mmWave Radar for Sit-to-Stand Analysis: A Comparative Study With Wearables and Kinect.

Area of Science:

• Biomedical Engineering
• Rehabilitation Technology
• Sensor Technology

Background:

• Sit-to-Stand (STS) movement analysis is crucial for assessing mobility and fall risk.
• Current motion capture methods often lack noncontact, privacy-preserving, or continuous monitoring capabilities.
• Millimeterwave (mmWave) radar presents a potential solution for unobtrusive, all-day health monitoring.

Purpose of the Study:

• To investigate the efficacy of mmWave radar for analyzing STS movements.
• To develop a noncontact, privacy-preserving system for healthcare applications.
• To extract clinically relevant features for fall risk assessment using mmWave radar data.

Main Methods:

• Utilized a 60GHz mmWave radar system to collect point cloud data during STS movements from 45 participants.
• Employed deep learning-based pose estimation and Inverse Kinematics (IK) to calculate joint angles.
• Segmented STS motions and extracted features, comparing them with Kinect and wearable sensor data.

Main Results:

• mmWave radar successfully captured general motion patterns and large joint movements, such as trunk motion.
• The system demonstrated potential for noncontact fall risk assessment.
• Challenges were identified in fine-grained motion analysis, indicating areas for future improvement.

Conclusions:

• mmWave radar technology is a viable, noncontact approach for analyzing STS movements in healthcare settings.
• The technology offers advantages in privacy preservation and continuous monitoring.
• Further research with high-precision motion capture systems is needed to validate findings and explore complex movements.