A camera calibration technique based on OpenCV

Camera calibration is very improtant in 3D computer vision systems. In this paper, the camera model in OpenCV (open source computer vision library) is discussed, the non-linear distortion of the tangential and radial distortion aberration are considered. Based on these, we introduce the corner extraction of the Camera Calibration Toolbox for Matlab, and an arithmetic of camera calibration based on OpenCV is given. The proposed algorithm can achieve accurate results. It has features such as computational efficiency and good cross-platform portability. It is able to meet the needs of 3D computer vision systems. Experimental results show the feasibility of the proposed method.

[1]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[2]  Paul R. Schrater,et al.  Bayesian modelling of camera calibration and reconstruction , 2005, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05).

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

[4]  Linda G. Shapiro,et al.  Computer Vision , 2001 .

[5]  Fernando Jaureguizar,et al.  VISIRE: photorealistic 3D reconstruction from video sequences , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[6]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[7]  Edi Karni,et al.  Utility theory with uncertainty , 1991 .

[8]  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..