Presentation 2002/5/17
Human Motion Recognition Based on Association Rules from Motion Data
Takaki MORI, Kuniaki UEHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we will propose 3 approaches to recognize human motion automatically. First, we will propose the method to extract association rules which represent the features of the motion from motion data. Next, in order to segment the motion data basad on contains, we will propose the segmentation method using the cepstrum that is known by voice recongniton domain. Finally, we will propose the recognition method not to use segmentation method, matching input data and model data by using RIFCDP. However, to match all body parts costs a lot of running time, so we will try to reduce running time with group.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) motion capture / motion recognition / association rule / primitive motion
Paper # AI2002-2
Date of Issue

Conference Information
Committee AI
Conference Date 2002/5/17(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 Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Human Motion Recognition Based on Association Rules from Motion Data
Sub Title (in English)
Keyword(1) motion capture
Keyword(2) motion recognition
Keyword(3) association rule
Keyword(4) primitive motion
1st Author's Name Takaki MORI
1st Author's Affiliation Faculty of Engineering, Kobe University()
2nd Author's Name Kuniaki UEHARA
2nd Author's Affiliation Faculty of Engineering, Kobe University
Date 2002/5/17
Paper # AI2002-2
Volume (vol) vol.102
Number (no) 91
Page pp.pp.-
#Pages 6
Date of Issue