Nonlinear Matrix Diffusion for Optic Flow Estimation

Authors:
Thomas Brox;Joachim Weickert
Affiliations:
-;-
Venue:
Proceedings of the 24th DAGM Symposium on Pattern Recognition
Year:
2002

Citing 7
Cited 15

Computing oriented texture fields

CVGIP: Graphical Models and Image Processing
Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow

IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance of optical flow techniques

International Journal of Computer Vision
Spatio-Temporal Image Processing: Theory and Scientific Applications

Spatio-Temporal Image Processing: Theory and Scientific Applications
Variational Optic Flow Computation with a Spatio-Temporal Smoothness Constraint

Journal of Mathematical Imaging and Vision
Spatiotemporally Adaptive Estimation and Segmenation of OF-Fields

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
An iterative image registration technique with an application to stereo vision

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2

Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods

International Journal of Computer Vision
Curvature-Driven PDE Methods for Matrix-Valued Images

International Journal of Computer Vision
Mathematical morphology for matrix fields induced by the Loewner ordering in higher dimensions

Signal Processing
Median and related local filters for tensor-valued images

Signal Processing
Morphology for matrix data: Ordering versus PDE-based approach

Image and Vision Computing
Symmetrical Dense Optical Flow Estimation with Occlusions Detection

International Journal of Computer Vision
Texture and color segmentation based on the combined use of the structure tensor and the image components

Signal Processing
Variational denoising of partly textured images

Journal of Visual Communication and Image Representation
Nonlinear structure tensors

Image and Vision Computing
Hip joint segmentation from 2D ultrasound data based on dynamic shape priors

ICECS'05 Proceedings of the 4th WSEAS international conference on Electronics, control and signal processing
Tensor processing for texture and colour segmentation

SCIA'05 Proceedings of the 14th Scandinavian conference on Image Analysis
A novel approach to ocular image enhancement with diffusion and parallel AOS algorithm

ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part I
Matrix-valued filters as convex programs

Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
Perfusion analysis of nonlinear liver ultrasound images based on nonlinear matrix diffusion

Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
An evaluation framework for stereo-based driver assistance

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a method for nonlinear diffusion of matrix-valued data. We adapt this technique to the well-known linear structure tensor in order to develop a new nonlinear structure tensor. It is then used to improve the optic flow estimation methods of Lucas and Kanade and its spatio-temporal variant of Big眉n et al.. Our experiments show that the nonlinear structure tensor leads to a better preservation of discontinuities in the optic flow field.