Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Full explicit consistency constraints in uncalibrated multiple homography estimation
Author: Chojnacki, W.
Szpak, Z.L.
Citation: Proceedings of the 14th Asian Conference on Computer Vision (ACCV 2018), as published in Lecture Notes in Computer Science, 2019 / vol.11361, pp.659-675
Publisher: Springer
Publisher Place: Cham, Switzerland
Issue Date: 2019
Series/Report no.: Lecture Notes in Computer Science; 11361
ISBN: 9783030208868
ISSN: 0302-9743
Conference Name: Asian Conference on Computer Vision (ACCV) (02 Dec 2018 - 06 Dec 2018 : Perth, Western Australia)
Statement of
Wojciech Chojnacki and Zygmunt L. Szpak
Abstract: We reveal a complete set of constraints that need to be imposed on a set of 3×3 matrices to ensure that the matrices represent genuine homographies associated with multiple planes between two views. We also show how to exploit the constraints to obtain more accurate estimates of homography matrices between two views. Our study resolves a long-standing research question and provides a fresh perspective and a more in-depth understanding of the multiple homography estimation task.
Keywords: Multiple homographies; Consistency constraints; Latent variables; Parameter estimation; Scale invariance; Maximum likelihood
Rights: © Springer Nature Switzerland AG 2019
RMID: 0030091011
DOI: 10.1007/978-3-030-20887-5_41
Published version:
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.