Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Developing Normative Gait Cycle Parameters for Clinical Analysis Using Human Pose Estimation

Rahm Ranjan, David Ahmedt-Aristizabal, Mohammad Ali Armin, Juno Kim

TL;DR

This cycle-wise kinematic analysis enables clinicians to simultaneously measure and compare multiple joint angles, assessing individuals against a normative population using just monocular RGB video, and automates the identification of specific spatial and temporal deviations and abnormalities within the gait cycle.

Abstract

Gait analysis using computer vision is an emerging field in AI, offering clinicians an objective, multi-feature approach to analyse complex movements. Despite its promise, current applications using RGB video data alone are limited in measuring clinically relevant spatial and temporal kinematics and establishing normative parameters essential for identifying movement abnormalities within a gait cycle. This paper presents a data-driven method using RGB video data and 2D human pose estimation for developing normative kinematic gait parameters. By analysing joint angles, an established kinematic measure in biomechanics and clinical practice, we aim to enhance gait analysis capabilities and improve explainability. Our cycle-wise kinematic analysis enables clinicians to simultaneously measure and compare multiple joint angles, assessing individuals against a normative population using just monocular RGB video. This approach expands clinical capacity, supports objective decision-making, and automates the identification of specific spatial and temporal deviations and abnormalities within the gait cycle.

Developing Normative Gait Cycle Parameters for Clinical Analysis Using Human Pose Estimation

TL;DR

This cycle-wise kinematic analysis enables clinicians to simultaneously measure and compare multiple joint angles, assessing individuals against a normative population using just monocular RGB video, and automates the identification of specific spatial and temporal deviations and abnormalities within the gait cycle.

Abstract

Gait analysis using computer vision is an emerging field in AI, offering clinicians an objective, multi-feature approach to analyse complex movements. Despite its promise, current applications using RGB video data alone are limited in measuring clinically relevant spatial and temporal kinematics and establishing normative parameters essential for identifying movement abnormalities within a gait cycle. This paper presents a data-driven method using RGB video data and 2D human pose estimation for developing normative kinematic gait parameters. By analysing joint angles, an established kinematic measure in biomechanics and clinical practice, we aim to enhance gait analysis capabilities and improve explainability. Our cycle-wise kinematic analysis enables clinicians to simultaneously measure and compare multiple joint angles, assessing individuals against a normative population using just monocular RGB video. This approach expands clinical capacity, supports objective decision-making, and automates the identification of specific spatial and temporal deviations and abnormalities within the gait cycle.

Paper Structure

This paper contains 21 sections, 2 equations, 12 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background on Clinical Gait Analysis
  3. Related Works
  4. Method
  5. Video Datasets
  6. GPJATK gait dataset
  7. Gait Abnormality in Video Dataset (GAVD)
  8. Clinical Abnormality Simulated Dataset (CASD)
  9. Annotation
  10. Feature Extraction
  11. Joint Angle Calculation
  12. Creating Normative Parameters
  13. Experiments
  14. Experimental Setup
  15. Results and Discussion
  16. ...and 6 more sections

Figures (12)

  • Figure 1: Example of typical kinematic parameters of left knee during gait cycle extrapolated from video of 351 normalised gait cycles.
  • Figure 2: Single joint detection of potential deviation of left knee angle during gait cycle, blue dots represent normal and red dots indicate abnormal.
  • Figure 3: Multi-joint abnormality detection for test video one from GPJATK datasetKwolek2019Calibrated with typical gait pattern.
  • Figure 4: Multi-joint abnormality detection for test video two from GAVDRanjan2024GAVD with atypical gait pattern
  • Figure 5: Multi-joint abnormality detection for test video three from CASDRanjan2024GAVD with typical gait pattern.
  • ...and 7 more figures