Authors:
Marcus Georgi
;
Christoph Amma
and
Tanja Schultz
Affiliation:
Karlsruhe Institute of Technology, Germany
Keyword(s):
Wearable Computing, Gesture Recognition, Inertial Measurement Unit, Electromyography.
Related
Ontology
Subjects/Areas/Topics:
Animation and Simulation
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Data Manipulation
;
Devices
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Human-Computer Interaction
;
Methodologies and Methods
;
Motion Control
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Soft Computing
;
Wearable Sensors and Systems
Abstract:
Session- and person-independent recognition of hand and finger gestures is of utmost importance for the
practicality of gesture based interfaces. In this paper we evaluate the performance of a wearable gesture
recognition system that captures arm, hand, and finger motions by measuring movements of, and muscle
activity at the forearm. We fuse the signals of an Inertial Measurement Unit (IMU) worn at the wrist, and the
Electromyogram (EMG) of muscles in the forearm to infer hand and finger movements. A set of 12 gestures
was defined, motivated by their similarity to actual physical manipulations and to gestures known from the
interaction with mobile devices. We recorded performances of our gesture set by five subjects in multiple
sessions. The resulting datacorpus will be made publicly available to build a common ground for future
evaluations and benchmarks. Hidden Markov Models (HMMs) are used as classifiers to discriminate between
the defined gesture classes. We achieve a re
cognition rate of 97.8% in session-independent, and of 74.3% in
person-independent recognition. Additionally, we give a detailed analysis of error characteristics and of the
influence of each modality to the results to underline the benefits of using both modalities together
(More)