Presentation 2001/7/11
The Method to Detect One's Action by Analysis of Sequential View Images in Everyday Life
Toshimasa IIJIMA, Toshio KAWASHIMA, Yoshinao AOKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we propose the method to detect and recognize one's antion by analysis of sequential view images in everyday life. In this method, we estimate user's head motion using optical flow by multi resolution images with gaussian filter to reduce the noises. And to acquire a user's hand position and track it from imput images, we use the color feature of human hand by the L^*a^*b color space. Obsering user's head motion and hand motion, we recognize user's action and it's kind, and detect target objects in qutomatically.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Recording action history / Optical flow / Skin region detection / Motion Estimation
Paper # IE2001-30,PRMU2001-50,MVE2001-29
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/7/11(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The Method to Detect One's Action by Analysis of Sequential View Images in Everyday Life
Sub Title (in English)
Keyword(1) Recording action history
Keyword(2) Optical flow
Keyword(3) Skin region detection
Keyword(4) Motion Estimation
1st Author's Name Toshimasa IIJIMA
1st Author's Affiliation Graduate School of Engineering, Hokkaido University()
2nd Author's Name Toshio KAWASHIMA
2nd Author's Affiliation Department of Media Architecture, FUTURE UNIVERSITY-HAKODATE
3rd Author's Name Yoshinao AOKI
3rd Author's Affiliation Graduate School of Engineering, Hokkaido University
Date 2001/7/11
Paper # IE2001-30,PRMU2001-50,MVE2001-29
Volume (vol) vol.101
Number (no) 202
Page pp.pp.-
#Pages 8
Date of Issue