Variational Multi-Valued Velocity Field Estimation for Transparent Sequences

Authors:
Alonso Ramírez-Manzanares;Mariano Rivera;Pierre Kornprobst;François Lauze
Affiliations:
Department of Mathematics, University of Guanajuato, Guanajuato, Mexico C.P. 36000;Centro de Investigacion en Matematicas A.C., Guanajuato, Mexico 36000;INRIA, Odyssée Lab., Sophia Antipolis, France 06902;Institute of Computer Science, University of Copenhagen, Kbh Ø, Denmark 2100
Venue:
Journal of Mathematical Imaging and Vision
Year:
2011

Citing 26
Cited 0

Visual reconstruction

Visual reconstruction
The existence of geometrical density—image transformations corresponding to object motion

Computer Vision, Graphics, and Image Processing
Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow

IEEE Transactions on Pattern Analysis and Machine Intelligence
Computing occluding and transparent motions

International Journal of Computer Vision
Performance of optical flow techniques

International Journal of Computer Vision
What is the goal of sensory coding?

Neural Computation
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields

Computer Vision and Image Understanding
On the unification of line processes, outlier rejection, and robust statistics with applications in early vision

International Journal of Computer Vision
Robustly estimating changes in image appearance

Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
Using known motion fields for image separation in transparency

Pattern Recognition Letters
Decoupling Fourir Components of Dynamic Image Sequences: A Theory of Signal Separation, Image Segmentation, and Optical Flow Estimation

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Layered 4D Representation and Voting for Grouping from Motion

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Unified Mixture Framework for Motion Segmentation: Incorporating Spatial Coherence and Estimating the Number of Models

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Skin and Bones: Multi-layer, Locally Affine, Optical Flow and Regularization with Transparency

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Spatio-temporal filters for transparent motion segmentation

ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3 - Volume 3
Separating Transparent Layers of Repetitive Dynamic Behaviors

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Highly Accurate Optic Flow Computation with Theoretically Justified Warping

International Journal of Computer Vision
Basis Tensor Decomposition for Restoring Intra-Voxel Structure and Stochastic Walks for Inferring Brain Connectivity in DT-MRI

International Journal of Computer Vision
A Fast Biologically Inspired Algorithm for Recurrent Motion Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
The separation of reflected and transparent layers from real-world image sequence

Machine Vision and Applications
Over-Parameterized Variational Optical Flow

International Journal of Computer Vision
Divide-and-conquer strategies for estimating multiple transparent motions

IWCM'04 Proceedings of the 1st international conference on Complex motion
A variational approach for multi-valued velocity field estimation in transparent sequences

SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
A theory of multiple orientation estimation

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
A robust multiscale B-spline function decomposition for estimating motion transparency

IEEE Transactions on Image Processing
Entropy-Controlled Quadratic Markov Measure Field Models for Efficient Image Segmentation

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motion estimation in sequences with transparencies is an important problem in robotics and medical imaging applications. In this work we propose a variational approach for estimating multi-valued velocity fields in transparent sequences. Starting from existing local motion estimators, we derive a variational model for integrating in space and time such a local information in order to obtain a robust estimation of the multi-valued velocity field. With this approach, we can indeed estimate multi-valued velocity fields which are not necessarily piecewise constant on a layer--each layer can evolve according to a non-parametric optical flow. We show how our approach outperforms existing methods; and we illustrate its capabilities on challenging experiments on both synthetic and real sequences.