Concurrent Validity of Motion Parameters Measured With an RGB-D Camera-Based Markerless 3D Motion Tracking Method in...

Area of Science:

• Biomechanics
• Medical Technology
• Human Movement Analysis

Background:

• Low-cost, portable RGB-D cameras offer accessible 3D motion analysis.
• Existing systems lack accuracy for clinical applications, especially in pediatrics.
• Previous work developed an accurate RGB-D camera-based tracking method for children and young adults.

Purpose of the Study:

• To evaluate the validity and accuracy of clinically relevant motion parameters derived from an RGB-D camera-based tracking method.
• To assess the system's suitability for clinical motion analysis in pediatric and young adult populations.

Main Methods:

• Twenty-three children and young adults (5-29 years) performed five movement tasks.
• Simultaneous recording using a marker-based Vicon system and an Azure Kinect RGB-D camera.
• Analysis of time series, peak measurements, and movement smoothness using correlation coefficients and mean absolute error (MAE).

Main Results:

• Time series measurements showed strong to excellent correlations (r=0.8-1.0).
• MAE for angles: 1.5-5 degrees; for distance parameters: 9-15 mm.
• MAE for smoothness parameters (SPARC): 0.02-0.09.

Conclusions:

• The RGB-D camera-based motion tracking method provides valid and accurate motion parameters for children and young adults.
• The system is suitable for clinical motion analysis across various movement tasks.
• This technology enables motion analysis outside specialized settings, approaching clinical gold-standard accuracy.