Stereo matching using gradient similarity and locally adaptive support-weight


Journal Article

Due to the similarities between neighbouring pixels as well as the intensity-value differences between corresponding pixels, classical matching measures based on intensity similarity produce slightly imprecise results. In this study, a gradient similarity-matching measure was implemented in a state-of-the-art local stereo-matching method (an adaptive support-weight algorithm). The new matching measure improved the precision of the results over the classical measures. Using the Middlebury stereo benchmark, when high accuracy was required in the disparity results our algorithm consistently outperformed other adaptive support-weight algorithms using different similarity measures, and it was the best local area-based method compared to the permanent Middlebury table entries. © 2011 Elsevier B.V. All rights reserved.

Full Text

Duke Authors

Cited Authors

  • De-Maeztu, L; Villanueva, A; Cabeza, R

Published Date

  • October 1, 2011

Published In

Volume / Issue

  • 32 / 13

Start / End Page

  • 1643 - 1651

International Standard Serial Number (ISSN)

  • 0167-8655

Digital Object Identifier (DOI)

  • 10.1016/j.patrec.2011.06.027

Citation Source

  • Scopus