A Camera Calibration Method in High-Precision Vision Measuring System

This paper presents a novel camera calibration method used in high-precision machine-vision-based measuring platform. This method depends on the high precision of the motion platform. Firstly we simplified the camera model to get the relation between the real-world coordinates and the pixel coordinates; secondly we move the motion platform to change the outer parameters of the camera precisely; then we detect the corresponding motion in pixel plane and get the calibration data using the simplified camera model. According to the experiment, the method’s accuracy is acceptable and has high utility value.

[1]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[2]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

[3]  Elsayed E. Hemayed,et al.  A survey of camera self-calibration , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[4]  T. Clarke,et al.  The Development of Camera Calibration Methods and Models , 1998 .

[5]  Binoy Pinto,et al.  Speeded Up Robust Features , 2011 .

[6]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

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