Related Experiment Video
Updated: Mar 6, 2026
07:25
An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor
Published on: February 12, 2018
7.3K
Segmentation of human upper body movement using multiple IMU sensors
Summary
This study introduces a new method for segmenting human body movements using inertial measurement unit sensors. The approach achieves over 85.8% accuracy in identifying movement endpoints for upper body motion analysis.
Area of Science:
- Biomechanics
- Robotics
- Human-Computer Interaction
Background:
- Accurate human body movement segmentation is crucial for applications like rehabilitation and human-robot interaction.
- Existing methods often rely on complex joint angle calculations, limiting real-time applicability.
Purpose of the Study:
- To develop a novel, direct approach for segmenting human body movements using raw inertial sensor data.
- To validate the proposed method's effectiveness and accuracy in classifying movement phases.
Main Methods:
- Utilized angular velocity and linear acceleration data directly from inertial measurement unit (IMU) sensors.
- Formulated movement segmentation as a classification problem, training a classifier to distinguish between motion endpoints and in-motion segments.
- Validated the approach using upper body movement data from reaching tasks.
Main Results:
- The proposed segmentation approach achieved a classification accuracy exceeding 85.8% in experimental validation.
- Demonstrated the efficacy of using raw IMU data without intermediate joint angle computation.
Conclusions:
- The direct classification of raw IMU data offers an effective and accurate method for human body movement segmentation.
- This approach simplifies the process and holds potential for real-time applications in various fields.
