www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/21655

Title: Real-Time Edge-Sensitive Local Stereo Matching with Iterative Disparity Refinement
Authors: Dumont, Maarten
Goorts, Patrik
Maesen, Steven
Lafruit, Gauthier
Bekaert, Philippe
Issue Date: 2015
Publisher: Springer International Publishing
Citation: Obaidat, M.S.; Holzinger, A.; Filipe, J. (Ed.). E-Business and Telecommunications: 11th International Joint Conference, ICETE 2014, Vienna, Austria, August 28-30, 2014, Revised Selected Papers, p. 435-456
Series/Report: Communications in Computer and Information Science
Series/Report no.: 554
Abstract: First, we present a novel cost aggregation method for stereo matching that uses two edge-sensitive shape-adaptive support windows per pixel region; one following the horizontal edges in the image, the other the vertical edges. Their combination defines the final aggregation window shape that closely follows all object edges and thereby achieves increased hypothesis confidence. Second, we present a novel iterative disparity refinement process and apply it to the initially estimated disparity map. The process consists of four rigorously defined and lightweight modules that can be iterated multiple times: a disparity cross check, bitwise fast voting, invalid disparity handling, and median filtering. We demonstrate that our iterative refinement has a large effect on the overall quality, resulting in smooth disparity maps with sharp object edges, especially around occluded areas. It can be applied to any stereo matching algorithm and tends to converge to a final solution. Finally, we perform a quantitative evaluation on various Middlebury datasets, showing an increase in quality of over several dB PSNR compared with their ground truth. Our whole disparity estimation algorithm supports efficient GPU implementation to facilitate scalability and real-time performance.
Notes: [Dumont, Maarten; Goorts, Patrik; Maesen, Steven; Bekaert, Philippe] Hasselt Univ, tUL, iMinds, Expertise Ctr Digital Media, Wetenschapspk 2, B-3590 Diepenbeek, Belgium. [Lafruit, Gauthier] Univ Brussels, Univ Libre Bruxelles, LISA Dept, B-1050 Brussels, Belgium.
URI: http://hdl.handle.net/1942/21655
DOI: 10.1007/978-3-319-25915-4_23
ISI #: 000369316300023
ISBN: 978-3-319-25914-7
ISSN: 1865-0929
Category: C1
Type: Proceedings Paper
Validation: ecoom, 2017
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
published version9.11 MBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.