Stereo matching using oriented spatial Habor filters

2016

Closed access Metadata (CSL-JSON)
DOI 10.1117/12.2248323
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

In this paper a method for solving stereo matching problem is presented. It is based on minimization of some energy functional by coarse-to-fine methods with using Habor filters. The solution such task, where presents of occlusions, weakly or periodic textured regions provides some ambiguity for optimization process, using coarse-to-fine method speed up matching process and reduces ambiguity. However due to using low-frequency filtration in coarse-to-fine method blurring of disparity function is appeared exceptionally near objects boundaries. To reduce this luck proposed method based on spatial Habor filtration is used.