Presentation 2006-03-16
Egomotion Analysis with Uncorrelated Optical Flow
Ryo TAKADA, Halyuan WU, Toshikazu WADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the case of wide area video surveillance, it is useful to detect moving objects from image sequences taken by a pan-tilt active camera. We consider this optical flow is separable because it is mixed by the background flow and moving object flow. In this paper, we propose an algorithm, which detects moving objects by whitening the optical flow obtained from the image sequences. Our method can detect the moving objects independent on the rotation of pan/tilt, by preparing only one arbitrary uniform flow. Through various experiments, we confirm the effectiveness of proposed algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Detection Moving Object / Egomotion Analysis / Whitening
Paper # PRMU2005-238
Date of Issue

Conference Information
Committee PRMU
Conference Date 2006/3/9(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) Egomotion Analysis with Uncorrelated Optical Flow
Sub Title (in English)
Keyword(1) Detection Moving Object
Keyword(2) Egomotion Analysis
Keyword(3) Whitening
1st Author's Name Ryo TAKADA
1st Author's Affiliation Graduate School of System Engineering, Wakayama University()
2nd Author's Name Halyuan WU
2nd Author's Affiliation Graduate School of System Engineering, Wakayama University
3rd Author's Name Toshikazu WADA
3rd Author's Affiliation Graduate School of System Engineering, Wakayama University
Date 2006-03-16
Paper # PRMU2005-238
Volume (vol) vol.105
Number (no) 673
Page pp.pp.-
#Pages 8
Date of Issue