Abstract
This paper describes a gesture recognition system which can recognize seated exercises that will be incorporated into an in-home automated interactive exercise program. Hidden Markov Models (HMMs) are used as a motion classifier, with motion features extracted from the grayscale images and the location of the subject's head estimated at initialization. An overall recognition rate of 94.1% is achieved.
Original language | English (US) |
---|---|
Pages (from-to) | 1915-1917 |
Number of pages | 3 |
Journal | Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference |
State | Published - 2008 |
ASJC Scopus subject areas
- Signal Processing
- Biomedical Engineering
- Computer Vision and Pattern Recognition
- Health Informatics