2003年11月
濃淡値の時系列変化を利用した画像からの手振りの検出
日本ロボット学会誌
- ,
- 巻
- 21
- 号
- 8
- 開始ページ
- 923
- 終了ページ
- 931
- 記述言語
- 日本語
- 掲載種別
- 研究論文(学術雑誌)
- DOI
- 10.7210/jrsj.21.923
- 出版者・発行元
- The Robotics Society of Japan
This paper proposes a method of detecting waving hands from images as a key technology for man-machine interface. FFT is applied to time series of intensity images. The images are converted to low-resolution ones, and FFT is applied to each pixel of the low-resolution images. The proposed method is robust to lighting condition and individual difference of skin color, because it doesn't use color information at all. Experiments show the stability and robustness of the proposed method. Additionally, the method is applied to an omnidirectional vision images and an infrared camera, so as to show the wide applicability of the method.
- リンク情報
- ID情報
-
- DOI : 10.7210/jrsj.21.923
- ISSN : 0289-1824
- CiNii Articles ID : 10012538538
- CiNii Books ID : AN00141189