The Study of Target Points Center Extracting and Matching in Calibration

Abstract:

It’s important to extract target points center from image in computer vision quickly and accurately. The center extract with the raw gradient information in the neighborhood of the target points boundary to get the parameters of the ellipse, avoids the intermediate stage of precisely extracting individual edge points. Moreover, under the dual space representation, the ellipse parameter can easily be calculated from the dual conic with the qualification of the ellipse, and the ellipse center will be got at the same time. Then, the RANSAC algorithm is used to match the pair of corresponding points between the calibration image and the calibration plate. The experiment and application result shows that the method is efficiently.

• Periodical: Advanced Materials Research (Volume 136)
• Pages: 167-171
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.136.167
• Online since: October 2010
• Authors: Bo Zhou, Dong Ping Wang, Jian Yang
• Keywords: Camera Calibration, Ellipse Center Extracting, Matching, RANSAC Algorithm

References

[1] Zhang Guangjun: Machine Vision (Science Press. Beijing 2005), pp.69-97.

[2] Li Yuan, Yan Bei: Computer Engineering and Applications Vol. 44(13) (2008) pp.242-244.

[3] J.N. Ouellet, P. Hebert: A simple operator for very precise estimation of ellipses, Computer and Robot Vision, (CRV'07), (2007), pp.21-28.

DOI: 10.1109/crv.2007.8

[4] Ma Songde, Zhang Zhengyou: Computer Vision (Science Press, Beijing 1998), pp.52-94.

[5] Zhou Bo, Chen Xinhe, Xie Xuedong: Journal of Heilongjiang Institute of Science and Technology Vol. 16 (2006), pp.107-110.

[6] Wu Fuchao: Mathematical Methods in Computer Vision (Science Press, Beijing 2008), pp.338-344.