuracy in Rehabilitation ExercisesVytautas Abromavičius0Ervinas Gisleris1Kristina Daunoravičienė2Jurgita Žižienė3Artūras Serackis4Rytis Maskeliūnas5Centre of Real Time Computer Systems, Faculty of Informatics, Kaunas University of Technology, LT-51423 Kaunas, LithuaniaDepartment of Electronic Systems, Vilnius Gediminas Technical University, Plytinės g. 25, LT-10105 Vilnius, LithuaniaDepartment of Biomechanical Engineering, Vilnius Gediminas Technical University, Plytinės g. 25, LT-10105 Vilnius, LithuaniaDepartment of Biomechanical Engineering, Vilnius Gediminas Technical University, Plytinės g. 25, LT-10105 Vilnius, LithuaniaDepartment of Electronic Systems, Vilnius Gediminas Technical University, Plytinės g. 25, LT-10105 Vilnius, LithuaniaCentre of Real Time Computer Systems, Faculty of Informatics, Kaunas University of Technology, LT-51423 Kaunas, LithuaniaThe objective of this work is to develop a method for tracking human skeletal movements by integrating data from two synchronized video streams. To achieve this, two datasets were created, each consisting of four different rehabilitation exercise videos featuring various individuals in diverse environments and wearing different clothing. The prediction model is employed to create a dual-image stream system that enables the tracking of joint positions even when a joint is obscured in one of the streams. This system also mitigates depth coordinate errors by using data from both video streams. The final implementation successfully corrects the positions of the right elbow and wrist joints, though some depth error persists in the left hand. The results demonstrate that adding a second video camera, rotated 90° and aimed at the subject, can compensate for depth prediction inaccuracies, reducing errors by up to 0.4 m. By using a dual-camera setup and fusing the predicted human skeletal models, it is possible to construct a complete human model even when one camera does not capture all body parts and to refine depth coordinates through error correction using a linear regression model.https://www.mdpi.com/2076-3417/15/2/906pose estimationrehabilitationdeep learningvideo stream |
| spellingShingle | Vytautas Abromavičius Ervinas Gisleris Kristina Daunoravičienė Jurgita Žižienė Artūras Serackis Rytis Maskeliūnas Enhanced Human Skeleton Tracking for Improved Joint Position and Depth Accuracy in Rehabilitation Exercises Applied Sciences pose estimation rehabilitation deep learning video stream |
| title | Enhanced Human Skeleton Tracking for Improved Joint Position and Depth Accuracy in Rehabilitation Exercises |
| title_full | Enhanced Human Skeleton Tracking for Improved Joint Position and Depth Accuracy in Rehabilitation Exercises |
| title_fullStr | Enhanced Human Skeleton Tracking for Improved Joint Position and Depth Accuracy in Rehabilitation Exercises |
| title_full_unstemmed | Enhanced Human Skeleton Tracking for Improved Joint Position and Depth Accuracy in Rehabilitation Exercises |
| title_short | Enhanced Human Skeleton Tracking for Improved Joint Position and Depth Accuracy in Rehabilitation Exercises |
| title_sort | enhanced human skeleton tracking for improved joint position and depth accuracy in rehabilitation exercises |
| topic | pose estimation rehabilitation deep learning video stream |
| url | https://www.mdpi.com/2076-3417/15/2/906 |
| work_keys_str_mv | AT vytautasabromavicius enhancedhumanskeletontrackingforimprovedjointpositionanddepthaccuracyinrehabilitationexercises AT ervinasgisleris enhancedhumanskeletontrackingforimprovedjointpositionanddepthaccuracyinrehabilitationexercises AT kristinadaunoraviciene enhancedhumanskeletontrackingforimprovedjointpositionanddepthaccuracyinrehabilitationexercises AT jurgitaziziene enhancedhumanskeletontrackingforimprovedjointpositionanddepthaccuracyinrehabilitationexercises AT arturasserackis enhancedhumanskeletontrackingforimprovedjointpositionanddepthaccuracyinrehabilitationexercises AT rytismaskeliunas enhancedhumanskeletontrackingforimprovedjointpositionanddepthaccuracyinrehabilitationexercises |