GML C++ Camera Calibration Toolbox

Contact person: Alexander Velizhev (avelizhev@graphics.cs.msu.ru)

Downloads

Latest binaries:
Download GML C++ Camera Calibration Toolbox 0.75


Latest sources:
Download GML C++ Camera Calibration sources 0.71

Download GML C++ Camera Calibration sources 0.4

Image samples:
Download images

 

ChangeLog

16.07.2013 v0.75

  • A critical bug was fixed.
23.12.2011 v0.73
  • Two criticals bugs were fixed. Many thanks to Fedor Ermishin for the great feedback!

23.12.2011 v0.71

  • Some criticals bugs and memory leaks were fixed. Many thanks to Mathieu Peyréga for the great feedback! He helped us a lot to make this update.

18.11.2011 v0.7

  • Camera calibration using multiples patterns;
  • Support video data (usage of each N-frame);

Figure 1: GML Camera Calibration toolbox v. 0.7 supports multiple calibration patterns within one project. During the calibration a relative orientation between pattern coordinate systems is recovered. Our experiments show the usage of multiple patterns makes the calibration procedure more stable and impoves calibration accuracy. Also less images for calibration are needed.

.

06.02.2006 v0.4

  • Calibration module is OS independent;
  • Added image zoom functions;
  • Added a new tab "Point Density" for the points location control

27.10.2005 v0.31

  • Added a new function "Undistort"
  • Added an accuracy rating of parameters
  • Added new export formats

26.09.2005 v.0.1

  • First release

Introduction

GML Camera Calibration toolbox is a free functionally completed tool for cameras' calibrating. You can easy calculate intrinsic and extrinsic camera parameters after calibrating. This software uses a as a calibration pattern. The calibration process is completely automatic. There are two chessboard detection algorithms in all.

 Figure 2: Toolbox interface.

  Figure 3: Calibration results.

GML Camera Calibration toolbox 0.7 supports multiple calibration patterns within one project. During the calibration a relative orientation between pattern coordinate systems is recovered. The usage of multiple patterns makes the calibration procedure more stable, this impoves calibration accuracy and less images for calibration is needed.

  Figure 4: Comparison of camera calibration using different number of patterns.

 

GML Camera Calibration toolbox 0.7 (beta) was released on 18.11.2011. Your Feedback is appreciated!

Requirements

The code was written for OpenCV 2.1 and was tested mostly on win32 (Windows XP, Windows Vista, Windows 7) platform. System Requirements: .Net Framework 3.5 SP1

Please read our recommendations for taking calibration photos before starting a calibration procedure.

Projects

Team

    Acknowledgements

    We extend our gratitude to Chibunitchev A., whose help was significant in creation of this toolbox.