Comparison of Shoulder Range of Motion Quantified with Mobile Phone Video-Based Skeletal Tracking and 3D Motion Capture—Preliminary Study
Background: The accuracy of human pose tracking using smartphone camera (2D-pose) to quantify shoulder range of motion (RoM) is not determined. Methods: Twenty healthy individuals were recruited and performed shoulder abduction, adduction, flexion, or extension, captured simultaneously using a smart...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/2/534 |
| _version_ | 1827369339099021312 |
|---|---|
| author | Wolbert van den Hoorn Maxence Lavaill Kenneth Cutbush Ashish Gupta Graham Kerr |
| author_facet | Wolbert van den Hoorn Maxence Lavaill Kenneth Cutbush Ashish Gupta Graham Kerr |
| author_sort | Wolbert van den Hoorn |
| collection | DOAJ |
| description | Background: The accuracy of human pose tracking using smartphone camera (2D-pose) to quantify shoulder range of motion (RoM) is not determined. Methods: Twenty healthy individuals were recruited and performed shoulder abduction, adduction, flexion, or extension, captured simultaneously using a smartphone-based human pose estimation algorithm (Apple’s vision framework) and using a skin marker-based 3D motion capture system. Validity was assessed by comparing the 2D-pose outcomes against a well-established 3D motion capture protocol. In addition, the impact of iPhone positioning was investigated using three smartphones in multiple vertical and horizontal positions. The relationship and validity were analysed using linear mixed models and Bland-Altman analysis. Results: We found that 2D-pose-based shoulder RoM was consistent with 3D motion capture (linear mixed model: R<sup>2</sup> > 0.93) but was somewhat overestimated by the smartphone. Differences were dependent on shoulder movement type and RoM amplitude, with adduction the worst performer among all tested movements. All motion types were described using linear equations. Correction methods are provided to correct potential out-of-plane shoulder movements. Conclusions: Shoulder RoM estimated using a smartphone camera is consistent with 3D motion-capture-derived RoM; however, differences between the systems were observed and are likely explained by differences in thoracic frame definitions. |
| first_indexed | 2024-03-08T09:46:42Z |
| format | Article |
| id | doaj.art-7c8cfb8a5c1743d4926634f8846045ea |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T09:46:42Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7c8cfb8a5c1743d4926634f8846045ea2024-01-29T14:16:02ZengMDPI AGSensors1424-82202024-01-0124253410.3390/s24020534Comparison of Shoulder Range of Motion Quantified with Mobile Phone Video-Based Skeletal Tracking and 3D Motion Capture—Preliminary StudyWolbert van den Hoorn0Maxence Lavaill1Kenneth Cutbush2Ashish Gupta3Graham Kerr4School of Exercise & Nutrition Sciences, Queensland University of Technology, Brisbane, QLD 4059, AustraliaQueensland Unit for Advanced Shoulder Research, Brisbane, QLD 4067, AustraliaQueensland Unit for Advanced Shoulder Research, Brisbane, QLD 4067, AustraliaQueensland Unit for Advanced Shoulder Research, Brisbane, QLD 4067, AustraliaSchool of Exercise & Nutrition Sciences, Queensland University of Technology, Brisbane, QLD 4059, AustraliaBackground: The accuracy of human pose tracking using smartphone camera (2D-pose) to quantify shoulder range of motion (RoM) is not determined. Methods: Twenty healthy individuals were recruited and performed shoulder abduction, adduction, flexion, or extension, captured simultaneously using a smartphone-based human pose estimation algorithm (Apple’s vision framework) and using a skin marker-based 3D motion capture system. Validity was assessed by comparing the 2D-pose outcomes against a well-established 3D motion capture protocol. In addition, the impact of iPhone positioning was investigated using three smartphones in multiple vertical and horizontal positions. The relationship and validity were analysed using linear mixed models and Bland-Altman analysis. Results: We found that 2D-pose-based shoulder RoM was consistent with 3D motion capture (linear mixed model: R<sup>2</sup> > 0.93) but was somewhat overestimated by the smartphone. Differences were dependent on shoulder movement type and RoM amplitude, with adduction the worst performer among all tested movements. All motion types were described using linear equations. Correction methods are provided to correct potential out-of-plane shoulder movements. Conclusions: Shoulder RoM estimated using a smartphone camera is consistent with 3D motion-capture-derived RoM; however, differences between the systems were observed and are likely explained by differences in thoracic frame definitions.https://www.mdpi.com/1424-8220/24/2/534shoulderrange of motionhuman pose tracking2D poseclinical assessmentvalidity |
| spellingShingle | Wolbert van den Hoorn Maxence Lavaill Kenneth Cutbush Ashish Gupta Graham Kerr Comparison of Shoulder Range of Motion Quantified with Mobile Phone Video-Based Skeletal Tracking and 3D Motion Capture—Preliminary Study Sensors shoulder range of motion human pose tracking 2D pose clinical assessment validity |
| title | Comparison of Shoulder Range of Motion Quantified with Mobile Phone Video-Based Skeletal Tracking and 3D Motion Capture—Preliminary Study |
| title_full | Comparison of Shoulder Range of Motion Quantified with Mobile Phone Video-Based Skeletal Tracking and 3D Motion Capture—Preliminary Study |
| title_fullStr | Comparison of Shoulder Range of Motion Quantified with Mobile Phone Video-Based Skeletal Tracking and 3D Motion Capture—Preliminary Study |
| title_full_unstemmed | Comparison of Shoulder Range of Motion Quantified with Mobile Phone Video-Based Skeletal Tracking and 3D Motion Capture—Preliminary Study |
| title_short | Comparison of Shoulder Range of Motion Quantified with Mobile Phone Video-Based Skeletal Tracking and 3D Motion Capture—Preliminary Study |
| title_sort | comparison of shoulder range of motion quantified with mobile phone video based skeletal tracking and 3d motion capture preliminary study |
| topic | shoulder range of motion human pose tracking 2D pose clinical assessment validity |
| url | https://www.mdpi.com/1424-8220/24/2/534 |
| work_keys_str_mv | AT wolbertvandenhoorn comparisonofshoulderrangeofmotionquantifiedwithmobilephonevideobasedskeletaltrackingand3dmotioncapturepreliminarystudy AT maxencelavaill comparisonofshoulderrangeofmotionquantifiedwithmobilephonevideobasedskeletaltrackingand3dmotioncapturepreliminarystudy AT kennethcutbush comparisonofshoulderrangeofmotionquantifiedwithmobilephonevideobasedskeletaltrackingand3dmotioncapturepreliminarystudy AT ashishgupta comparisonofshoulderrangeofmotionquantifiedwithmobilephonevideobasedskeletaltrackingand3dmotioncapturepreliminarystudy AT grahamkerr comparisonofshoulderrangeofmotionquantifiedwithmobilephonevideobasedskeletaltrackingand3dmotioncapturepreliminarystudy |