Presentation	2007-09-04 Anomaly detection using scene segmentation by worker's motion Sanae SHIMIZU, Hidekazu HIRAYU, Hirotsugu ASAI, Yoshinori NIWA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Human error detection is the most important to improve the quality of the products and the productive efficiency. In this paper, we propose a method for detecting mistakes of work operation using movies captured worker's motion. We first segment the movie and classify the scenes of work by extracting motion features, and then detect anomaly by comparing the work pattern with standardized work pattern. Experiments to the movie captured in the real manufacturing premise show the effectiveness of the proposed method.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)
Paper #	PRMU2007-78,HIP2007-87
Date of Issue

Conference Information
Committee	PRMU
Conference Date	2007/8/27(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)	Anomaly detection using scene segmentation by worker's motion
Sub Title (in English)
Keyword(1)
1st Author's Name	Sanae SHIMIZU
1st Author's Affiliation	Gifu Prefectural Research Institute of Information Technology()
2nd Author's Name	Hidekazu HIRAYU
2nd Author's Affiliation	Gifu Prefectural Research Institute of Information Technology
3rd Author's Name	Hirotsugu ASAI
3rd Author's Affiliation	Gifu Prefectural Research Institute of Information Technology
4th Author's Name	Yoshinori NIWA
4th Author's Affiliation	Gifu Prefectural Research Institute of Information Technology
Date	2007-09-04
Paper #	PRMU2007-78,HIP2007-87
Volume (vol)	vol.107
Number (no)	206
Page	pp.pp.-
#Pages	6
Date of Issue