Presentation 2010-03-16
Study of Extracting Multiple Independently Moving Objects and Estimating the Egomotion from Active Stereo Sequences
Yingdi XIE, Jun OHYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a modified RANSAC based method that can detect multiple independently moving objects from the video sequences acquired by active stereo cameras, and can estimate the egomotion of the stereo cameras. From the optical flows that computed by matching the feature descriptors within temporal frames, a modified RANSAC is adopted to extract the valid egomotion models, under which enough homogenous optical flows can be found. Each of the egomotion models corresponds to either the background or one of the independent moving individuals. The optical flows of the background are then utilized to calculate the real egomotion. Experiments using real stereo sequences demonstrate the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Independent Motion Detection / Egomotion / A Modified RANSAC
Paper # PRMU2009-303,HIP2009-188
Date of Issue

Conference Information
Committee HIP
Conference Date 2010/3/8(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 Human Information Processing (HIP)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Study of Extracting Multiple Independently Moving Objects and Estimating the Egomotion from Active Stereo Sequences
Sub Title (in English)
Keyword(1) Independent Motion Detection
Keyword(2) Egomotion
Keyword(3) A Modified RANSAC
1st Author's Name Yingdi XIE
1st Author's Affiliation Student of GITS, Waseda University()
2nd Author's Name Jun OHYA
2nd Author's Affiliation Student of GITS, Waseda University
Date 2010-03-16
Paper # PRMU2009-303,HIP2009-188
Volume (vol) vol.109
Number (no) 471
Page pp.pp.-
#Pages 6
Date of Issue