Dual-Camera Markerless Motion Capture System for Precise Lower-Limb Kinematic Analysis in Osteoarthritis

Area of Science:

• Biomechanics
• Medical Imaging
• Orthopedics

Background:

• Osteoarthritis (OA) diagnosis and monitoring often rely on accurate lower-limb kinematic analysis.
• Traditional marker-based motion capture systems are effective but costly and complex.
• There is a need for simpler, more accessible methods for kinematic assessment in clinical settings.

Purpose of the Study:

• To develop and validate a dual-camera markerless system for measuring lower-limb kinematics.
• To assess the system's agreement with a gold-standard marker-based motion capture system.
• To evaluate the system's utility for patients with osteoarthritis.

Main Methods:

• A dual-camera markerless system using a neural network-based 2D pose extractor and 3D triangulation was developed.
• Kinematic gait data were collected simultaneously from 152 osteoarthritis patients using both markerless and marker-based systems.
• Agreement was assessed using root mean square distance (RMSD), root mean square error (RMSE), and intraclass correlation coefficient (ICC).

Main Results:

• The markerless system achieved a grand mean RMSD of 11.0 mm and an ICC of 0.95 for keypoints.
• Joint angle analysis showed a mean RMSE of 4.25°.
• ICC values for joint angle waveforms reached 0.90 (sagittal), 0.48 (frontal), and 0.24 (transverse plane).

Conclusions:

• The dual-camera markerless system provides accurate lower-limb kinematic measurements in patient populations.
• The system offers advantages in cost-effectiveness, ease of installation, and reduced expertise requirements.
• This technology facilitates efficient biomechanical assessment for clinical applications.