Feature Ensemble Network with Occlusion Disambiguation for Accurate Patch-Based Stereo Matching

Xiaoqing YE  Jiamao LI  Han WANG  Xiaolin ZHANG  

IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.12   pp.3077-3080
Publication Date: 2017/12/01
Publicized: 2017/09/14
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2017EDL8122
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
stereo matching,  convolutional neural network,  patch-based,  occlusion disambiguation,  

Full Text: PDF(886.3KB)>>
Buy this Article

Accurate stereo matching remains a challenging problem in case of weakly-textured areas, discontinuities and occlusions. In this letter, a novel stereo matching method, consisting of leveraging feature ensemble network to compute matching cost, error detection network to predict outliers and priority-based occlusion disambiguation for refinement, is presented. Experiments on the Middlebury benchmark demonstrate that the proposed method yields competitive results against the state-of-the-art algorithms.