Methods for Spatiotemporal Analysis of Human Gait Based on Data from Depth Sensors

Area of Science:

• Biomedical Engineering
• Rehabilitation Technology
• Human Movement Science

Background:

• Gait analysis is crucial for healthcare, particularly in assessing fall risk in the elderly.
• Depth sensors offer a viable solution for gait analysis in clinical and home environments.
• Spatiotemporal gait parameters are key indicators of mobility and health.

Purpose of the Study:

• To compare three distinct methods for spatiotemporal gait analysis using depth sensor data.
• To evaluate the influence of sensor viewing angles and subject clothing on gait analysis accuracy.
• To determine the most informative and robust method for depth-sensor-based gait analysis.

Main Methods:

• Utilized depth sensor data (Kinect v2) for gait analysis.
• Compared trajectory analysis of knees, feet, and center of mass.
• Assessed accuracy against a reference system (Zebris FDM platform).
• Investigated effects of varying viewing angles and clothing types.

Main Results:

• Viewing angle and clothing significantly impact the uncertainty of spatiotemporal gait parameter estimation.
• The method analyzing foot trajectories provided the richest dataset.
• The center of mass trajectory analysis demonstrated the highest robustness.

Conclusions:

• Depth sensor-based gait analysis is sensitive to environmental factors like viewing angle and clothing.
• Foot trajectory analysis offers comprehensive insights into gait dynamics.
• Center of mass analysis provides a reliable and robust measure for spatiotemporal gait parameters.