Please use this identifier to cite or link to this item:
Title: Horn-schunck optical flow with a multi-scale strategy
Authors: Meinhardt-Llopis, Enric
Sánchez, Javier 
UNESCO Clasification: 220990 Tratamiento digital. Imágenes
Keywords: Optical flow
Issue Date: 2013
Journal: Image Processing On Line 
Abstract: The seminal work of Horn and Schunck [8] is the first variational method for optical flow estimation. It introduced a novel framework where the optical flow is computed as the solution of a minimization problem. From the assumption that pixel intensities do not change over time, the optical flow constraint equation is derived. This equation relates the optical flow with the derivatives of the image. There are infinitely many vector fields that satisfy the optical flow constraint, thus the problem is ill-posed. To overcome this problem, Horn and Schunck introduced an additional regularity condition that restricts the possible solutions. Their method minimizes both the optical flow constraint and the magnitude of the variations of the flow field, producing smooth vector fields. One of the limitations of this method is that, typically, it can only estimate small motions. In the presence of large displacements, this method fails when the gradient of the image is not smooth enough. In this work, we describe an implementation of the original Horn and Schunck method and also introduce a multi-scale strategy in order to deal with larger displacements. For this multi-scale strategy, we create a pyramidal structure of downsampled images and change the optical flow constraint equation with a nonlinear formulation. In order to tackle this nonlinear formula, we linearize it and solve the method iteratively in each scale. In this sense, there are two common approaches: one that computes the motion increment in the iterations, like in ; or the one we follow, that computes the full flow during the iterations, like in. The solutions are incrementally refined ower the scales. This pyramidal structure is a standard tool in many optical flow methods.
ISSN: 2105-1232
DOI: 10.5201/ipol.2013.20
Source: Image Processing On Line [ISSN 2105-1232], v. 3, p. 151-172
Rights: by-nc-nd
Appears in Collections:Artículos
Adobe PDF (9,26 MB)
Adobe PDF (7,05 MB)
Show full item record


checked on Nov 19, 2023

Page view(s)

checked on Oct 23, 2022


checked on Oct 23, 2022

Google ScholarTM




Export metadata

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