Robust homography estimation based on nonlinear least squares optimization

The homography between image pairs is normally estimated by minimizing a suitable cost function given 2D keypoint correspondences. The correspondences are typically established using descriptor distance of keypoints. However, the correspondences are often incorrect due to ambiguous descriptors which...

Full description

Saved in:
Bibliographic Details
Main Authors: Mou, Wei, Wang, Han, Seet, Gerald
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2014
Subjects:
Online Access:https://hdl.handle.net/10356/104021
http://hdl.handle.net/10220/19386
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-104021
record_format dspace
spelling sg-ntu-dr.10356-1040212020-03-07T13:22:22Z Robust homography estimation based on nonlinear least squares optimization Mou, Wei Wang, Han Seet, Gerald School of Electrical and Electronic Engineering School of Mechanical and Aerospace Engineering DRNTU::Science::Mathematics The homography between image pairs is normally estimated by minimizing a suitable cost function given 2D keypoint correspondences. The correspondences are typically established using descriptor distance of keypoints. However, the correspondences are often incorrect due to ambiguous descriptors which can introduce errors into following homography computing step. There have been numerous attempts to filter out these erroneous correspondences, but it is unlikely to always achieve perfect matching. To deal with this problem, we propose a nonlinear least squares optimization approach to compute homography such that false matches have no or little effect on computed homography. Unlike normal homography computation algorithms, our method formulates not only the keypoints’ geometric relationship but also their descriptor similarity into cost function. Moreover, the cost function is parametrized in such a way that incorrect correspondences can be simultaneously identified while the homography is computed. Experiments show that the proposed approach can perform well even with the presence of a large number of outliers. Published version 2014-05-20T05:24:25Z 2019-12-06T21:24:45Z 2014-05-20T05:24:25Z 2019-12-06T21:24:45Z 2014 2014 Journal Article Mou, W., Wang, H., & Seet, G. (2014). Robust Homography Estimation Based on Nonlinear Least Squares Optimization. Mathematical Problems in Engineering, 2014, 897050-. 1024-123X https://hdl.handle.net/10356/104021 http://hdl.handle.net/10220/19386 10.1155/2014/897050 en Mathematical problems in engineering © 2014 The Author(s).This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Science::Mathematics
spellingShingle DRNTU::Science::Mathematics
Mou, Wei
Wang, Han
Seet, Gerald
Robust homography estimation based on nonlinear least squares optimization
description The homography between image pairs is normally estimated by minimizing a suitable cost function given 2D keypoint correspondences. The correspondences are typically established using descriptor distance of keypoints. However, the correspondences are often incorrect due to ambiguous descriptors which can introduce errors into following homography computing step. There have been numerous attempts to filter out these erroneous correspondences, but it is unlikely to always achieve perfect matching. To deal with this problem, we propose a nonlinear least squares optimization approach to compute homography such that false matches have no or little effect on computed homography. Unlike normal homography computation algorithms, our method formulates not only the keypoints’ geometric relationship but also their descriptor similarity into cost function. Moreover, the cost function is parametrized in such a way that incorrect correspondences can be simultaneously identified while the homography is computed. Experiments show that the proposed approach can perform well even with the presence of a large number of outliers.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Mou, Wei
Wang, Han
Seet, Gerald
format Article
author Mou, Wei
Wang, Han
Seet, Gerald
author_sort Mou, Wei
title Robust homography estimation based on nonlinear least squares optimization
title_short Robust homography estimation based on nonlinear least squares optimization
title_full Robust homography estimation based on nonlinear least squares optimization
title_fullStr Robust homography estimation based on nonlinear least squares optimization
title_full_unstemmed Robust homography estimation based on nonlinear least squares optimization
title_sort robust homography estimation based on nonlinear least squares optimization
publishDate 2014
url https://hdl.handle.net/10356/104021
http://hdl.handle.net/10220/19386
_version_ 1681040248537088000