Presentation 2008-06-20
Situation-based behavior modeling for anomality detection
Hiromi OKAMOTO, Shuichi NISHIO, Noboru BABAGUCHI, Fujiki MORII, Norihiro HAGITA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we propose a method for anomality detection by classifying people behavior patterns based on situation. In public spaces, people show strong tendency in following some typical patterns. The proposed method learns these patterns from the observed trajectories by composing Hidden Markov Model for each separate situation such as train arrival or departure. Anomalous behaviors are detected by thresholding the output probability. Over 2,401 trajectories observed in an actual train station were used for evaluation which resulted in fine performance with the overall detection rate of 90%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) anomality detection / visual surveillance / situation based model / Hidden Markov Model
Paper # DE2008-19,PRMU2008-37
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/6/12(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) Situation-based behavior modeling for anomality detection
Sub Title (in English)
Keyword(1) anomality detection
Keyword(2) visual surveillance
Keyword(3) situation based model
Keyword(4) Hidden Markov Model
1st Author's Name Hiromi OKAMOTO
1st Author's Affiliation Nara women's University:ATR Intelligent Robotics and Communication Laboratories()
2nd Author's Name Shuichi NISHIO
2nd Author's Affiliation ATR Intelligent Robotics and Communication Laboratories
3rd Author's Name Noboru BABAGUCHI
3rd Author's Affiliation Osaka University:ATR Intelligent Robotics and Communication Laboratories
4th Author's Name Fujiki MORII
4th Author's Affiliation Nara women's University
5th Author's Name Norihiro HAGITA
5th Author's Affiliation ATR Intelligent Robotics and Communication Laboratories
Date 2008-06-20
Paper # DE2008-19,PRMU2008-37
Volume (vol) vol.108
Number (no) 94
Page pp.pp.-
#Pages 6
Date of Issue