Accurate and dense wide-baseline stereo matching using SW-POC

Shuji Sakai, Koichi Ito, Takafumi Aoki, Hiroki Unten

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper proposes an accurate and dense wide-baseline stereo matching method using Scaled Window Phase-Only Correlation (SW-POC). The wide-baseline setting of the stereo camera can improve the accuracy of the 3D reconstruction compared with the short-baseline setting. However, it is difficult to find accurate and dense correspondence from wide-baseline stereo images due to its large perspective distortion. Addressing this problem, we employ the SW-POC, which is a correspondence matching method using 1D POC with the concept of Scale Window Matching (SWM). The use of SW-POC makes it possible to find the accurate and dense correspondence from a wide-baseline stereo image pair with low computational cost. We also apply the proposed method to 3D reconstruction using a moving and uncalibrated consumer digital camera.

Original languageEnglish
Title of host publication1st Asian Conference on Pattern Recognition, ACPR 2011
Pages335-339
Number of pages5
DOIs
Publication statusPublished - 2011 Dec 1
Event1st Asian Conference on Pattern Recognition, ACPR 2011 - Beijing, China
Duration: 2011 Nov 282011 Nov 28

Publication series

Name1st Asian Conference on Pattern Recognition, ACPR 2011

Other

Other1st Asian Conference on Pattern Recognition, ACPR 2011
CountryChina
CityBeijing
Period11/11/2811/11/28

Keywords

  • 3D reconstruction
  • Scaled Window Phase-Only Correlation
  • stereo correspondence
  • wide-baseline stereo

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Accurate and dense wide-baseline stereo matching using SW-POC'. Together they form a unique fingerprint.

Cite this