Gait biometrics using RGB camera and computer vision

ˑ: 

Dr. Med., Professor T.T. Batysheva1, 2
PhD, Associate Professor S.V. Tikhonov1, 2
PhD, Associate Professor M.V. Alekseeva1, 2
D.A. Peganskiy3, 4
1Federal Scientific Center of Psychological and Multidisciplinary Researches, Moscow
2Scientific and Practical Center for Pediatric Psychoneurology of the Moscow Health Department, Moscow
3Agency AST, Omsk
4Lesgaft National State University of Physical Education, Sport and Health, St. Petersburg

Objective of the study was to substantiate the method of calculating human walking parameters using the method of neural networks and computer vision technologies.
Methods and structure of the study. The scientific work included the following stages: 1) video recording with one RGB camera; 2) calculation of point coordinates using the OpenPose neural network and formation of a data array; 3) cleaning the resulting array from artifacts using the Hodrick-Prescott filter; 4) identification of the gait cycle; 5) calculation of gait parameters. The subject's gait parameters were recorded and evaluated in the Zebris Rehawalk system (system configuration from h/p/cosmos) based at the Scientific and Practical Center for Pediatric Neurology of the Moscow Department of Health. Video recording was carried out with a Panasonic HC-VX1 video camera. The Body_25 model was used to calculate the coordinates of the location of the subject's body elements in space. The parameters were calculated for the sagittal projection using the Edinburgh Human Gait Scale.
Results and conclusions. Based on the calculation results, the following indicator values ​​were obtained: walking cycle time is 1,58±0,92 s, step execution time is 0,78±0,03 s, step length is 41,33±1,92 cm, walking speed is 1,91±0,09 km/h. The calculation of the subject's hip, knee, and foot movement indicators was performed. Based on a comparison of the obtained values ​​with the standard values, minor deviations in the subject's walking from normal were revealed. The calculation accuracy was 0.95. The results showed that computer vision is sufficiently accurate in assessing the biomechanics of human movement and can be used as an objective monitoring tool in various sports, medical diagnostics, and rehabilitation. The use of this approach does not require special training, equipment, or premises, which facilitates monitoring of human movement indicators in any conditions.

Keywords: gait analysis, Edinburgh Visual Gait Scale, computer vision, OpenPose.

References

  1. Wang H. et al. Markerless gait analysis through a single camera and computer vision // Journal of Biomechanics. 2024. Vol. 165. pp. 112027. https://doi.org/10.1016/j.jbiomech.2024.112027.
  2. Hatamzadeh M.A et al. kinematic-geometric model based on ankles’ depth trajectory in frontal plane for gait analysis using a single RGB-D camera eh // Journal of Biomechanics. 2022. Vol. 145. pp. 111358. https://doi.org/10.1016/j.jbiomech.2022.111358.
  3. Leardini Al. et al. Kinematic models of lower limb joints for musculo-skeletal modelling and optimization in gait analysis // Journal of Biomechanics. 2017. Vol. 62. pp. 77-86. https://doi.org/10.1016/j.jbiomech.2017.04.029.
  4. Klöpfer-Krämer et al. Is. Gait analysis – Available platforms for outcome assessment // Injury. – 2020. –Vol. 51, Supplement 2. – pp. S90-S96. https://doi.org/10.1016/j.injury.2019.11.011.
  5. Kumar M. et al. Gait recognition based on vision systems: A systematic survey // Journal of Visual Communication and Image Representation. – 2021. – Vol. 75. – pp. 103052. https://doi.org/10.1016/j.jvcir.2021.103052.
  6. Ramesh S.H. et al. Automated Implementation of the Edinburgh Visual Gait Score (EVGS) Using OpenPose and Handheld Smartphone Video // Sensors. 2023, Vol. 23. pp. 4839. https://doi.org/10.3390/s23104839.
  7. Zeni Jr. J. A. Two simple methods for determining gait events during treadmill and overground walking using kinematic data // Gait & posture. 2008. Vol. 27. No 4. pp. 710-714.