Presentation 2014-03-06
Abnormal Scene Extraction in Machinery Operation using Spatio-temporal Feature and Unsupervised Learning
Hiromitsu KOBAYASHI, Kota AOKI, Hiroshi NAGAHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a new method for extracting abnormal scene in the video of periodic machinery operations. Firstly, we segment the video into periods and extract STIPs (Space-time Interest Points). Then, we examine frequency of appearance of STIPs to determine ROIs (regions of interest). After the calculation of features in the ROIs, abnormality of each segment is estimated by 1 class SVM (1 class Support Vector Machine). We conducted some experiments to compare the proposed method with conventional methods using PCA (Principal Component Analysis) and confirmed that our method is sensitive to the variation of the machinery motion and robust against background and illumination variations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spatio-temporal Feature / Unsupervised Learning / Anomaly Detection
Paper # IMQ2013-41,IE2013-150,MVE2013-79
Date of Issue

Conference Information
Committee MVE
Conference Date 2014/2/27(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Abnormal Scene Extraction in Machinery Operation using Spatio-temporal Feature and Unsupervised Learning
Sub Title (in English)
Keyword(1) Spatio-temporal Feature
Keyword(2) Unsupervised Learning
Keyword(3) Anomaly Detection
1st Author's Name Hiromitsu KOBAYASHI
1st Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology()
2nd Author's Name Kota AOKI
2nd Author's Affiliation Imaging Science and Engineering Laboratory, Tokyo Institute of Technology
3rd Author's Name Hiroshi NAGAHASHI
3rd Author's Affiliation Imaging Science and Engineering Laboratory, Tokyo Institute of Technology
Date 2014-03-06
Paper # IMQ2013-41,IE2013-150,MVE2013-79
Volume (vol) vol.113
Number (no) 470
Page pp.pp.-
#Pages 6
Date of Issue