Presentation 2011-02-18
Human Attribute Analysis using a Ceiling Camera in a Public Space
Tomoaki MATSUNAMI, Toshihiko YAMASAKI, Kiyoharu AIZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a method for analyzing human attributes such us sex and whether he or she has a baggage or not. We focused time variation of the human position, shape, and their contours. We extracted the pedestrians' features using center of gravities of human coordinate, human area, and Fourier descriptors of human contours. We classified pedestrians' sex and whether he or she has baggage or not. We conducted experiments 60 munities video captured by a ceiling camera at the Haneda airport. Experimental results show that the classification accuracy is 68.5% for sex classification and 78.2% for classifying "with/without baggage."
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Surveillance system / Human tracking / Attribute analysis
Paper # PRMU2010-229
Date of Issue

Conference Information
Committee PRMU
Conference Date 2011/2/10(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) Human Attribute Analysis using a Ceiling Camera in a Public Space
Sub Title (in English)
Keyword(1) Surveillance system
Keyword(2) Human tracking
Keyword(3) Attribute analysis
1st Author's Name Tomoaki MATSUNAMI
1st Author's Affiliation Department of Information and Communication Engineering, The University of Tokyo()
2nd Author's Name Toshihiko YAMASAKI
2nd Author's Affiliation Department of Information and Communication Engineering, The University of Tokyo
3rd Author's Name Kiyoharu AIZAWA
3rd Author's Affiliation Interfaculty Initiative in Information Studies, The University of Tokyo:Department of Information and Communication Engineering, The University of Tokyo
Date 2011-02-18
Paper # PRMU2010-229
Volume (vol) vol.110
Number (no) 414
Page pp.pp.-
#Pages 6
Date of Issue