Presentation 2002/10/11
Analysis Method of Image Sequence Using Temporal Templates
Heetak SHIN, Toshinori WATANABE, Ken SUGAWARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, the accumulation of digital image sequences is rapidly increasing in various fields. Then, retrieval techniques of contents, searching for part of interest in image sequence, and the construction of the system which can automatically summarize and classify the contents, are supposed to become more important in the future. Here, we propose a new method based on the combination of the temporal templates, appearance-based approach to the representation and recognition of movement that is designed to support the direct recognition of the motion itself, and the multi-dimensional feature rectangle method that assists both the abstraction and the comparison of moment vector sets output by temporal templates.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Motion recognition / temporal templates / MEI / MHI / moment / FRC
Paper # NC2002-64
Date of Issue

Conference Information
Committee NC
Conference Date 2002/10/11(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Analysis Method of Image Sequence Using Temporal Templates
Sub Title (in English)
Keyword(1) Motion recognition
Keyword(2) temporal templates
Keyword(3) MEI
Keyword(4) MHI
Keyword(5) moment
Keyword(6) FRC
1st Author's Name Heetak SHIN
1st Author's Affiliation Graduate School of Information Systems, The University of Electro-Communications()
2nd Author's Name Toshinori WATANABE
2nd Author's Affiliation Graduate School of Information Systems, The University of Electro-Communications
3rd Author's Name Ken SUGAWARA
3rd Author's Affiliation Graduate School of Information Systems, The University of Electro-Communications
Date 2002/10/11
Paper # NC2002-64
Volume (vol) vol.102
Number (no) 382
Page pp.pp.-
#Pages 6
Date of Issue