Presentation 2003/12/11
A Method for Human Region Segmentation from Video Image Using Color Information in Combination with Thermal Information
Kazutaka YASUDA, Makoto IIDA, Takeshi NAEMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have implemented the Thermo-Key system for segmenting human region from video sequence in real time using thermal information. This system works well in various background or lighting conditions and can be applied to communication, presentation and other interactive systems. But there is a limit of segmentation when the thermal condition is poor. In this paper, we propose a new method for human region segmentation in poor thermal condition using color information for making up a deficit.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Segmentation / Human Region / Thermal Information / Clustering / K-means Algorithm
Paper # PRMU2003-175
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/12/11(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) A Method for Human Region Segmentation from Video Image Using Color Information in Combination with Thermal Information
Sub Title (in English)
Keyword(1) Image Segmentation
Keyword(2) Human Region
Keyword(3) Thermal Information
Keyword(4) Clustering
Keyword(5) K-means Algorithm
1st Author's Name Kazutaka YASUDA
1st Author's Affiliation School of Information Science and Technology, The University of Tokyo()
2nd Author's Name Makoto IIDA
2nd Author's Affiliation School of Engineering, The University of Tokyo
3rd Author's Name Takeshi NAEMURA
3rd Author's Affiliation School of Information Science and Technology, The University of Tokyo
Date 2003/12/11
Paper # PRMU2003-175
Volume (vol) vol.103
Number (no) 515
Page pp.pp.-
#Pages 6
Date of Issue