Presentation 2009-03-25
Robust Gesture Recognition using Spatio-Temporal Image Processing
Shinichiro MAEDA, Yuya SASAKI, Hideto INUMARU, Yoshihiro OKADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a robust gesture recognition method by using spatio-temporal image processing. Gesture sections are estimated by detecting the movement velocity with two spatio-temporal images: x-t and y-t. Gestures are recognized by comparing the shape of the trace which emerged on spatio-temporal images with the feature model that was previously generated. The spatio-temporal image processing enables us to eliminate small movements and extract motion features derived from major change. Furthermore, we show that the gesture recognition that is robust to noises and illumination changes is available by changing dynamically the threshold of the color extraction in the motion regions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) gesture recognition / motion velocity / spatio-temporal image / human computer interaction
Paper # HCS2008-76
Date of Issue

Conference Information
Committee HCS
Conference Date 2009/3/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Human Communication Science (HCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Robust Gesture Recognition using Spatio-Temporal Image Processing
Sub Title (in English)
Keyword(1) gesture recognition
Keyword(2) motion velocity
Keyword(3) spatio-temporal image
Keyword(4) human computer interaction
1st Author's Name Shinichiro MAEDA
1st Author's Affiliation Division of Media Infomatics, Graduate School of Science and Technology, Ryukoku University()
2nd Author's Name Yuya SASAKI
2nd Author's Affiliation Department of Media Infomatics, Faculty of Science and Technology, Ryukoku University
3rd Author's Name Hideto INUMARU
3rd Author's Affiliation Department of Media Infomatics, Faculty of Science and Technology, Ryukoku University
4th Author's Name Yoshihiro OKADA
4th Author's Affiliation Department of Media Infomatics, Faculty of Science and Technology, Ryukoku University
Date 2009-03-25
Paper # HCS2008-76
Volume (vol) vol.108
Number (no) 487
Page pp.pp.-
#Pages 6
Date of Issue