An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow Problem

An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow Problem

Total variation (TV) is widely used in many image processing problems including the regularization of optical flow estimation. In order to deal with non differentiability of the TV regularization term, smooth approximations have been considered in the literature. In this paper, we investigate the us...

Full description

Bibliographic Details
Main Author: El Mostafa Kalmoun
Format: Article
Language:English
Published: MDPI AG 2018-01-01
Series:Journal of Imaging
Subjects:
optical flow
total variation
smooth approximations
Online Access:http://www.mdpi.com/2313-433X/4/2/31
id doaj-4ce8f34d827d437790a3982a208e1647
record_format Article
spelling doaj-4ce8f34d827d437790a3982a208e16472020-11-24T21:59:44ZengMDPI AGJournal of Imaging2313-433X2018-01-01423110.3390/jimaging4020031jimaging4020031An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow ProblemEl Mostafa Kalmoun0Department of Mathematics, College of Science, King Khalid University, Abha 61421, Saudi ArabiaTotal variation (TV) is widely used in many image processing problems including the regularization of optical flow estimation. In order to deal with non differentiability of the TV regularization term, smooth approximations have been considered in the literature. In this paper, we investigate the use of three known smooth TV approximations, namely: the Charbonnier, Huber and Green functions. We establish the maximum theoretical error of these approximations and discuss their performance evaluation when applied to the optical flow problem.http://www.mdpi.com/2313-433X/4/2/31optical flowtotal variationsmooth approximations
collection DOAJ
language English
format Article
sources DOAJ
author El Mostafa Kalmoun
spellingShingle El Mostafa Kalmoun
An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow Problem
Journal of Imaging
optical flow
total variation
smooth approximations
author_facet El Mostafa Kalmoun
author_sort El Mostafa Kalmoun
title An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow Problem
title_short An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow Problem
title_full An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow Problem
title_fullStr An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow Problem
title_full_unstemmed An Investigation of Smooth TV-Like Regularization in the Context of the Optical Flow Problem
title_sort investigation of smooth tv-like regularization in the context of the optical flow problem
publisher MDPI AG
series Journal of Imaging
issn 2313-433X
publishDate 2018-01-01
description Total variation (TV) is widely used in many image processing problems including the regularization of optical flow estimation. In order to deal with non differentiability of the TV regularization term, smooth approximations have been considered in the literature. In this paper, we investigate the use of three known smooth TV approximations, namely: the Charbonnier, Huber and Green functions. We establish the maximum theoretical error of these approximations and discuss their performance evaluation when applied to the optical flow problem.
topic optical flow
total variation
smooth approximations
url http://www.mdpi.com/2313-433X/4/2/31
work_keys_str_mv AT elmostafakalmoun aninvestigationofsmoothtvlikeregularizationinthecontextoftheopticalflowproblem
AT elmostafakalmoun investigationofsmoothtvlikeregularizationinthecontextoftheopticalflowproblem
_version_ 1725847485046325248

Similar Items