Publication detail

Bayesian methods for optical flow estimation using a variational approximation, with applications to ultrasound

Jan Dorazil, Bernard H. Fleury, Franz Hlawatsch

Original Title

Bayesian methods for optical flow estimation using a variational approximation, with applications to ultrasound

Type

conference paper

Language

English

Original Abstract

We develop a unified Bayesian framework for optical flow (OF) estimation that uses a variational lower bound to obtain a variational approximation of the posterior probability distribution. Our framework enables the incorporation of domain-specific knowledge as well as a quantification of the uncertainty of OF estimation, and it encompasses existing maximum a posteriori (MAP) and variational Bayes (VB) methods as special cases. We leverage this flexibility for the ultrasound modality by using ultrasound-specific likelihood functions within both MAP and VB methods. Numerical results for the problem of cardiac motion estimation demonstrate that VB methods outperform MAP methods, in addition to providing a more faithful uncertainty measure.

Keywords

Optical flow; Bayesian estimation; variational approximation; ultrasound; cardiac motion estimation

Authors

Jan Dorazil, Bernard H. Fleury, Franz Hlawatsch

Released

4. 6. 2023

ISBN

978-1-7281-6327-7

Book

IEEE ICASSP 2023

Pages from

1

Pages to

5

Pages count

5

URL

https://ieeexplore.ieee.org/abstract/document/10095694

BibTex

@inproceedings{BUT186844,
  author="Jan {Dorazil} and Bernard H. {Fleury} and Franz {Hlawatsch}",
  title="Bayesian methods for optical flow estimation using a variational approximation, with applications to ultrasound",
  booktitle="IEEE ICASSP 2023",
  year="2023",
  pages="1--5",
  doi="10.1109/ICASSP49357.2023.10095694",
  isbn="978-1-7281-6327-7",
  url="https://ieeexplore.ieee.org/abstract/document/10095694"
}