Line matching in wide-baseline stereo

A top-down approach

Mohammed Al-Shahri, Alper Yilmaz

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

This paper introduces a new algorithm for matching lines across images that exploit the epipolar geometry and the coplanarity constraints between pairs of lines. In contrast to common treatment in matching of interest points, we use the epipolar geometry to constrain coplanarity conditions between line-pairs. This treatment eliminates the potential matching problems due to the incomplete line observations with nonmatching endpoints. This observation is used to detect a set of candidate line-pair correspondences. These matching pairs are then verified via local homography transforms derived from the neighboring interest point correspondences. This step results in a line affinity matrix, which is processed to obtain matching lines. During this process, we do not use appearance models and show that the proposed treatment performs better than the state-of-the-art appearance and geometry-based methods, especially for images with wide-baseline.

Original languageEnglish
Article number6837536
Pages (from-to)4199-4210
Number of pages12
JournalIEEE Transactions on Image Processing
Volume23
Issue number9
DOIs
Publication statusPublished - 2014

Fingerprint

Geometry

Keywords

  • Coplanarity
  • Epipolar geometry
  • Line matching
  • Wide-baseline

ASJC Scopus subject areas

  • Software
  • Medicine(all)
  • Computer Graphics and Computer-Aided Design

Cite this

Line matching in wide-baseline stereo : A top-down approach. / Al-Shahri, Mohammed; Yilmaz, Alper.

In: IEEE Transactions on Image Processing, Vol. 23, No. 9, 6837536, 2014, p. 4199-4210.

Research output: Contribution to journalArticle

@article{86d3d6f8ba414eaf8833e904511a1575,
title = "Line matching in wide-baseline stereo: A top-down approach",
abstract = "This paper introduces a new algorithm for matching lines across images that exploit the epipolar geometry and the coplanarity constraints between pairs of lines. In contrast to common treatment in matching of interest points, we use the epipolar geometry to constrain coplanarity conditions between line-pairs. This treatment eliminates the potential matching problems due to the incomplete line observations with nonmatching endpoints. This observation is used to detect a set of candidate line-pair correspondences. These matching pairs are then verified via local homography transforms derived from the neighboring interest point correspondences. This step results in a line affinity matrix, which is processed to obtain matching lines. During this process, we do not use appearance models and show that the proposed treatment performs better than the state-of-the-art appearance and geometry-based methods, especially for images with wide-baseline.",
keywords = "Coplanarity, Epipolar geometry, Line matching, Wide-baseline",
author = "Mohammed Al-Shahri and Alper Yilmaz",
year = "2014",
doi = "10.1109/TIP.2014.2331147",
language = "English",
volume = "23",
pages = "4199--4210",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

TY - JOUR

T1 - Line matching in wide-baseline stereo

T2 - A top-down approach

AU - Al-Shahri, Mohammed

AU - Yilmaz, Alper

PY - 2014

Y1 - 2014

N2 - This paper introduces a new algorithm for matching lines across images that exploit the epipolar geometry and the coplanarity constraints between pairs of lines. In contrast to common treatment in matching of interest points, we use the epipolar geometry to constrain coplanarity conditions between line-pairs. This treatment eliminates the potential matching problems due to the incomplete line observations with nonmatching endpoints. This observation is used to detect a set of candidate line-pair correspondences. These matching pairs are then verified via local homography transforms derived from the neighboring interest point correspondences. This step results in a line affinity matrix, which is processed to obtain matching lines. During this process, we do not use appearance models and show that the proposed treatment performs better than the state-of-the-art appearance and geometry-based methods, especially for images with wide-baseline.

AB - This paper introduces a new algorithm for matching lines across images that exploit the epipolar geometry and the coplanarity constraints between pairs of lines. In contrast to common treatment in matching of interest points, we use the epipolar geometry to constrain coplanarity conditions between line-pairs. This treatment eliminates the potential matching problems due to the incomplete line observations with nonmatching endpoints. This observation is used to detect a set of candidate line-pair correspondences. These matching pairs are then verified via local homography transforms derived from the neighboring interest point correspondences. This step results in a line affinity matrix, which is processed to obtain matching lines. During this process, we do not use appearance models and show that the proposed treatment performs better than the state-of-the-art appearance and geometry-based methods, especially for images with wide-baseline.

KW - Coplanarity

KW - Epipolar geometry

KW - Line matching

KW - Wide-baseline

UR - http://www.scopus.com/inward/record.url?scp=84940299226&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940299226&partnerID=8YFLogxK

U2 - 10.1109/TIP.2014.2331147

DO - 10.1109/TIP.2014.2331147

M3 - Article

VL - 23

SP - 4199

EP - 4210

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 9

M1 - 6837536

ER -