Presentation 2008-12-18
Human Activity Recognition Based on Camera Selection by Boosting
Kouji SHUTOU, Seiichi UCHIDA, Ken'ichi MOROOKA, Ryo KURAZUME, Kenji HARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A gesture recognition method for multi-camera surveillance is proposed. The proposed method possesses the following three characteristics desirable for practical surveillans. First, the final recognition result is provided by integrating recognition results from individual cameras complementary. Second, camera calibration is not necessary. Third, various sensors other than cameras can be incorporated. The complementary integration is systematically done by an AdaBoost-based training. In addition, we use the local feature which is less discriminative to the important difference among the gestures.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multi-camera / gesture recognition / AdaBoost / local feature
Paper # PRMU2008-157
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/12/11(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) Human Activity Recognition Based on Camera Selection by Boosting
Sub Title (in English)
Keyword(1) multi-camera
Keyword(2) gesture recognition
Keyword(3) AdaBoost
Keyword(4) local feature
1st Author's Name Kouji SHUTOU
1st Author's Affiliation Kyushu University()
2nd Author's Name Seiichi UCHIDA
2nd Author's Affiliation Kyushu University
3rd Author's Name Ken'ichi MOROOKA
3rd Author's Affiliation Kyushu University
4th Author's Name Ryo KURAZUME
4th Author's Affiliation Kyushu University
5th Author's Name Kenji HARA
5th Author's Affiliation Kyushu University
Date 2008-12-18
Paper # PRMU2008-157
Volume (vol) vol.108
Number (no) 363
Page pp.pp.-
#Pages 6
Date of Issue