A Segmentation-Based Multiple-Baseline Stereo (SMBS) Scheme for Acquisition of Depth in 3-D Scenes

Takashi IMORI  Tadahiko KIMOTO  Bunpei TOUJI  Toshiaki FUJII  Masayuki TANIMOTO  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E81-D   No.2   pp.215-223
Publication Date: 1998/02/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Processing,Computer Graphics and Pattern Recognition
Keyword: 
multiple-baseline stereo,  region segmentation,  stereo matching,  error correction,   interpolated viewpoint,  

Full Text: PDF(1.4MB)>>
Buy this Article




Summary: 
This paper presents a new scheme to estimate depth in a natural three-dimensional scene using a multi-viewpoint image set. In the conventional Multiple-Baseline Stereo (MBS) scheme for the image set, although errors of stereo matching are somewhat reduced by using multiple stereo pairs, the use of square blocks of fixed size sometimes causes false matching, especially, in that image area where occlusion occurs and that image area of small variance of brightness levels. In the proposed scheme, the reference image is segmented into regions which are capable of being arbitrarily shaped, and a depth value is estimated for each region. Also, by comparing the image generated by projection with the original image, depth values are newly estimated in a top-down manner. Then, the error of the previous depth value is detected, and it is corrected. The results of experiments show advantages of the proposed scheme over the MBS scheme.