Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/11184
Title: Computing inverse optical flow
Authors: Sánchez, Javier 
Salgado de la Nuez, Agustín Javier 
Monzón, Nelson 
UNESCO Clasification: 220990 Tratamiento digital. Imágenes
Keywords: Inverse optical flow
Backward flow
Inverse mapping
Back registration
Occlusions, et al
Issue Date: 2015
Citation: CTIM Technical Report nº3
Journal: Pattern Recognition Letters 
Abstract: We propose four algorithms for computing the inverse optical flow between two images. We assume that the forward optical flow has already been obtained and we need to estimate the flow in the backward direction. The forward and backward flows can be related through a warping formula, which allows us to propose very efficient algorithms. These are presented in increasing order of complexity. The proposed methods provide high accuracy with low memory requirements and low running times.In general, the processing reduces to one or two image passes. Typically, when objects move in a sequence, some regions may appear or disappear. Finding the inverse flows in these situations is difficult and, in some cases, it is not possible to obtain a correct solution. Our algorithms deal with occlusions very easy and reliably. On the other hand, disocclusions have to be overcome as a post-processing step. We propose three approaches for filling disocclusions. In the experimental results, we use standard synthetic sequences to study the performance of the proposed methods, and show that they yield very accurate solutions. We also analyze the performance of the filling strategies. 
URI: http://hdl.handle.net/10553/11184
ISSN: 0167-8655
DOI: 10.1016/j.patrec.2014.09.009
Source: Pattern Recognition Letters[ISSN 0167-8655],v. 52, p. 32-39
Appears in Collections:Artículos
Thumbnail
Informes y Memorias
Adobe PDF (11,78 MB)
Show full item record

SCOPUSTM   
Citations

6
checked on Mar 24, 2024

WEB OF SCIENCETM
Citations

6
checked on Feb 25, 2024

Page view(s)

112
checked on Mar 2, 2024

Download(s)

337
checked on Mar 2, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



This item is licensed under a Creative Commons License Creative Commons