Fast motion estimation using bidirectional gradient methods

Yosi Keller, Amir Averbuch

Research output: Contribution to journalArticlepeer-review

Abstract

Gradient-based motion estimation methods (GMs) are considered to be in the heart of state-of-the-art registration algorithms, being able to account for both pixel and subpixel registration and to handle various motion models (translation, rotation, affine, and projective). These methods estimate the motion between two images based on the local changes in the image intensities while assuming image smoothness. This paper offers two main contributions. The first is enhancement of the GM technique by introducing two new bidirectional formulations of the GM. These improve the convergence properties for large motions. The second is that we present an analytical convergence analysis of the GM and its properties. Experimental results demonstrate the applicability of these algorithms to real images.

Original languageEnglish
Pages (from-to)1042-1054
Number of pages13
JournalIEEE Transactions on Image Processing
Volume13
Issue number8
DOIs
StatePublished - Aug 2004

Fingerprint

Dive into the research topics of 'Fast motion estimation using bidirectional gradient methods'. Together they form a unique fingerprint.

Cite this