Dense Stereo Matching from Separated Views of Wide-Baseline Images
Refereed conference paper presented and published in conference proceedings

Full Text

Times Cited
Web of Science2WOS source URL (as at 23/05/2020) Click here for the latest count

Other information
AbstractIn this paper, we present a dense stereo matching algorithm from multiple wide-baseline images with separated views. The algorithm utilizes the coarse-to-fine strategy to propagate the sparse feature matching to dense stereo for image pixels. First, the images are segmented into non-overlapping homogeneous partitions. Then, in the coarse step, the initial disparity map is estimated by assigning the sparse feature; correspondences, where the spatial location of these features is incorporated with the over-segmentation. The initial occlusion status is obtained by cross-checking test. Finally, the stereo maps are refined by the proposed discontinuity-preserving regularization algorithm, which directly coupling the disparity and occlusion labeling. The experimental results implemented on the real date sets of challenging samples, including the wide-baseline image pairs with both identical scale and different scale, demonstrated the good subjective performance of the proposed method.
All Author(s) ListZhang QA, Ngan KN
Name of Conference12th International Conference on Advanced Concepts for Intelligent Vision Systems
Start Date of Conference13/12/2010
End Date of Conference16/12/2010
Place of ConferenceSydney
Country/Region of ConferenceAustralia
Journal nameLecture Notes in Artificial Intelligence
Detailed descriptionCSIRO, Australia
Volume Number6474
Pages255 - 266
LanguagesEnglish-United Kingdom
Keywordscolor segmentation; sparse matching; stereo estimation; wide-baseline images
Web of Science Subject CategoriesComputer Science; Computer Science, Information Systems; Computer Science, Theory & Methods

Last updated on 2020-24-05 at 00:07