Presentation 2015-03-20
Study of Early Event Recognition Based on 3D Positions of Joints of Human Bodies : Utilizing Skeletons Based on Relative Positions of Joints of Human Bodies in a Lie Group and Max-Margin Early Event Detectors
Naotomo TATEMATSU, Jun OHYA, Larry S. DAVIS,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a method for detecting early events by utilizing 3D Positions of Joints of Human Bodies in RGB and Depth (RGBD) image sequences acquired by Kinect[○!C]. Our method incorporates features based on relative positions of joints of human bodies in a Lie Group into the max-margin early event detectors. Experiments using multiple human actions in real color and depth image sequences demonstrate the effectiveness of our method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Kinect / Early Event Detection / MMED / Skelton
Paper # BioX2014-77,PRMU2014-197
Date of Issue

Conference Information
Committee PRMU
Conference Date 2015/3/12(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) Study of Early Event Recognition Based on 3D Positions of Joints of Human Bodies : Utilizing Skeletons Based on Relative Positions of Joints of Human Bodies in a Lie Group and Max-Margin Early Event Detectors
Sub Title (in English)
Keyword(1) Kinect
Keyword(2) Early Event Detection
Keyword(3) MMED
Keyword(4) Skelton
1st Author's Name Naotomo TATEMATSU
1st Author's Affiliation Graduate School of Global Information and Telecommunication Studies, Waseda University()
2nd Author's Name Jun OHYA
2nd Author's Affiliation Graduate School of Global Information and Telecommunication Studies, Waseda University
3rd Author's Name Larry S. DAVIS
3rd Author's Affiliation University of Maryland
Date 2015-03-20
Paper # BioX2014-77,PRMU2014-197
Volume (vol) vol.114
Number (no) 521
Page pp.pp.-
#Pages 6
Date of Issue