On a Decomposition Model for Optical Flow

Authors:
Jochen Abhau;Zakaria Belhachmi;Otmar Scherzer
Affiliations:
Department of Mathematics, University of Innsbruck, Innsbruck, Austria A-6020;Laboratoire de Mathématiques LMAM, UMR 7122, Université UPV-Metz, ISGMP, Metz, France 57045;Department of Mathematics, University of Vienna, Wien, Austria A-1090 and Radon Institute of Computational and Applied Mathematics, Linz, Austria A-4040
Venue:
EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Year:
2009

Citing 13
Cited 1

Oscillating Patterns in Image Processing and Nonlinear Evolution Equations: The Fifteenth Dean Jacqueline B. Lewis Memorial Lectures

Oscillating Patterns in Image Processing and Nonlinear Evolution Equations: The Fifteenth Dean Jacqueline B. Lewis Memorial Lectures
A Theoretical Framework for Convex Regularizers in PDE-Based Computation of Image Motion

International Journal of Computer Vision
Variational Optic Flow Computation with a Spatio-Temporal Smoothness Constraint

Journal of Mathematical Imaging and Vision
Optical-Flow Estimation while Preserving Its Discontinuities: A Variational Approach

ACCV '95 Invited Session Papers from the Second Asian Conference on Computer Vision: Recent Developments in Computer Vision
Modeling Textures with Total Variation Minimization and Oscillating Patterns in Image Processing

Journal of Scientific Computing
An Algorithm for Total Variation Minimization and Applications

Journal of Mathematical Imaging and Vision
Dual Norms and Image Decomposition Models

International Journal of Computer Vision
Image Decomposition into a Bounded Variation Component and an Oscillating Component

Journal of Mathematical Imaging and Vision
Simultaneous Higher-Order Optical Flow Estimation and Decomposition

SIAM Journal on Scientific Computing
Variational dense motion estimation using the Helmholtz decomposition

Scale Space'03 Proceedings of the 4th international conference on Scale space methods in computer vision
A duality based approach for realtime TV-L1 optical flow

Proceedings of the 29th DAGM conference on Pattern recognition
A study of non-smooth convex flow decomposition

VLSM'05 Proceedings of the Third international conference on Variational, Geometric, and Level Set Methods in Computer Vision
Image decomposition via the combination of sparse representations and a variational approach

IEEE Transactions on Image Processing

Optic flow scale space

SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a variational method for determining cartoon and texture components of the optical flow of a noisy image sequence. The method is realized by reformulating the optical flow problem first as a variational denoising problem for multi-channel data and then by applying decomposition methods. Thanks to the general formulation, several norms can be used for the decomposition. We study a decomposition for the optical flow into bounded variation and oscillating component in greater detail. Numerical examples demonstrate the capabilities of the proposed approach.