Optical flow diffusion with robustified kernels

A Doshi; A G Bors

Optical flow diffusion with robustified kernels

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper provides a comparison study among a set of robust diffusion algorithms for processing optical flows. The proposed algorithms combine the smoothing ability of the heat kernel, modelled by the local Hessian, and the outlier rejection mechanisms of robust statistics algorithms. Smooth optical flow variation can be modelled very well using heat kernels. The diffusion kernel is considered Gaussian, where the covariance matrix implements the inverse of the local Hessian. Robust statistics operators improve the results provided by the heat kernel based diffusion, by rejecting outliers and by avoiding optical flow oversmoothing. Alpha-trimmed mean and median statistics are considered for robustifying diffusion kernels. The robust diffusion smoothing is applied onto multiple frames and is extended to 3D lattices.

Original language	English
Title of host publication	COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS
Editors	A Gagalowicz, W Philips
Place of Publication	BERLIN
Publisher	Springer
Pages	222-230
Number of pages	9
ISBN (Print)	3-540-28969-0
Publication status	Published - 2005
Event	11th International Conference on Computer Analysis of Images and Patterns - Versailles Duration: 5 Sept 2005 → 8 Sept 2005

Conference

Conference	11th International Conference on Computer Analysis of Images and Patterns
City	Versailles
Period	5/09/05 → 8/09/05

Keywords

ANISOTROPIC DIFFUSION

Cite this

@inproceedings{c53dfe1ee1b94d8c813bc5f94d1732b4,

title = "Optical flow diffusion with robustified kernels",

abstract = "This paper provides a comparison study among a set of robust diffusion algorithms for processing optical flows. The proposed algorithms combine the smoothing ability of the heat kernel, modelled by the local Hessian, and the outlier rejection mechanisms of robust statistics algorithms. Smooth optical flow variation can be modelled very well using heat kernels. The diffusion kernel is considered Gaussian, where the covariance matrix implements the inverse of the local Hessian. Robust statistics operators improve the results provided by the heat kernel based diffusion, by rejecting outliers and by avoiding optical flow oversmoothing. Alpha-trimmed mean and median statistics are considered for robustifying diffusion kernels. The robust diffusion smoothing is applied onto multiple frames and is extended to 3D lattices.",

keywords = "ANISOTROPIC DIFFUSION",

author = "A Doshi and Bors, {A G}",

year = "2005",

language = "English",

isbn = "3-540-28969-0",

pages = "222--230",

editor = "A Gagalowicz and W Philips",

booktitle = "COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS",

publisher = "Springer",

address = "Germany",

note = "11th International Conference on Computer Analysis of Images and Patterns ; Conference date: 05-09-2005 Through 08-09-2005",

}

TY - GEN

T1 - Optical flow diffusion with robustified kernels

AU - Doshi, A

AU - Bors, A G

PY - 2005

Y1 - 2005

N2 - This paper provides a comparison study among a set of robust diffusion algorithms for processing optical flows. The proposed algorithms combine the smoothing ability of the heat kernel, modelled by the local Hessian, and the outlier rejection mechanisms of robust statistics algorithms. Smooth optical flow variation can be modelled very well using heat kernels. The diffusion kernel is considered Gaussian, where the covariance matrix implements the inverse of the local Hessian. Robust statistics operators improve the results provided by the heat kernel based diffusion, by rejecting outliers and by avoiding optical flow oversmoothing. Alpha-trimmed mean and median statistics are considered for robustifying diffusion kernels. The robust diffusion smoothing is applied onto multiple frames and is extended to 3D lattices.

AB - This paper provides a comparison study among a set of robust diffusion algorithms for processing optical flows. The proposed algorithms combine the smoothing ability of the heat kernel, modelled by the local Hessian, and the outlier rejection mechanisms of robust statistics algorithms. Smooth optical flow variation can be modelled very well using heat kernels. The diffusion kernel is considered Gaussian, where the covariance matrix implements the inverse of the local Hessian. Robust statistics operators improve the results provided by the heat kernel based diffusion, by rejecting outliers and by avoiding optical flow oversmoothing. Alpha-trimmed mean and median statistics are considered for robustifying diffusion kernels. The robust diffusion smoothing is applied onto multiple frames and is extended to 3D lattices.

KW - ANISOTROPIC DIFFUSION

M3 - Conference contribution

SN - 3-540-28969-0

SP - 222

EP - 230

BT - COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS

A2 - Gagalowicz, A

A2 - Philips, W

PB - Springer

CY - BERLIN

T2 - 11th International Conference on Computer Analysis of Images and Patterns

Y2 - 5 September 2005 through 8 September 2005

ER -