Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Differentiable Biomechanics for Markerless Motion Capture in Upper Limb Stroke Rehabilitation: A Comparison with Optical Motion Capture

Tim Unger, Arash Sal Moslehian, J. D. Peiffer, Johann Ullrich, Roger Gassert, Olivier Lambercy, R. James Cotton, Chris Awai Easthope

TL;DR

Findings indicate that the MMC for arm tracking is approaching the accuracy of marker-based methods, supporting its potential for use in clinical settings and potentially enhancing the effectiveness of rehabilitation strategies.

Abstract

Marker-based Optical Motion Capture (OMC) paired with biomechanical modeling is currently considered the most precise and accurate method for measuring human movement kinematics. However, combining differentiable biomechanical modeling with Markerless Motion Capture (MMC) offers a promising approach to motion capture in clinical settings, requiring only minimal equipment, such as synchronized webcams, and minimal effort for data collection. This study compares key kinematic outcomes from biomechanically modeled MMC and OMC data in 15 stroke patients performing the drinking task, a functional task recommended for assessing upper limb movement quality. We observed a high level of agreement in kinematic trajectories between MMC and OMC, as indicated by high correlations (median r above 0.95 for the majority of kinematic trajectories) and median RMSE values ranging from 2-5 degrees for joint angles, 0.04 m/s for end-effector velocity, and 6 mm for trunk displacement. Trial-to-trial biases between OMC and MMC were consistent within participant sessions, with interquartile ranges of bias around 1-3 degrees for joint angles, 0.01 m/s in end-effector velocity, and approximately 3mm for trunk displacement. Our findings indicate that our MMC for arm tracking is approaching the accuracy of marker-based methods, supporting its potential for use in clinical settings. MMC could provide valuable insights into movement rehabilitation in stroke patients, potentially enhancing the effectiveness of rehabilitation strategies.

Differentiable Biomechanics for Markerless Motion Capture in Upper Limb Stroke Rehabilitation: A Comparison with Optical Motion Capture

TL;DR

Findings indicate that the MMC for arm tracking is approaching the accuracy of marker-based methods, supporting its potential for use in clinical settings and potentially enhancing the effectiveness of rehabilitation strategies.

Abstract

Marker-based Optical Motion Capture (OMC) paired with biomechanical modeling is currently considered the most precise and accurate method for measuring human movement kinematics. However, combining differentiable biomechanical modeling with Markerless Motion Capture (MMC) offers a promising approach to motion capture in clinical settings, requiring only minimal equipment, such as synchronized webcams, and minimal effort for data collection. This study compares key kinematic outcomes from biomechanically modeled MMC and OMC data in 15 stroke patients performing the drinking task, a functional task recommended for assessing upper limb movement quality. We observed a high level of agreement in kinematic trajectories between MMC and OMC, as indicated by high correlations (median r above 0.95 for the majority of kinematic trajectories) and median RMSE values ranging from 2-5 degrees for joint angles, 0.04 m/s for end-effector velocity, and 6 mm for trunk displacement. Trial-to-trial biases between OMC and MMC were consistent within participant sessions, with interquartile ranges of bias around 1-3 degrees for joint angles, 0.01 m/s in end-effector velocity, and approximately 3mm for trunk displacement. Our findings indicate that our MMC for arm tracking is approaching the accuracy of marker-based methods, supporting its potential for use in clinical settings. MMC could provide valuable insights into movement rehabilitation in stroke patients, potentially enhancing the effectiveness of rehabilitation strategies.

Paper Structure

This paper contains 18 sections, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Participants
  4. Data Acquisition and Preprocessing
  5. Data Processing and Inverse Kinematics
  6. Two-Stage OMC
  7. End-to-End MMC
  8. System Comparison
  9. Kinematic Trajectories
  10. Movement Quality Measures
  11. Results
  12. Study Population
  13. Data and Processing
  14. System comparison
  15. Kinematic Trajectories
  16. ...and 3 more sections

Figures (4)

  • Figure 1: Camera perspectives of the five webcams used for MMC.
  • Figure 2: Visualization of biomechnical modelling. left: OMC data with Opensim; right: end-to-end MMC with Mujoco.
  • Figure 3: Exemplary kinematic trajectories of participant p01, showing one trial each for the affected and unaffected arm. Horizontal lines outline the movement quality measures, and the x's on the end-effector velocity mark each movement unit.
  • Figure 4: Correlation plot for each measure, comparing two-stage OMC and end-to-end MMC. Each data point represents a single trial. Trials are color-coded per participant and shape-coded per arm.