Presentation 2005-11-25
Indoor Event Discrimination by Utilizing Uncalibrated Cameras
Takashi NISHIZAKI, Yoshinari KAMEDA, Yuchi OHTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) With a large number of surveillance cameras, it is not an easy task to determine which camera should be monitored and which region of the camera images should be checked so that all the activities and/or events in a scene are examined. We present a new method to realize effective visual surveillance under an environment in which a number of non-calibrated fixed surveillance cameras are being operated. The method is based on extractions of "regions of interests (ROI)" that are important for visual surveillance, and useful for monitoring multi-view videos of the cameras and automated event detection and/or recognition. In our method, ROIs are extracted by eliminating redundant regions of multi-view images stored on the visual surveillance using multiple cameras. By calculating co-occurrence between each pair of ROIs, our method estimates ROIs where events are to be observed. This helps viewers to know which other ROIs they should check when an events is observed in a certain ROI. In addition, the method can be applied to automated event detection and event recognition on a massive number of multi-view videos.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) massive sensing / multi-view videos / regions of interests / event detection / event recognition
Paper # MVE2005-53
Date of Issue

Conference Information
Committee MVE
Conference Date 2005/11/17(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) Indoor Event Discrimination by Utilizing Uncalibrated Cameras
Sub Title (in English)
Keyword(1) massive sensing
Keyword(2) multi-view videos
Keyword(3) regions of interests
Keyword(4) event detection
Keyword(5) event recognition
1st Author's Name Takashi NISHIZAKI
1st Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba()
2nd Author's Name Yoshinari KAMEDA
2nd Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba
3rd Author's Name Yuchi OHTA
3rd Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba
Date 2005-11-25
Paper # MVE2005-53
Volume (vol) vol.105
Number (no) 433
Page pp.pp.-
#Pages 6
Date of Issue