Optical Aberration Correction by Divide-and-Learn for Accurate Camera Calibration

  title={Optical Aberration Correction by Divide-and-Learn for Accurate Camera Calibration},
  author={Yongtae Do},
  journal={2014 International Conference on Computational Science and Computational Intelligence},
  • Y. Do
  • Published 10 March 2014
  • Physics
  • 2014 International Conference on Computational Science and Computational Intelligence
The accuracy of three dimensional vision depends heavily on the accuracy of camera calibration. A major source of calibration error is the system nonlinearity due mainly to optical aberration. Although there are various physical models that have been employed to correct the nonlinear image distortion due to the aberration, it is uncertain practically that which model best fits a given optical system. In this paper, an intelligent learning technique to correct errors from the nonlinear optics is… 

Figures and Tables from this paper



A new method for linear camera calibration and nonlinear distortion correction

Recent progress of images taken by non-metric digital cameras encourages amateurs to utilize it for 3D measurements, but also introduces the difficulties of calibration. The ideal camera projection

Camera Calibration with Distortion Models and Accuracy Evaluation

A camera model that accounts for major sources of camera distortion, namely, radial, decentering, and thin prism distortions is presented and a type of measure is introduced that can be used to directly evaluate the performance of calibration and compare calibrations among different systems.

Correcting non-linear lens distortion in cameras without using a model

Hybrid calibration of CCD cameras using artificial neural nets

  • J. WenG. Schweitzer
  • Computer Science
    [Proceedings] 1991 IEEE International Joint Conference on Neural Networks
  • 1991
It is shown experimentally that the accuracy of the image frame coordinates has been improved by a factor two through the hybrid calibration, and appears to be a new idea to add an artificial neural network to the physical and mathematical model of a system in order to improve the overall description of the system.

An Efficient Method for Camera Calibration Using MultiLayer Perceptron Type Neural Network

The experimental results show that the proposed 3D camera calibration method improved calibration accuracy over widely used Tsai's two stage method (TSM).

Analytically solving radial distortion parameters

  • Simone GrafT. Hanning
  • Physics
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
This article shows that the problem of determining the parameters of a radial distortion can be solved in a closed form, and presents an algorithm in which this is done and compares it to classic approaches.

Implicit and Explicit Camera Calibration: Theory and Experiments

  • G. WeiSongde Ma
  • Computer Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1994
Under the assumption of the radial distortion model, this paper presents a computationally efficient method for explicitly correcting the distortion of image coordinates in frame buffer without involving the computation of camera position and orientation.

On the neural computation of the scale factor in perspective transformation camera model

  • Y. Do
  • Computer Science
    2013 10th IEEE International Conference on Control and Automation (ICCA)
  • 2013
A unique neural network structure and its learning algorithm to compute the scale factor of a 3D point so that further vision processing such as camera calibration can be performed efficiently using the value.

The calibration problem for stereoscopic vision

This paper first reviews the pinhole camera model that is used and analyzes its relationship with respect to the internal camera parameters and its position in space, then studies its behavior withrespect to changes of coordinate systems.