Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/45744
Title: Line detection in images showing significant lens distortion and application to distortion correction
Authors: Alemán-Flores, Miguel 
Alvarez, Luis 
Gomez, Luis 
Santana-Cedrés, Daniel 
UNESCO Clasification: 220990 Tratamiento digital. Imágenes
120601 Construcción de algoritmos
120602 Ecuaciones diferenciales
120326 Simulación
Keywords: Line detection
Lens distortion
Hough transform
Issue Date: 2014
Project: Modelización Matemática de Los Procesos de Calibración de Cámaras de Video. 
Journal: Pattern Recognition Letters 
Abstract: Lines are one of the basic primitives used by the perceptual system to analyze and interpret a scene. Therefore, line detection is a very important issue for the robustness and flexibility of Computer Vision systems. However, in the case of images showing a significant lens distortion, standard line detection methods fail because lines are not straight. In this paper we present a new technique to deal with this problem: we propose to extend the usual Hough representation by introducing a new parameter which corresponds to the lens distortion, in such a way that the search space is a three-dimensional space, which includes orientation, distance to the origin and also distortion. Using the collection of distorted lines which have been recovered, we are able to estimate the lens distortion, remove it and create a new distortion-free image by using a two-parameter lens distortion model. We present some experiments in a variety of images which show the ability of the proposed approach to extract lines in images showing a significant lens distortion.
URI: http://hdl.handle.net/10553/45744
ISSN: 0167-8655
DOI: 10.1016/j.patrec.2013.06.020
Source: Pattern Recognition Letters [ISSN 0167-8655], v. 36, p. 261-271
Appears in Collections:Artículos
Adobe PDF (878,7 kB)
Show full item record

SCOPUSTM   
Citations

22
checked on Nov 3, 2024

WEB OF SCIENCETM
Citations

22
checked on Nov 3, 2024

Page view(s)

153
checked on Oct 31, 2024

Download(s)

57
checked on Oct 31, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



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