Skip navigation
Skip navigation

Evaluating Multi-scale Over-segment and Its Contribution to Real Scene Stereo Matching by High-Order MRFs

Xie, Yiran; Cao, Rui; Tong, Hangyang; Liu, Sheng; Liu, Nianjun

Description

The paper is to propose a framework to qualitatively and quantitatively evaluate five of state-of-the-art over-segment approaches. Moreover upon over-segments evaluation, an efficient approach is developed for dense stereo matching through robust higher-order MRFs and graph cut based optimization, which combines the conventional data and smoothness terms with the robust higher-order potential term. The experimental results on real-scene data sets clearly demonstrate that our over-segment-based...[Show more]

CollectionsANU Research Publications
Date published: 2010
Type: Conference paper
URI: http://hdl.handle.net/1885/33270
Source: Proceedings of the Digital Image Computing: Techniques and Applications (DICTA 2010)
DOI: 10.1109/DICTA.2010.50

Download

File Description SizeFormat Image
01_Xie_Evaluating_Multi-scale_2010.pdf986.06 kBAdobe PDF    Request a copy


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

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator