Presentation 2021-12-16
A Dataset for Work Instruction Deviation Detection from Field Work Videos
Ryosuke Furuta, Motohiro Takagi, Yusuke Sugano, Yoichi Sato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is important to follow the work instruction manuals for field workers in order to protect them from accidents. In this work, we tackle a new task called "work instruction deviation detection", which aims to detect the behaviors that violate work instruction manuals. Especially, we focus on two types of work instruction deviation: operating with (i) wrong ways and (ii) wrong procedure. To this end, we built a new dataset captured from both first-person and third-person views with annotations, and evaluated baseline methods on the dataset.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Anomaly detection / work instruction deviation detection / field work videos / action recognition
Paper # PRMU2021-30
Date of Issue 2021-12-09 (PRMU)

Conference Information
Committee PRMU
Conference Date 2021/12/16(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Seiichi Uchida(Kyushu Univ.)
Vice Chair Masakazu Iwamura(Osaka Pref. Univ.) / Mitsuru Anpai(Denso IT Lab.)
Secretary Masakazu Iwamura(NTT) / Mitsuru Anpai(Tottori Univ.)
Assistant Kouta Yamaguchi(CyberAgent) / Yusuke Matsui(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Dataset for Work Instruction Deviation Detection from Field Work Videos
Sub Title (in English)
Keyword(1) Anomaly detection
Keyword(2) work instruction deviation detection
Keyword(3) field work videos
Keyword(4) action recognition
1st Author's Name Ryosuke Furuta
1st Author's Affiliation The University of Tokyo(UTokyo)
2nd Author's Name Motohiro Takagi
2nd Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
3rd Author's Name Yusuke Sugano
3rd Author's Affiliation The University of Tokyo(UTokyo)
4th Author's Name Yoichi Sato
4th Author's Affiliation The University of Tokyo(UTokyo)
Date 2021-12-16
Paper # PRMU2021-30
Volume (vol) vol.121
Number (no) PRMU-304
Page pp.pp.37-42(PRMU),
#Pages 6
Date of Issue 2021-12-09 (PRMU)