直近一年間の累計
アクセス数 : ?
ダウンロード数 : ?
ID 119575
著者
Togo, Shoichiro Tokushima University
キーワード
Gesture recognition
UAV manipulation
feature extraction
hand region estimation
fast Fourier transform
machine learning
OpenPose
long short-term memory
資料タイプ
学術雑誌論文
抄録
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.
掲載誌名
SICE Journal of Control, Measurement, and System Integration
ISSN
18824889
18849970
cat書誌ID
AA12293218
出版者
Taylor & Francis
15
2
開始ページ
145
終了ページ
161
発行日
2022-08-05
権利情報
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
出版社版DOI
出版社版URL
フルテキストファイル
言語
eng
著者版フラグ
出版社版
部局
理工学系