Dense Motion Estimation Using Regularization Constraints on Local Parametric Models

Dense Motion Estimation Using Regularization Constraints on Local Parametric Models
I. Patras, M. Worring, R. van den Boomgaard
In IEEE Transactions on Image Processing 2004.
[bibtex] [pdf] [url]
Abstract
This paper presents a method for dense optical flow estimation in which the motion field within patches that result from an initial intensity segmentation is parametrized with models of different order. We propose a novel formulation which introduces regularization constraints between the model parameters of neighboring patches. In this way, we provide the additional constraints for very small patches and for patches whose intensity variation cannot sufficiently constrain the estimation of their motion parameters. In order to preserve motion discontinuities, we use robust functions as a regularization mean. We adopt a three-frame approach and control the balance between the backward and forward constraints by a real-valued direction field on which regularization constraints are applied. An iterative deterministic relaxation method is employed in order to solve the corresponding optimization problem. Experimental results show that the proposed method deals successfully with motions large in magnitude, motion discontinuities, and produces accurate piecewise-smooth motion fields.

Bibtex Entry
@Article{PatrasTIP2004,
  author       = "Patras, I. and Worring, M. and van den Boomgaard, R.",
  title        = "Dense Motion Estimation Using Regularization Constraints on Local Parametric Models",
  journal      = "IEEE Transactions on Image Processing",
  number       = "11",
  volume       = "13",
  pages        = "1432--1443",
  year         = "2004",
  url          = "https://ivi.fnwi.uva.nl/isis/publications/2004/PatrasTIP2004",
  pdf          = "https://ivi.fnwi.uva.nl/isis/publications/2004/PatrasTIP2004/PatrasTIP2004.pdf"
}
Powered by bibtexbrowser