DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Homography generation for image registration in inlier-poor domains

Abstract

A method for efficient image registration between two images in the presence of inlier-poor domains includes receiving a set of candidate correspondences between the two images. An approximate homography between the two images is generated based upon a first correspondence in the correspondences. The set of candidate correspondences is filtered to identify inlier correspondences based upon the approximate homography. A candidate homography is computed based upon the inlier correspondences. The candidate homography can be selected as a final homography between the two images based upon a support of the candidate homography against the set of candidate correspondences. An image registration is performed between the two images based upon the candidate homography being selected as the final homography.

Inventors:
; ;
Issue Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1987052
Patent Number(s):
11557019
Application Number:
17/118,805
Assignee:
National Technology & Engineering Solutions of Sandia, LLC (Albuquerque, NM)
DOE Contract Number:  
NA0003525
Resource Type:
Patent
Resource Relation:
Patent File Date: 12/11/2020
Country of Publication:
United States
Language:
English

Citation Formats

Gonzales, Antonio, Perkins, Tony, and Monical, Cara Patricia. Homography generation for image registration in inlier-poor domains. United States: N. p., 2023. Web.
Gonzales, Antonio, Perkins, Tony, & Monical, Cara Patricia. Homography generation for image registration in inlier-poor domains. United States.
Gonzales, Antonio, Perkins, Tony, and Monical, Cara Patricia. Tue . "Homography generation for image registration in inlier-poor domains". United States. https://www.osti.gov/servlets/purl/1987052.
@article{osti_1987052,
title = {Homography generation for image registration in inlier-poor domains},
author = {Gonzales, Antonio and Perkins, Tony and Monical, Cara Patricia},
abstractNote = {A method for efficient image registration between two images in the presence of inlier-poor domains includes receiving a set of candidate correspondences between the two images. An approximate homography between the two images is generated based upon a first correspondence in the correspondences. The set of candidate correspondences is filtered to identify inlier correspondences based upon the approximate homography. A candidate homography is computed based upon the inlier correspondences. The candidate homography can be selected as a final homography between the two images based upon a support of the candidate homography against the set of candidate correspondences. An image registration is performed between the two images based upon the candidate homography being selected as the final homography.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2023},
month = {1}
}

Works referenced in this record:

Panoramic Image Stitching Using Objects
patent-application, June 2017


System and Methods for a Trackerless Navigation System
patent-application, February 2022


Threshold Determination in a RANSAC Algorithm
patent-application, June 2017


4D Visualization of Building Design and Construction Modeling with Photographs
patent-application, October 2015


1-Point-RANSAC Structure from Motion for Vehicle-Mounted Cameras by Exploiting Non-holonomic Constraints
journal, April 2011


Homography From Two Orientation- and Scale-Covariant Features
conference, October 2019