Presentation 2007-12-13
Posture Classification by SVM from Bird's-eye View of Range Data
Norihiro TAKAHASHI, Kazumasa YAMAZAWA, Masahiro IKUMO, Masaru NODA, Naokazu YOKOYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Elimination of waste enables to upgrade a product and boost productivity. Improvement activity is done by specialists of Industrial Engineering and plant foreman. It depends on worker's expertise for continuous improvement. In addition, it requires a great investment of time. In this paper, we propose a method of human posture classification for waste detection in the assembly work of human-sized product. In our method, a range image sensor is fixed to a ceiling and captures bird's-eye range images. Features for human posture classification are computed from the bird's-eye range images, human postures are classified by SVM. In simulations of assembly work, we show that our proposed method is useful for human posture classification and waste detection.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) range image sensor / bird's-eye view / posture classification / SVM
Paper # PRMU2007-144
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/12/6(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) Posture Classification by SVM from Bird's-eye View of Range Data
Sub Title (in English)
Keyword(1) range image sensor
Keyword(2) bird's-eye view
Keyword(3) posture classification
Keyword(4) SVM
1st Author's Name Norihiro TAKAHASHI
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Kazumasa YAMAZAWA
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Masahiro IKUMO
3rd Author's Affiliation Sensing & Control Technology Laboratory, OMRON Corporation
4th Author's Name Masaru NODA
4th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
5th Author's Name Naokazu YOKOYA
5th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2007-12-13
Paper # PRMU2007-144
Volume (vol) vol.107
Number (no) 384
Page pp.pp.-
#Pages 6
Date of Issue