Pseudo-polar based estimation of large translations rotations and scalings in images

Yosi Keller, Amir Averbuch, Moshe Israeli

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

One of the major challenges related to image registration is the estimation of large motions without prior knowledge. This paper presents a Fourier based approach that estimates large translation, scale and rotation motions. The algorithm uses the pseudo-polar transform to achieve substantial improved approximations of the polar and log-polar Fourier transforms of an image. Thus, rotation and scale changes are reduced to translations which are estimated using phase correlation. By utilizing the pseudo-polar grid we increase the performance (accuracy, speed, robustness) of the registration algorithms. Scales up to 4 and arbitrary rotation angles can be robustly recovered, compared to a maximum scaling of 2 recovered by the current state-of-the-art algorithms. The algorithm utilizes only 1D FFT calculations whose overall complexity is significantly lower than prior works. Experimental results demonstrate the applicability of these algorithms.

Original languageEnglish
Title of host publicationProceedings - IEEE Workshop on Motion and Video Computing, MOTION 2005
PublisherIEEE Computer Society
Pages201-206
Number of pages6
ISBN (Print)0769522718, 9780769522715
DOIs
StatePublished - 2005
EventIEEE Workshop on Motion and Video Computing, MOTION 2005 - Breckenridge, CO, United States
Duration: 4 Jan 20057 Jan 2005

Publication series

NameProceedings - IEEE Workshop on Motion and Video Computing, MOTION 2005

Conference

ConferenceIEEE Workshop on Motion and Video Computing, MOTION 2005
Country/TerritoryUnited States
CityBreckenridge, CO
Period4/01/057/01/05

Fingerprint

Dive into the research topics of 'Pseudo-polar based estimation of large translations rotations and scalings in images'. Together they form a unique fingerprint.

Cite this