Correspondence-free determination of the affine fundamental matrix

Lehmann, S., Bradley, A.P., Clarkson, I.V.L., Williams, J. and Kootsookos, P.J. (2007) Correspondence-free determination of the affine fundamental matrix. IEEE Transactions On Pattern Analysis And Machine Intelligence, 29 1: 82-97. doi:10.1109/TPAMI.2007.250601

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Lehmann, S.
Bradley, A.P.
Clarkson, I.V.L.
Williams, J.
Kootsookos, P.J.
Title Correspondence-free determination of the affine fundamental matrix
Journal name IEEE Transactions On Pattern Analysis And Machine Intelligence   Check publisher's open access policy
ISSN 0162-8828
Publication date 2007
Sub-type Article (original research)
DOI 10.1109/TPAMI.2007.250601
Volume 29
Issue 1
Start page 82
End page 97
Total pages 16
Editor Bowyer, K.
Kroeker, K.
Place of publication Los Alamitos
Publisher IEEE Computer Society
Collection year 2008
Language eng
Subject 280207 Pattern Recognition
730111 Hearing, vision, speech and their disorders
Abstract Fundamental matrix estimation is a central problem in computer vision and forms the basis of tasks such as stereo imaging and structure from motion. Existing algorithms typically analyze the relative geometries of matched feature points identified in both projected views. Automated feature matching is itself a challenging problem. Results typically have a large number of false matches. Traditional fundamental matrix estimation methods are very sensitive to matching errors, which led naturally to the application of robust statistical estimation techniques to the problem. In this work, an entirely novel approach is proposed to the fundamental matrix estimation problem. Instead of analyzing the geometry of matched feature points, the problem is recast in the frequency domain through the use of Integral Projection, showing how this is a reasonable model for orthographic cameras. The problem now reduces to one of identifying matching lines in the frequency domain which, most importantly, requires no feature matching or correspondence information. Experimental results on both real and synthetic data are presented that demonstrate the algorithm is a practical technique for fundamental matrix estimation. The behavior of the proposed algorithm is additionally characterized with respect to input noise, feature counts, and other parameters of interest.
Keyword Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
computer vision
epipolar geometry
fundamental matrix
robust estimation
slice theorem
Radon transformation
Q-Index Code C1
Q-Index Status Confirmed Code

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 9 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 7 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Mon, 18 Feb 2008, 15:54:35 EST