Segmentation-Based Adaptive Support for Accurate Stereo Correspondence

Significant achievements have been attained in the field of dense stereo correspondence by local algorithms based on an adaptive support. Given the problem of matching two correspondent pixels within a local stereo process, the basic idea is to consider as support for each pixel only those points wh...

Full description

Saved in:
Bibliographic Details
Published inAdvances in Image and Video Technology Vol. 4872; pp. 427 - 438
Main Authors Tombari, Federico, Mattoccia, Stefano, Di Stefano, Luigi
Format Book Chapter
LanguageEnglish
Published Germany Springer Berlin / Heidelberg 2007
Springer Berlin Heidelberg
SeriesLecture Notes in Computer Science
Subjects
Graphical & digital media applications
Image processing
Pattern recognition
segmentation
stereo matching
Stereo vision
variable support
Online AccessGet full text
ISBN9783540771289
354077128X
ISSN0302-9743
1611-3349
DOI10.1007/978-3-540-77129-6_38

Cover

More Information
Summary:Significant achievements have been attained in the field of dense stereo correspondence by local algorithms based on an adaptive support. Given the problem of matching two correspondent pixels within a local stereo process, the basic idea is to consider as support for each pixel only those points which lay on the same disparity plane, rather than those belonging to a fixed support. This paper proposes a novel support aggregation strategy which includes information obtained from a segmentation process. Experimental results on the Middlebury dataset demonstrate that our approach is effective in improving the state of the art.
ISBN:9783540771289
354077128X
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-540-77129-6_38