Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/11765
Title: A scale-space approach to nonlocal optical flow calculations
Authors: Álvarez León, Luis Miguel 
Weickert, Joachim
Sánchez, Javier 
UNESCO Clasification: 220990 Tratamiento digital. Imágenes
120601 Construcción de algoritmos
120602 Ecuaciones diferenciales
Keywords: Optical Flow
Parabolic System
Asymptotic State
Average Angular Error
Euclidean Error
Issue Date: 1999
Journal: Lecture Notes in Computer Science 
Conference: 2nd International Conference on Scale Space Theory in Computer Vision (Scale-Space 99) 
2nd International Conference on Scale-Space Theories in Computer Vision, 1999 
Abstract: This paper presents an interpretation of a classic optical flow method by Nagel and Enkelmann as a tensor-driven anisotropic diffusion approach in digital image analysis. We introduce an improvement into the model formulation, and we establish well-posedness results for the resulting system of parabolic partial differential equations. Our method avoids linearizations in the optical flow constraint, and it can recover displacement fields which are far beyond the typical one-pixel limits that are characteristic for many differential methods for optical flow recovery. A robust numerical scheme is presented in detail. We avoid convergence to irrelevant local minima by embedding our method into a linear scale-space framework and using a focusing strategy from coarse to fine scales. The high accuracy of the proposed method is demonstrated by means of a synthetic and a real-world image sequence.
URI: http://hdl.handle.net/10553/11765
ISBN: 978-3-540-66498-7
354066498X
ISSN: 0302-9743
DOI: 10.1007/3-540-48236-9_21
Source: Nielsen M., Johansen P., Olsen O.F., Weickert J. (eds) Scale-Space Theories in Computer Vision. Scale-Space 1999. Lecture Notes in Computer Science, vol 1682. Springer, Berlin, Heidelberg
Rights: by-nc-nd
Appears in Collections:Actas de congresos
Thumbnail
Adobe PDF (277,62 kB)
Show full item record

SCOPUSTM   
Citations

55
checked on Feb 21, 2021

WEB OF SCIENCETM
Citations

39
checked on Feb 21, 2021

Page view(s)

40
checked on Feb 21, 2021

Download(s)

73
checked on Feb 21, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.