Related Experiment Videos
A measurement system for the recognition of arm gestures using accelerometers
M E Harrington1, R W Daniel, P J Kyberd
1Oxford Orthopaedic Engineering Centre, Nuffield Orthopaedic Centre, Headington.
Summary
This study presents a novel accelerometer-based method for recognizing arm gestures, offering a new computer input for individuals with motor impairments like cerebral palsy.
Area of Science:
- Biomedical Engineering
- Human-Computer Interaction
- Rehabilitation Technology
Background:
- Computer input methods are challenging for individuals with severe motor impairments, such as athetoid cerebral palsy.
- Existing devices often fail to meet the specific needs of this population.
- Gesture recognition offers a potential alternative for computer interaction.
Purpose of the Study:
- To develop and evaluate an accelerometer-based strategy for measuring arm movements for computer recognition of arm gestures.
- To provide an accessible computer input method for individuals with motor impairments.
Main Methods:
- A model-based approach was used to estimate arm kinematic motion from acceleration data.
- The system models the forearm as a rigid body using four linear accelerometers.
- Data were reduced to step inputs suitable for pattern classification and recognition.
Main Results:
- The data parameterization successfully preserved the information content of arm gestures.
- Initial experimental results demonstrate the viability of the approach.
- The method provides a foundation for developing effective gesture recognition systems.
Conclusions:
- The proposed accelerometer-based strategy is effective for capturing arm gesture information.
- This approach shows promise as an alternative computer input for individuals with motor impairments.
- Further development could enhance accessibility and usability for target users.