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

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, w...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiran Xie, Rui Cao, Hanyang Tong, Sheng Liu, Nianjun Liu
Format: Conference Proceeding
Language:English
Subjects:
Brightness
Image segmentation
Partitioning algorithms
Pixel
Robustness
Shape
Stereo vision
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 higher-order stereo matching approach outperforms conventional stereo matching algorithms, as well as how over-segments improve the stereo matching process.
DOI:10.1109/DICTA.2010.50