Izvestiya of Saratov University.

Mathematics. Mechanics. Informatics

ISSN 1816-9791 (Print)
ISSN 2541-9005 (Online)

For citation:

Smirnova V. V. Development and validation of a hardware-software system for quantitative assessment of posture using digital video data. Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, 2026, vol. 26, iss. 1, pp. 91-100. DOI: 10.18500/1816-9791-2026-26-1-91-100, EDN: PDPEPN

This is an open access article distributed under the terms of Creative Commons Attribution 4.0 International License (CC-BY 4.0).
Published online: 
02.03.2026
Full text:
download
(downloads: 52)
Language: 
Russian
Heading: 
Mechanics
Article type: 
Article
UDC: 
004.932
DOI: 
10.18500/1816-9791-2026-26-1-91-100
EDN: 
PDPEPN

Development and validation of a hardware-software system for quantitative assessment of posture using digital video data

Autors: 
Smirnova Victoriya V., Kazan (Volga Region) Federal University
Abstract: 

The study aims to verify the accuracy of a developed hardware-software system for analyzing human posture using a digital video camera. The objective of the work was to compare the results obtained with the developed system to the data from the Vicon Nexus motion capture system. The research included the development of a methodology for processing video images to determine posture parameters, the creation of software for automatic video analysis and metric calculation, and the conduct of an experimental study involving 14 participants (7 men and 7 women). Simultaneous recording was performed using a digital video camera (4K resolution, 30 fps) and the Vicon Nexus system with infrared cameras and reflective markers. Data analysis employed computer vision techniques, including the use of the pre-trained neural model SAM for image segmentation and the computation of angular posture characteristics. Statistical analysis demonstrated a high degree of agreement between the two systems (cross-correlation coefficient $r = 0.81$), with a result discrepancy of 4–5%. Key factors affecting accuracy include technical limitations of the video camera, errors in mathematical models, and optical system distortion. The obtained results confirm the potential of using the developed system for posture assessment in clinical settings, opening up prospects for its application in sports medicine, rehabilitation, and biomechanics.

Key words: 
video analysis
biomechanics
posture
Vicon Nexus system
computer vision
neural networks
image segmentation
angular characteristics
clinical applicability
Acknowledgments: 
The research was funded by the subsidy allocated to Kazan Federal University for the state assignment in the sphere of scientific activities (project No. FZSM-2023-0009).
References: 
  1. Wei S. E., Ramakrishna V., Kanade T., Sheikh Y. Convolutional pose machines. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA, 2016, pp. 4724–4732. DOI: https://doi.org/10.1109/cvpr.2016.511
  2. Baker R. Gait analysis methods in rehabilitation. Journal of NeuroEngineering and Rehabilitation, 2006, vol. 3, iss. 1, art. 4. DOI: https://doi.org/10.1186/1743-0003-3-4
  3. Hensley C. P., Lenihan E. M., Pratt K., Shah A., O’Donnell E., Nee P.-C., Lee J., Yang A., Chang A. H. Patterns of video-based motion analysis use among sports physical therapists. Physical Therapy in Sport, 2021, vol. 50, pp. 159–165. DOI: https://doi.org/10.1016/j.ptsp.2021.05.003
  4. Scataglini S., Abts E., Van Bocxlaer C., Van den Bussche M., Meletani S., Truijen S. Accuracy, validity, and reliability of markerless camera-based 3D motion capture systems versus marker-based 3D motion capture systems in gait analysis: A systematic review and meta-analysis. Sensors, 2024, vol. 24, iss. 11, art. 3686. DOI: https://doi.org/10.3390/s24113686
  5. Das K., de Paula Oliveira T., Newell J. Comparison of markerless and marker-based motion capture systems using 95% functional limits of agreement in a linear mixed-effects modelling framework. Scientific Reports, 2023, vol. 13, iss. 1, art. 22880. DOI: https://doi.org/10.1038/s41598-023-49360-2
  6. Ma Y., Mithraratne K., Wilson N. C., Wang X., Zhang Y. The validity and reliability of a kinect v2-based gait analysis system for children with cerebral palsy. Sensors, 2019, vol. 19, iss. 7, art. 1660. DOI: https://doi.org/10.3390/s19071660
  7. Fiorentino N. M., Kutschke M. J., Atkins P. R., Foreman K. B., Kapron A. L., Anderson A. E. Accuracy of functional and predictive methods to calculate the hip joint center in young nonpathologic asymptomatic adults with dual fluoroscopy as a reference standard. Annals of Biomedical Engineering, 2015, vol. 44, iss. 7, pp. 2168–2180. DOI: https://doi.org/10.1007/s10439-015-1522-1
  8. Tao W., Liu T., Zheng R., Feng H. Gait analysis using wearable sensors. Sensors, 2012, vol. 12, iss. 2, pp. 2255–2283. DOI: https://doi.org/10.3390/s120202255
  9. Vincent A. C., Furman H., Slepian R. C., Ammann K. R., Di Maria C., Chien J. H., Siu K.-C., Slepian M. J. Smart phone-based motion capture and analysis: Importance of operating envelope definition and application to clinical use. Applied Sciences, 2022, vol. 12, iss. 12, art. 6173. DOI: https://doi.org/10.3390/app12126173
  10. Zult T., Allsop J., Tabernero J., Pardhan S. A low-cost 2-D video system can accurately and reliably assess adaptive gait kinematics in healthy and low vision subjects. Scientific Reports, 2019, vol. 9, iss. 1, art. 18385. DOI: https://doi.org/10.1038/s41598-019-54913-5
  11. Chou C.-J., Chien J.-T., Chen H.-T. Self adversarial training for human pose estimation. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). Honolulu, HI, USA, 2018, pp. 17–30. DOI: https://doi.org/10.23919/apsipa.2018.8659538
  12. Fan X., Zheng K., Lin Y., Wang S. Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, MA, 2015, pp. 1347–1355. DOI: https://doi.org/10.1109/CVPR.2015.7298740
  13. Newell A., Yang K., Deng J. Stacked hourglass networks for human pose estimation. In: Leibe B., Matas J., Sebe N., Welling M. (eds.) Computer Vision – ECCV 2016. ECCV 2016. Lecture Notes in Computer Science, vol 9912. Cham, Springer, 2016, pp. 483–499. DOI: https://doi.org/10.1007/978-3-319-46484-8_29
  14. Kirillov A., Mintun E., Ravi N., Mao H., Rolland C., Gustafson L., Xiao T., Whitehead S., Berg A., Lo W., Dollar P., Girshick R. Segment anything. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris, France, 2023, pp. 3992–4003. DOI: https://doi.org/10.1109/iccv51070.2023.00371
  15. Li F., Zhang H., Sun P., Zou X., Liu S., Yang J., Li C., Zhang L., Gao J. Segment and recognize anything at any granularity. In: Leonardis A., Ricci E., Roth S., Russakovsky O., Sattler T., Varol G. (eds.) Computer Vision– ECCV 2024. Lecture Notes in Computer Science, vol. 15106. Cham, Springer, 2025, pp. 467–484. DOI: https://doi.org/10.1007/978-3-031-73195-2_27
  16. Smirnova V., Khamatnurova R., Kharin N., Yaikova E., Baltina T., Sachenkov O. The automatization of the gait analysis by the Vicon video system: A pilot study. Sensors, 2022, vol. 22, iss. 19, art. 7178. DOI: https://doi.org/10.3390/s22197178
  17. Zhang Z. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, vol. 22, iss. 11, pp. 1330–1334. DOI: https://doi.org/10.1109/34.888718
  18. Devernay F., Faugeras O. Straight lines have to be straight. Machine Vision and Applications, 2001, vol. 13, iss. 1, pp. 14–24. DOI: https://doi.org/10.1007/pl00013269
Received: 
11.04.2025
Accepted: 
27.09.2025
Published: 
02.03.2026
  • 172 reads