Camera calibration using two or three vanishing points

The perspective projection models the way a 3D scene is transformed into a 2D image, usually through a camera or an eye. In a projective transformation, parallel lines intersect in a point called vanishing point. This paper presents in detail two calibration methods that exploit the properties of vanishing points. The aim of the paper is to offer a practical tool for the choice of the appropriate calibration method depending on the application and on the initial conditions. The methods, using two respectively three vanishing points, are presented in detail and are compared. First, the two models are analyzed using synthetic data. Finally, each method is tested in a real configuration and the results show the quality of the calibration.

[1]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[2]  Jana Kosecka,et al.  Efficient computation of vanishing points , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[3]  Janne Heikkilä,et al.  A four-step camera calibration procedure with implicit image correction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Ernest L. Hall,et al.  Measuring Curved Surfaces for Robot Vision , 1982, Computer.

[5]  Jean-Yves Bouguet,et al.  Camera calibration toolbox for matlab , 2001 .

[6]  Roberto Cipolla,et al.  Camera Calibration from Vanishing Points in Image of Architectural Scenes , 1999, BMVC.

[7]  D. W. Murray,et al.  Camera Calibration using Vanishing Points , 1992 .

[8]  Michael Bosse,et al.  Vanishing points and three-dimensional lines from omni-directional video , 2003, The Visual Computer.

[9]  Dong Hoon Lee,et al.  Intrinsic Camera Calibration Based on Radical Center Estimation , 2004, CISST.

[10]  Carsten Rother,et al.  A New Approach for Vanishing Point Detection in Architectural Environments , 2000, BMVC.

[11]  L. Grammatikopoulosa,et al.  CAMERA CALIBRATION COMBINING IMAGES WITH TWO VANISHING POINTS , 2004 .

[12]  Jean-Philippe Tardif,et al.  Non-iterative approach for fast and accurate vanishing point detection , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[13]  Y.F. Li,et al.  A novel method for camera calibration using vanishing points , 2007, 2007 14th International Conference on Mechatronics and Machine Vision in Practice.

[14]  B. Caprile,et al.  Using vanishing points for camera calibration , 1990, International Journal of Computer Vision.

[15]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[16]  Eric Maisel,et al.  Using vanishing points for camera calibration and coarse 3D reconstruction from a single image , 2000, The Visual Computer.

[17]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[18]  Philipp Slusallek,et al.  Wide area camera calibration using virtual calibration objects , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[19]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Richard I. Hartley,et al.  Sensitivity of Calibration to Principal Point Position , 2002, ECCV.

[21]  Xavier Armangué,et al.  A comparative review of camera calibrating methods with accuracy evaluation , 2002, Pattern Recognit..