• Corpus ID: 231740379

Nonlinear Evolutionary PDE-Based Refinement of Optical Flow

@article{Doshi2021NonlinearEP,
  title={Nonlinear Evolutionary PDE-Based Refinement of Optical Flow},
  author={Hirak Doshi and N. Uday Kiran},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.00487}
}
The goal of this paper is to propose two nonlinear variational models for obtaining a refined motion estimation from an image sequence. Both the proposed models can be considered as a part of a generalized framework for an accurate estimation of physics-based flow fields such as rotational and fluid flow. The first model is novel in the sense that it is divided into two phases: the first phase obtains a crude estimate of the optical flow and then the second phase refines this estimate using… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 59 REFERENCES
Constraint Based Refinement of Optical Flow
TLDR
A general framework for a constraint-based refinement of the optical flow using variational methods and it is demonstrated that for a particular choice of the constraint, formulated as a minimization problem with the quadratic regularization, the results are close to the continuity equation based fluid flow.
A framework for estimating potential fluid flow from digital imagery.
TLDR
This work develops the mathematical formulation of the potential optical flow framework and demonstrates the technique on synthetic flows that represent important dynamics for mass transport in fluid flows, as well as a flow generated by a satellite data-verified ocean model of temperature transport.
A Theoretical Framework for Convex Regularizers in PDE-Based Computation of Image Motion
TLDR
This taxonomy provides a unifying framework for data-driven and flow-driven, isotropic and anisotropic, as well as spatial and spatio-temporal regularizers, and proves that all these methods are well-posed.
Nonlinear Variational Method for Optical Flow Computation
We present a new method for optical flow computation based on the minimization of a non-quadratic functional. The solution of the obtained nonlinear differential equations is done with a time
An Improved Algorithm for TV-L 1 Optical Flow
TLDR
This work proposes an improvement variant of the original duality based TV-L 1 optical flow algorithm that can preserve discontinuities in the flow field by employing total variation (TV) regularization and integrates a median filter into the numerical scheme to further increase the robustness to sampling artefacts in the image data.
Fluid experimental flow estimation based on an optical-flow scheme
TLDR
The proposed technique is an extension of “optical-flow” schemes used in the computer vision community, which includes a specific enhancement for fluid mechanics applications, and enables to provide accurate dense motion fields.
Optical Flow with Harmonic Constraint and Oriented Smoothness
TLDR
A new optical flow model is proposed which incorporates the harmonic smoothness constraint borrowed from the harmonic gradient vector flow (HGVF) model into the oriented Smoothness constraint and combines the curl term of the harmonic constraint with the oriented smoothness to control the direction of the displacement vectors together.
Optical flow computation using extended constraints
TLDR
Two new solutions for optical flow computation are proposed, which are based on an approximation of the constraint equations, which have been used with both EOFC and OFC constraint equations and are compared with several well-known computational methods for Optical flow estimation in different motion conditions.
On Optical Flow Models for Variational Motion Estimation
TLDR
This paper discusses several approaches for quality measures of motion estimation and applies them to compare the previously discussed regularization approaches.
A Duality Based Approach for Realtime TV-L1 Optical Flow
TLDR
This work presents a novel approach to solve the TV-L1 formulation, which is based on a dual formulation of the TV energy and employs an efficient point-wise thresholding step.
...
1
2
3
4
5
...