Presentation 2007-09-03
Euclidean Reconstruction from Image Sequences with missing data
Eijiro SHIBUSAWA, Wataru MITSUHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper we address the problem of estimating the Euclidean structure of a scene from uncalibrated perspective cameras. We use a stratified approach in which the projective structure is firstly recovered from image correspondences by the factorization method and in a subsequent step the previous reconstruction is upgraded to the Euclidean structure by self calibration based on the dual absolute quadric. For the matrix factorization involved in the projective reconstruction, we adopt the resection-intersection technique, which can readily handle image sequences with missing data by ignoring the corresponding components. We also provide a technique to incorporate a minimization on a covariance-weighted reprojection error into the projective factorization and a method to handle the singularity constraints of the absolute dual quadric in the linear solution for self-calibration.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # PRMU2007-57,HIP2007-66
Date of Issue

Conference Information
Committee HIP
Conference Date 2007/8/27(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Euclidean Reconstruction from Image Sequences with missing data
Sub Title (in English)
Keyword(1)
1st Author's Name Eijiro SHIBUSAWA
1st Author's Affiliation Graduate School of Electro-Communications, The University of Electro-Communications()
2nd Author's Name Wataru MITSUHASHI
2nd Author's Affiliation Graduate School of Electro-Communications, The University of Electro-Communications
Date 2007-09-03
Paper # PRMU2007-57,HIP2007-66
Volume (vol) vol.107
Number (no) 207
Page pp.pp.-
#Pages 6
Date of Issue