Gesture recognition with 3D sensors using Hidden Markov Models and clustering
- We propose a method for recognizing dynamic gestures using a 3D sensor. New aspects of the developed system include problem-adapted data conversion and compression as well as automatic detection of different variants of the same gesture via clustering with a suitable metric inspired by Jaccard metric. The combination of Hidden Markov Models and clustering leads to robust detection of different executions based on a small set of training data. We achieved an increase of 5% recognition rate compared to regular Hidden Markov Models. The system has been used for human-machine interaction and might serve as an assistive system in physiotherapy and neurological or orthopedic diagnosis.
| Author of HS Reutlingen | Priwitzer, Barbara |
|---|---|
| DOI: | https://doi.org/10.1109/IWOBI47054.2019.9114513 |
| Erschienen in: | IWOBI 2019 : IEEE International Work Conference on Bioinspired Intelligence : proceeding, July 3-5, 2019, Budapest, Hungary |
| Publisher: | IEEE |
| Place of publication: | Piscataway, NJ |
| Document Type: | Conference proceeding |
| Language: | English |
| Publication year: | 2019 |
| Tag: | HMM; clustering; depth sensor; gesture |
| Page Number: | 6 |
| First Page: | 127 |
| Last Page: | 132 |
| DDC classes: | 004 Informatik |
| Open access?: | Nein |
| Licence (German): |  In Copyright - Urheberrechtlich geschützt |
