Stereo Matching Based on Efficient Image-Guided Cost Aggregation

Yunlong ZHAN  Yuzhang GU  Xiaolin ZHANG  Lei QU  Jiatian PI  Xiaoxia HUANG  Yingguan WANG  Jufeng LUO  Yunzhou QIU  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D   No.3   pp.781-784
Publication Date: 2016/03/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDL8223
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
Keyword: 
stereo matching,  guidance image,  cost aggregation,  guided filter,  bilateral filter,  

Full Text: PDF(734.9KB)>>
Buy this Article




Summary: 
Cost aggregation is one of the most important steps in local stereo matching, while it is difficult to fulfill both accuracy and speed. In this letter, a novel cost aggregation, consisting of guidance image, fast aggregation function and simplified scan-line optimization, is developed. Experiments demonstrate that the proposed algorithm has competitive performance compared with the state-of-art aggregation methods on 32 Middlebury stereo datasets in both accuracy and speed.