Oblique aerial image matching based on iterative simulation and homography evaluation

Woo Hyuck Song, Hong Gyu Jung, In Youb Gwak, Seong Whan Lee

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper presents a fast and accurate method for matching oblique aerial image pairs. In order to achieve accurate matching results, we must consider viewpoint differences between the input images in addition to rotation and scaling. Existing methods that match aerial image pairs with viewpoint differences undergo heavy computation and have difficulty finding correspondences. In this paper, we propose a homography matrix evaluation method based on a geometric approach to increase the accuracy of image matching results. In addition, we achieve faster matching through an iterative transform simulation that reduces computational complexity. Experimental results show that the proposed method improves aerial image matching in terms of computational efficiency while achieving successful matching results.

Original languageEnglish
Pages (from-to)317-331
Number of pages15
JournalPattern Recognition
Volume87
DOIs
Publication statusPublished - 2019 Mar 1

Fingerprint

Image matching
Antennas
Computational efficiency
Computational complexity

Keywords

  • Aerial image
  • Feature matching
  • Homography matrix
  • SIFT descriptor
  • Viewpoint change

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Oblique aerial image matching based on iterative simulation and homography evaluation. / Song, Woo Hyuck; Jung, Hong Gyu; Gwak, In Youb; Lee, Seong Whan.

In: Pattern Recognition, Vol. 87, 01.03.2019, p. 317-331.

Research output: Contribution to journalArticle

Song, Woo Hyuck ; Jung, Hong Gyu ; Gwak, In Youb ; Lee, Seong Whan. / Oblique aerial image matching based on iterative simulation and homography evaluation. In: Pattern Recognition. 2019 ; Vol. 87. pp. 317-331.
@article{e866b6d2acf949ee9a55a42b4999f6b2,
title = "Oblique aerial image matching based on iterative simulation and homography evaluation",
abstract = "This paper presents a fast and accurate method for matching oblique aerial image pairs. In order to achieve accurate matching results, we must consider viewpoint differences between the input images in addition to rotation and scaling. Existing methods that match aerial image pairs with viewpoint differences undergo heavy computation and have difficulty finding correspondences. In this paper, we propose a homography matrix evaluation method based on a geometric approach to increase the accuracy of image matching results. In addition, we achieve faster matching through an iterative transform simulation that reduces computational complexity. Experimental results show that the proposed method improves aerial image matching in terms of computational efficiency while achieving successful matching results.",
keywords = "Aerial image, Feature matching, Homography matrix, SIFT descriptor, Viewpoint change",
author = "Song, {Woo Hyuck} and Jung, {Hong Gyu} and Gwak, {In Youb} and Lee, {Seong Whan}",
year = "2019",
month = "3",
day = "1",
doi = "10.1016/j.patcog.2018.10.027",
language = "English",
volume = "87",
pages = "317--331",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Oblique aerial image matching based on iterative simulation and homography evaluation

AU - Song, Woo Hyuck

AU - Jung, Hong Gyu

AU - Gwak, In Youb

AU - Lee, Seong Whan

PY - 2019/3/1

Y1 - 2019/3/1

N2 - This paper presents a fast and accurate method for matching oblique aerial image pairs. In order to achieve accurate matching results, we must consider viewpoint differences between the input images in addition to rotation and scaling. Existing methods that match aerial image pairs with viewpoint differences undergo heavy computation and have difficulty finding correspondences. In this paper, we propose a homography matrix evaluation method based on a geometric approach to increase the accuracy of image matching results. In addition, we achieve faster matching through an iterative transform simulation that reduces computational complexity. Experimental results show that the proposed method improves aerial image matching in terms of computational efficiency while achieving successful matching results.

AB - This paper presents a fast and accurate method for matching oblique aerial image pairs. In order to achieve accurate matching results, we must consider viewpoint differences between the input images in addition to rotation and scaling. Existing methods that match aerial image pairs with viewpoint differences undergo heavy computation and have difficulty finding correspondences. In this paper, we propose a homography matrix evaluation method based on a geometric approach to increase the accuracy of image matching results. In addition, we achieve faster matching through an iterative transform simulation that reduces computational complexity. Experimental results show that the proposed method improves aerial image matching in terms of computational efficiency while achieving successful matching results.

KW - Aerial image

KW - Feature matching

KW - Homography matrix

KW - SIFT descriptor

KW - Viewpoint change

UR - http://www.scopus.com/inward/record.url?scp=85055750336&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055750336&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2018.10.027

DO - 10.1016/j.patcog.2018.10.027

M3 - Article

AN - SCOPUS:85055750336

VL - 87

SP - 317

EP - 331

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -