Presentation 2005-02-24
Realtime Human Action Recognition using High Speed Calculation of Subgraph Similarity in Feature Space
Hiroki SHIMONO, MASAMI Sato, Hitoshi KITAZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) An extension of human action detection by the similarity of subgraphs which represent action templates and measurement is presented. Based on the continuous DP Matching, a high speed and frame-to-frame calculation method of subgraph similarity is proposed. Experimental results of compound action detection are shown.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) recognizing human action / silhouette / feature space / subgraphs / shortest path search / continuous DP Matching
Paper # NLC2004-115,PRMU2004-197
Date of Issue

Conference Information
Committee NLC
Conference Date 2005/2/17(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Realtime Human Action Recognition using High Speed Calculation of Subgraph Similarity in Feature Space
Sub Title (in English)
Keyword(1) recognizing human action
Keyword(2) silhouette
Keyword(3) feature space
Keyword(4) subgraphs
Keyword(5) shortest path search
Keyword(6) continuous DP Matching
1st Author's Name Hiroki SHIMONO
1st Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology()
2nd Author's Name MASAMI Sato
2nd Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology
3rd Author's Name Hitoshi KITAZAWA
3rd Author's Affiliation Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology
Date 2005-02-24
Paper # NLC2004-115,PRMU2004-197
Volume (vol) vol.104
Number (no) 667
Page pp.pp.-
#Pages 6
Date of Issue