Related Experiment Video
Updated: Nov 18, 2025
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
963
Synergy-Based Sensor Reduction for Recording the Whole Hand Kinematics
Néstor J Jarque-Bou1, Joaquín L Sancho-Bru1, Margarita Vergara1
1Department of Mechanical Engineering and Construction, Universitat Jaume I, E12071 Castellón, Spain.
Sensors (Basel, Switzerland)
|February 9, 2021
Summary
This study simplifies hand motion tracking by reducing sensors using kinematic synergies. This method accurately estimates 16 joint angles using only 8 key measurements, improving efficiency in motion analysis.
Area of Science:
- Biomechanics
- Human Motion Analysis
- Robotics
Background:
- Simultaneous measurement of hand kinematics is challenging due to sensor limitations.
- Kinematic synergies offer a potential solution by identifying fundamental movement patterns.
Purpose of the Study:
- To reduce the number of sensors required for hand motion tracking.
- To identify and utilize kinematic synergies for efficient hand pose estimation.
Main Methods:
- Extracted 10 kinematic synergies per subject from the KIN-MUS UJI database (22 subjects).
- Clustered synergies to identify key joint angles for estimation.
- Validated the reduced set of 8 joint angles against the KINE-ADL BE-UJI dataset.
Main Results:
- Reduced the original 16 hand joint angles to 8 essential ones.
- Achieved average estimation errors below 10% of the range of motion for most activities.
- Observed cross-activity errors ranging from 3.1% to 16.8%.
Conclusions:
- Kinematic synergies effectively reduce sensor requirements for hand motion capture.
- The proposed 8-joint model provides a robust and accurate representation of hand kinematics.
- This approach enhances the practicality of motion analysis in various applications.
