Presentation 2001/12/14
3D Reconstruction of Surfaces by Using Scanline Stereo Matching
Yuichi Katase, Natsuki TANI, Masami Iwatsuki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We proposed a new robust method of stereo matching using coarse to fine hierarchical color segmentation of each scanline in stereo images. However, it is difficult to remove fault correspondences in the case of that similar sequences of color segments exist in multiple in the proposed method. Therefore, this paper proposes an approach to detect and modify fault correspondences by taking into account of consistency of disparity of region contours. The proposed method can reconstruct 3D surfaces on matching regions from corner points obtained by 3D line segmentation of the contours by using Delauney triangulation and finite element method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Stereo Macthing / Scanline / Color Segmentation / Region Contour / 3D Reconstruction
Paper # PRMU2001-180
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/12/14(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) 3D Reconstruction of Surfaces by Using Scanline Stereo Matching
Sub Title (in English)
Keyword(1) Stereo Macthing
Keyword(2) Scanline
Keyword(3) Color Segmentation
Keyword(4) Region Contour
Keyword(5) 3D Reconstruction
1st Author's Name Yuichi Katase
1st Author's Affiliation Faculty of Engineering, Hosei University()
2nd Author's Name Natsuki TANI
2nd Author's Affiliation Faculty of Engineering, Hosei University
3rd Author's Name Masami Iwatsuki
3rd Author's Affiliation Faculty of Engineering, Hosei University
Date 2001/12/14
Paper # PRMU2001-180
Volume (vol) vol.101
Number (no) 525
Page pp.pp.-
#Pages 6
Date of Issue