A Flexible New Technique for Camera Calibration
IEEE Transactions on Pattern Analysis and Machine Intelligence
Use of the Hough transformation to detect lines and curves in pictures
Communications of the ACM
Multiple view geometry in computer visiond
Multiple view geometry in computer visiond
Machine Vision and Applications
Camera Self-Calibration: Theory and Experiments
ECCV '92 Proceedings of the Second European Conference on Computer Vision
A simple and robust line detection algorithm based on small eigenvalue analysis
Pattern Recognition Letters
A straight line detection using principal component analysis
Pattern Recognition Letters
An Algebraic Approach to Lens Distortion by Line Rectification
Journal of Mathematical Imaging and Vision
A Simple Method of Radial Distortion Correction with Centre of Distortion Estimation
Journal of Mathematical Imaging and Vision
Interpreting perspective images
Artificial Intelligence
New orientation-based elimination approach for accurate line-detection
Pattern Recognition Letters
Generic self-calibration of central cameras
Computer Vision and Image Understanding
Accurate Depth Dependent Lens Distortion Models: An Application to Planar View Scenarios
Journal of Mathematical Imaging and Vision
Robust radial distortion from a single image
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part II
Automatic Radial Distortion Estimation from a Single Image
Journal of Mathematical Imaging and Vision
Hi-index | 0.10 |
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.