Homography generation for image registration in inlier-poor domains
| DWPI Title: Computing system for facilitating image registration and computation of homography between images, has processor for identifying inlier correspondences in set of candidate correspondences based upon reprojection errors of correspondences |
| 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. |
| Use: Computer system for efficient image registration between two images in the presence of inlier-poor domains. |
| Advantage: Computer system identifies a final homography that is sufficiently accurate to use for image registration between the images. |
| Novelty: The system (100) has a memory (108) stores instructions executed by processor (106) selects first candidate correspondence from the set. Processor identifies multiple inlier correspondences in the set of candidate correspondences (122) based upon reprojection errors of the candidate correspondences relative to the homography approximation. Processor computes a final homograph (130) between the first image and the second image by draws sample correspondences from among the inlier correspondences. Processor performs an image registration between the first image and the second image based upon the final homography. The feature matching algorithm belongs to a family of scale-invariant feature transform (SIFT) algorithms. The feature matching algorithm belongs to a family of speeded-up robust features (SURF) algorithms. |
| Filed: 12/11/2020 |
| Application Number: US17118805A |
| Tech ID: SD 15397.0 |
| This invention was made with Government support under Contract No. DE-NA0003525 awarded by the United States Department of Energy/National Nuclear Security Administration. The Government has certain rights in the invention. |
| Data from Derwent World Patents Index, provided by Clarivate All rights reserved. Republication or redistribution of Clarivate content, including by framing or similar means, is prohibited without the prior written consent of Clarivate. Clarivate and its logo, as well as all other trademarks used herein are trademarks of their respective owners and used under license. |