Please use this identifier to cite or link to this item:
Title: Robust optical flow estimation
Authors: Sánchez, Javier 
Monzón López, Nelson 
Salgado de la Nuez, Agustín Javier 
UNESCO Clasification: 220990 Tratamiento digital. Imágenes
Keywords: Optical flow
Motion estimation
Variational techniques
Issue Date: 2013
Project: Métodos Adaptados Para El Cálculo Del Flujo Óptico en Secuencias de Imágenes. 
Journal: Image Processing On Line 
Abstract: In this work, we describe an implementation of the variational method proposed by Brox et al. in 2004, which yields accurate optical flows with low running times. It has several benefits with respect to the method of Horn and Schunck: it is more robust to the presence of outliers, produces piecewise-smooth flow fields and can cope with constant brightness changes. This method relies on the brightness and gradient constancy assumptions, using the information of the image intensities and the image gradients to find correspondences. It also generalizes the use of continuous L1 functionals, which help mitigate the efect of outliers and create a Total Variation (TV) regularization. Additionally, it introduces a simple temporal regularization scheme that enforces a continuous temporal coherence of the flow fields.
ISSN: 2105-1232
DOI: 10.5201/ipol.2013.21
Source: Image Processing On Line [ISSN 2105-1232], v. 3, p.242-260
Rights: by-nc-nd
Appears in Collections:Artículos
Adobe PDF (9,64 MB)
Show full item record

Google ScholarTM




Export metadata

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