ID | 119575 |
Author |
Togo, Shoichiro
Tokushima University
|
Keywords | Gesture recognition
UAV manipulation
feature extraction
hand region estimation
fast Fourier transform
machine learning
OpenPose
long short-term memory
|
Content Type |
Journal Article
|
Description | In this study, we discuss a unmanned aerial vehicle operation system by recognizing human gestures. Here, we focus on both dynamic and static gestures, such as moving the right hand repeatedly or holding it in a certain position. And, we propose two methods, one is a feature-based (FB) method to detect the position of the right hand in an image and identify the gesture form features estimated by FFT, and the other is a machine learning (ML) method to detect the position of the right hand in an image and identify the gesture by the framework of the ML. In experiments, we compare the results of gesture recognition by each method. As a result, the recognition rate of the FB method is higher than that of the ML method under the conditions assumed in the FB method. But, in other cases, the ML method is higher than that of the FB method. The ML method is also effective in terms of extensibility, such as adding more types of gestures.
|
Journal Title |
SICE Journal of Control, Measurement, and System Integration
|
ISSN | 18824889
18849970
|
NCID | AA12293218
|
Publisher | Taylor & Francis
|
Volume | 15
|
Issue | 2
|
Start Page | 145
|
End Page | 161
|
Published Date | 2022-08-05
|
Rights | This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
|
EDB ID | |
DOI (Published Version) | |
URL ( Publisher's Version ) | |
FullText File | |
language |
eng
|
TextVersion |
Publisher
|
departments |
Science and Technology
|