Graph-based surface reconstruction from stereo pairs using image segmentation

Michael Bleyer; Margrit Gelautz

doi:10.1117/12.586502

17 January 2005 Graph-based surface reconstruction from stereo pairs using image segmentation

Michael Bleyer, Margrit Gelautz

Proceedings Volume 5665, Videometrics VIII; 56650U (2005) https://doi.org/10.1117/12.586502
Event: Electronic Imaging 2005, 2005, San Jose, California, United States

Abstract

This paper describes a novel stereo matching algorithm for epipolar rectified images. The method applies colour segmentation on the reference image. The use of segmentation makes the algorithm capable of handling large untextured regions, estimating precise depth boundaries and propagating disparity information to occluded regions, which are challenging tasks for conventional stereo methods. We model disparity inside a segment by a planar equation. Initial disparity segments are clustered to form a set of disparity layers, which are planar surfaces that are likely to occur in the scene. Assignments of segments to disparity layers are then derived by minimization of a global cost function via a robust optimization technique that employs graph cuts. The cost function is defined on the pixel level, as well as on the segment level. While the pixel level measures the data similarity based on the current disparity map and detects occlusions symmetrically in both views, the segment level propagates the segmentation information and incorporates a smoothness term. New planar models are then generated based on the disparity layers' spatial extents. Results obtained for benchmark and self-recorded image pairs indicate that the proposed method is able to compete with the best-performing state-of-the-art algorithms.

Citation Download Citation

Michael Bleyer and Margrit Gelautz "Graph-based surface reconstruction from stereo pairs using image segmentation", Proc. SPIE 5665, Videometrics VIII, 56650U (17 January 2005); https://doi.org/10.1117/12.586502

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available