Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/18341

Title: Iterative Refinement for Real-time Local Stereo Matching
Authors: DUMONT, Maarten
GOORTS, Patrik
MAESEN, Steven
BEKAERT, Philippe
LAFRUIT, Gauthier
Issue Date: 2014
Publisher: IEEE Xplore
Citation: Proceedings of 3D Stereo Media
Series/Report: International Conference on 3D Imaging (IC3D)
Abstract: We present a novel iterative refinement process to apply to any stereo matching algorithm. The quality of its disparity map output is increased using four rigorously defined refinement modules, which can be iterated multiple times: a disparity cross check, bitwise fast voting, invalid disparity handling, and median filtering. We apply our refinement process to our recently developed aggregation window method for stereo matching that combines two adaptive windows per pixel region [2]; 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. We demonstrate that the iterative disparity refinement has a large effect on the overall quality, especially around occluded areas, and tends to converge to a final solution. We perform a quantitative evaluation on various Middlebury datasets. Our whole disparity estimation process supports efficient GPU implementation to facilitate scalability and real-time performance.
URI: http://hdl.handle.net/1942/18341
DOI: 10.1109/IC3D.2014.7032581
ISI #: 000380557000010
ISBN: 9781479980239
ISSN: 2379-1772
Category: C1
Type: Proceedings Paper
Validation: ecoom, 2017
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
N/A502.78 kBAdobe PDF

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