Fine-grained and real-time gesture recognition by using IMU sensors

Dian ZHANG; Xiaofeng WU; Chen WANG

doi:10.1109/ICPADS.2017.00100

Fine-grained and real-time gesture recognition by using IMU sensors

Dian ZHANG^*
, Xiaofeng WU
, Chen WANG

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

4 Citations (Scopus)

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	2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017 : Proceedings
Publisher	IEEE Computer Society
Pages	747-754
Number of pages	8
ISBN (Electronic)	9781538621295
ISBN (Print)	9781538632086
DOIs	https://doi.org/10.1109/ICPADS.2017.00100
Publication status	Published - 2017
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/Territory	China
City	Shenzhen
Period	15/12/17 → 17/12/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Funding

This research was supported in part by Shenzhen Peacock Talent Grant 827-000175, Guangdong Natural Science Foundation (2016A030313036 Shenzhen Science and Technology Foundation (JCYJ20150324140036842) and NSF-China and Guangdong Province Joint Project: U1301252.

Keywords

Gesture-recognition
IMU
Motion-tracking

Access to Document

10.1109/ICPADS.2017.00100

Cite this

ZHANG, D., WU, X., & WANG, C. (2017). Fine-grained and real-time gesture recognition by using IMU sensors. In 2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017 : Proceedings (pp. 747-754). (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS; Vol. 2017-December). IEEE Computer Society. https://doi.org/10.1109/ICPADS.2017.00100

@inproceedings{5843d682a19d49d3bf63091b513949c9,

title = "Fine-grained and real-time gesture recognition by using IMU sensors",

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.",

keywords = "Gesture-recognition, IMU, Motion-tracking",

author = "Dian ZHANG and Xiaofeng WU and Chen WANG",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 23rd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2017 ; Conference date: 15-12-2017 Through 17-12-2017",

year = "2017",

doi = "10.1109/ICPADS.2017.00100",

language = "English",

isbn = "9781538632086",

series = "Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS",

publisher = "IEEE Computer Society",

pages = "747--754",

booktitle = "2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017 : Proceedings",

address = "United States",

}

ZHANG, D, WU, X & WANG, C 2017, Fine-grained and real-time gesture recognition by using IMU sensors. in 2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017 : Proceedings. Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS, vol. 2017-December, IEEE Computer Society, pp. 747-754, 23rd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2017, Shenzhen, China, 15/12/17. https://doi.org/10.1109/ICPADS.2017.00100

Fine-grained and real-time gesture recognition by using IMU sensors. / ZHANG, Dian; WU, Xiaofeng; WANG, Chen.
2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017 : Proceedings. IEEE Computer Society, 2017. 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) › Referred Conference Paper › 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 - 2017

Y1 - 2017

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 - https://www.scopus.com/pages/publications/85048378105

U2 - 10.1109/ICPADS.2017.00100

DO - 10.1109/ICPADS.2017.00100

M3 - Conference paper (refereed)

AN - SCOPUS:85048378105

SN - 9781538632086

T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS

SP - 747

EP - 754

BT - 2017 IEEE 23rd International Conference on Parallel and Distributed Systems, ICPADS 2017 : Proceedings

PB - IEEE Computer Society

T2 - 23rd IEEE International Conference on Parallel and Distributed Systems, ICPADS 2017

Y2 - 15 December 2017 through 17 December 2017

ER -

Fine-grained and real-time gesture recognition by using IMU sensors

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this