Abstract
Gesture recognition by using Inertial Measurement Unit (IMU) sensors plays an important role in various Internet of Things (IOT) applications, e.g., smart home, intelligent medical system and so on. Traditional technologies usually utilize machine learning algorithms to train different gestures during the offline phase, then recognize the gesture during the online phase. However, such technologies cannot recognize these gestures without prior training. Even for the same gesture, with different gesture amplitude may result in unsuccessful recognition. On the other hand, if we change the person to perform the same gesture, the algorithms also fails. In order to overcome these drawbacks, we propose an approach, which will be able to track the human body motion in real-time and also recognize complicated gestures. Our experiments results show that, the successfully recognition rate of our algorithm is 100%. Furthermore, any part of the human body can be well tracked, the tracking accuracy can reach 0.06m.
| Original language | English |
|---|---|
| Title of host publication | Proceedings : 2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017 |
| Publisher | IEEE Computer Society |
| Pages | 747-754 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781538621295 |
| DOIs | |
| Publication status | Published - 29 May 2018 |
| Externally published | Yes |
| Event | 23rd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2017 - Shenzhen, China Duration: 15 Dec 2017 → 17 Dec 2017 |
Publication series
| Name | Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS |
|---|---|
| Volume | 2017-December |
| ISSN (Print) | 1521-9097 |
Conference
| Conference | 23rd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2017 |
|---|---|
| Country | China |
| City | Shenzhen |
| Period | 15/12/17 → 17/12/17 |
Fingerprint
Keywords
- Gesture-recognition
- IMU
- Motion-tracking
Cite this
}
Fine-grained and real-time gesture recognition by using IMU sensors. / ZHANG, Dian; WU, Xiaofeng; WANG, Chen.
Proceedings : 2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017. IEEE Computer Society, 2018. p. 747-754 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS; Vol. 2017-December).Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review
TY - GEN
T1 - Fine-grained and real-time gesture recognition by using IMU sensors
AU - ZHANG, Dian
AU - WU, Xiaofeng
AU - WANG, Chen
PY - 2018/5/29
Y1 - 2018/5/29
N2 - Gesture recognition by using Inertial Measurement Unit (IMU) sensors plays an important role in various Internet of Things (IOT) applications, e.g., smart home, intelligent medical system and so on. Traditional technologies usually utilize machine learning algorithms to train different gestures during the offline phase, then recognize the gesture during the online phase. However, such technologies cannot recognize these gestures without prior training. Even for the same gesture, with different gesture amplitude may result in unsuccessful recognition. On the other hand, if we change the person to perform the same gesture, the algorithms also fails. In order to overcome these drawbacks, we propose an approach, which will be able to track the human body motion in real-time and also recognize complicated gestures. Our experiments results show that, the successfully recognition rate of our algorithm is 100%. Furthermore, any part of the human body can be well tracked, the tracking accuracy can reach 0.06m.
AB - Gesture recognition by using Inertial Measurement Unit (IMU) sensors plays an important role in various Internet of Things (IOT) applications, e.g., smart home, intelligent medical system and so on. Traditional technologies usually utilize machine learning algorithms to train different gestures during the offline phase, then recognize the gesture during the online phase. However, such technologies cannot recognize these gestures without prior training. Even for the same gesture, with different gesture amplitude may result in unsuccessful recognition. On the other hand, if we change the person to perform the same gesture, the algorithms also fails. In order to overcome these drawbacks, we propose an approach, which will be able to track the human body motion in real-time and also recognize complicated gestures. Our experiments results show that, the successfully recognition rate of our algorithm is 100%. Furthermore, any part of the human body can be well tracked, the tracking accuracy can reach 0.06m.
KW - Gesture-recognition
KW - IMU
KW - Motion-tracking
UR - http://www.scopus.com/inward/record.url?scp=85048378105&partnerID=8YFLogxK
U2 - 10.1109/ICPADS.2017.00100
DO - 10.1109/ICPADS.2017.00100
M3 - Conference paper (refereed)
T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS
SP - 747
EP - 754
BT - Proceedings : 2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017
PB - IEEE Computer Society
ER -