FFT-based estimation of large motions in images: a robust gradient-based approach

A fast and robust gradient-based motion estimation technique which operates in the frequency domain is presented. The algorithm combines the natural advantages of a good feature selection offered by gradient-based methods with the robustness and speed provided by FFT-based correlation schemes. Exper...

Full description

Bibliographic Details
Main Authors: Tzimiropoulos, Georgios, Argyriou, Vasileios, Stathaki, Tania
Format: Conference or Workshop Item
Published: 2009
Subjects:
Online Access:https://eprints.nottingham.ac.uk/31417/
_version_ 1848794196613267456
author Tzimiropoulos, Georgios
Argyriou, Vasileios
Stathaki, Tania
author_facet Tzimiropoulos, Georgios
Argyriou, Vasileios
Stathaki, Tania
author_sort Tzimiropoulos, Georgios
building Nottingham Research Data Repository
collection Online Access
description A fast and robust gradient-based motion estimation technique which operates in the frequency domain is presented. The algorithm combines the natural advantages of a good feature selection offered by gradient-based methods with the robustness and speed provided by FFT-based correlation schemes. Experimentation with real images taken from a popular database showed that, unlike any other Fourier-based techniques, the method was able to estimate translations, arbitrary rotations and scale factors in the range 4-6.
first_indexed 2025-11-14T19:12:21Z
format Conference or Workshop Item
id nottingham-31417
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:12:21Z
publishDate 2009
recordtype eprints
repository_type Digital Repository
spelling nottingham-314172020-05-04T20:26:22Z https://eprints.nottingham.ac.uk/31417/ FFT-based estimation of large motions in images: a robust gradient-based approach Tzimiropoulos, Georgios Argyriou, Vasileios Stathaki, Tania A fast and robust gradient-based motion estimation technique which operates in the frequency domain is presented. The algorithm combines the natural advantages of a good feature selection offered by gradient-based methods with the robustness and speed provided by FFT-based correlation schemes. Experimentation with real images taken from a popular database showed that, unlike any other Fourier-based techniques, the method was able to estimate translations, arbitrary rotations and scale factors in the range 4-6. 2009-04 Conference or Workshop Item PeerReviewed Tzimiropoulos, Georgios, Argyriou, Vasileios and Stathaki, Tania (2009) FFT-based estimation of large motions in images: a robust gradient-based approach. In: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2009), 19-24 April 2009, Taipei, Taiwan. Fast Fourier transforms Gradient methods Motion estimation http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4959747
spellingShingle Fast Fourier transforms
Gradient methods
Motion estimation
Tzimiropoulos, Georgios
Argyriou, Vasileios
Stathaki, Tania
FFT-based estimation of large motions in images: a robust gradient-based approach
title FFT-based estimation of large motions in images: a robust gradient-based approach
title_full FFT-based estimation of large motions in images: a robust gradient-based approach
title_fullStr FFT-based estimation of large motions in images: a robust gradient-based approach
title_full_unstemmed FFT-based estimation of large motions in images: a robust gradient-based approach
title_short FFT-based estimation of large motions in images: a robust gradient-based approach
title_sort fft-based estimation of large motions in images: a robust gradient-based approach
topic Fast Fourier transforms
Gradient methods
Motion estimation
url https://eprints.nottingham.ac.uk/31417/
https://eprints.nottingham.ac.uk/31417/