Progressive Matching Based On Segmentation for 3D reconstruction

Author

YongZhuang Ma ; Weijun Liu

Author_Institution

Shenyang Inst. of Autom., Chinese Acad. of Sci. Shenyang, Liaoning

fYear

2005

fDate

21-23 Sept. 2005

Firstpage

575

Lastpage

579

Abstract

Dense matching plays an important role for 3D scene reconstruction. A simple rectified algorithm is given in this paper. Then the new matching algorithm starts from GCPS as seeds with rectified stereo pairs. First color segment is used to capture disparity discontinuity and the reliable seed point from GCPS which is computed by using fast ZNCC based on asymmetric window can propagate the other correspondence points according to continuity constraint in each region. The algorithm is demonstrated on standard images pairs and shows better applications on 3D reconstruction

Keywords

image colour analysis; image matching; image segmentation; stereo image processing; 3D scene reconstruction; asymmetric window; color segment; dense image matching; ground control points; images pairs; progressive image matching algorithm; rectified stereo pairs; Automation; Computer vision; Image reconstruction; Image segmentation; Layout; Mobile robots; Navigation; Remotely operated vehicles; Stereo image processing; Stereo vision; GCPS; correlation; dense match; segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Technology, 2005. CIT 2005. The Fifth International Conference on

Conference_Location

Shanghai

Print_ISBN

0-7695-2432-X

Type

conf

DOI

10.1109/CIT.2005.157

Filename

1562714