Stereo matching using epipolar distance transform

Qingxiong Yang, Narendra Ahuja

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a simple but effective image transform, called the epipolar distance transform, for matching low-texture regions. It converts image intensity values to a relative location inside a planar segment along the epipolar line, such that pixels in the low-texture regions become distinguishable. We theoretically prove that the transform is affine invariant, thus the transformed images can be directly used for stereo matching. Any existing stereo algorithms can be directly used with the transformed images to improve reconstruction accuracy for low-texture regions. Results on real indoor and outdoor images demonstrate the effectiveness of the proposed transform for matching low-texture regions, keypoint detection, and description for low-texture scenes. Our experimental results on Middlebury images also demonstrate the robustness of our transform for highly textured scenes. The proposed transform has a great advantage, its low computational complexity. It was tested on a MacBook Air laptop computer with a 1.8 GHz Core i7 processor, with a speed of about 9 frames per second for a video graphics array-sized image.

Original languageEnglish (US)
Article number6236163
Pages (from-to)4410-4419
Number of pages10
JournalIEEE Transactions on Image Processing
Volume21
Issue number10
DOIs
StatePublished - Sep 28 2012

Fingerprint

Textures
Affine transforms
Laptop computers
Computational complexity
Pixels
Air

Keywords

  • Epipolar
  • stereo matching
  • texture

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Stereo matching using epipolar distance transform. / Yang, Qingxiong; Ahuja, Narendra.

In: IEEE Transactions on Image Processing, Vol. 21, No. 10, 6236163, 28.09.2012, p. 4410-4419.

Research output: Contribution to journalArticle

@article{5c96b5684220403387bb180d82508e6d,
title = "Stereo matching using epipolar distance transform",
abstract = "In this paper, we propose a simple but effective image transform, called the epipolar distance transform, for matching low-texture regions. It converts image intensity values to a relative location inside a planar segment along the epipolar line, such that pixels in the low-texture regions become distinguishable. We theoretically prove that the transform is affine invariant, thus the transformed images can be directly used for stereo matching. Any existing stereo algorithms can be directly used with the transformed images to improve reconstruction accuracy for low-texture regions. Results on real indoor and outdoor images demonstrate the effectiveness of the proposed transform for matching low-texture regions, keypoint detection, and description for low-texture scenes. Our experimental results on Middlebury images also demonstrate the robustness of our transform for highly textured scenes. The proposed transform has a great advantage, its low computational complexity. It was tested on a MacBook Air laptop computer with a 1.8 GHz Core i7 processor, with a speed of about 9 frames per second for a video graphics array-sized image.",
keywords = "Epipolar, stereo matching, texture",
author = "Qingxiong Yang and Narendra Ahuja",
year = "2012",
month = "9",
day = "28",
doi = "10.1109/TIP.2012.2207393",
language = "English (US)",
volume = "21",
pages = "4410--4419",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",

}

TY - JOUR

T1 - Stereo matching using epipolar distance transform

AU - Yang, Qingxiong

AU - Ahuja, Narendra

PY - 2012/9/28

Y1 - 2012/9/28

N2 - In this paper, we propose a simple but effective image transform, called the epipolar distance transform, for matching low-texture regions. It converts image intensity values to a relative location inside a planar segment along the epipolar line, such that pixels in the low-texture regions become distinguishable. We theoretically prove that the transform is affine invariant, thus the transformed images can be directly used for stereo matching. Any existing stereo algorithms can be directly used with the transformed images to improve reconstruction accuracy for low-texture regions. Results on real indoor and outdoor images demonstrate the effectiveness of the proposed transform for matching low-texture regions, keypoint detection, and description for low-texture scenes. Our experimental results on Middlebury images also demonstrate the robustness of our transform for highly textured scenes. The proposed transform has a great advantage, its low computational complexity. It was tested on a MacBook Air laptop computer with a 1.8 GHz Core i7 processor, with a speed of about 9 frames per second for a video graphics array-sized image.

AB - In this paper, we propose a simple but effective image transform, called the epipolar distance transform, for matching low-texture regions. It converts image intensity values to a relative location inside a planar segment along the epipolar line, such that pixels in the low-texture regions become distinguishable. We theoretically prove that the transform is affine invariant, thus the transformed images can be directly used for stereo matching. Any existing stereo algorithms can be directly used with the transformed images to improve reconstruction accuracy for low-texture regions. Results on real indoor and outdoor images demonstrate the effectiveness of the proposed transform for matching low-texture regions, keypoint detection, and description for low-texture scenes. Our experimental results on Middlebury images also demonstrate the robustness of our transform for highly textured scenes. The proposed transform has a great advantage, its low computational complexity. It was tested on a MacBook Air laptop computer with a 1.8 GHz Core i7 processor, with a speed of about 9 frames per second for a video graphics array-sized image.

KW - Epipolar

KW - stereo matching

KW - texture

UR - http://www.scopus.com/inward/record.url?scp=84866612189&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866612189&partnerID=8YFLogxK

U2 - 10.1109/TIP.2012.2207393

DO - 10.1109/TIP.2012.2207393

M3 - Article

AN - SCOPUS:84866612189

VL - 21

SP - 4410

EP - 4419

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 10

M1 - 6236163

ER -