Using Single Image Parallelepipeds for Camera Calibration

Abstract:

Human vision is generally regarded as a complicated process from feeling to consciousness. In other words, it refers to a projection form 3-D object to 2-D image, as well as a cognition of real objects according to 2-D image,The process that a real object is modeled through some images is called 3-D reconstruction. Presently, camera calibration attracts many researchers, and it includes the internal parameters and the external parameters, such as coordinate of main point, parameters of rotation and translation. Some researchers have pointed out that parallelepiped has a strict topological structure and geometric constraints. Therefore, it is suitable for the self-calibration of camera. This paper briefly explains parallelepiped methods and tries to apply this method to deal with self-calibration. The experiments show that this method is flexible and available. image.

• Periodical: Applied Mechanics and Materials (Volumes 496-500)
• Pages: 1869-1872
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.496-500.1869
• Online since: January 2014
• Authors: Ye Tian, Zhen Wei Wang, Feng Chen
• Keywords: Camera Self-Calibration, Geometric Constraints, Parallelepiped, Topological Constraints

References

[1] R. Tsai, An Efficient and Accurate Camera Calibration Techniquefor 3D Machine Vision, Proc. Conf. Computer Vision and Pattern Recognition, pp.364-374, (1986).

[2] Zhengyou Zhang : A Flexible New Technique for Camera Calibration IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.

DOI: 10.1109/34.888718

[3] S.J. Maybank and O.D. Faugeras, A theory of Self-calibration of a Moving Camera[J], Internal Journal of Computer Vision, 1992, 8(2): 123-151.

DOI: 10.1007/bf00127171

[4] Hartley R. Kruppa's equations derived from the fundamental [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19(2): 133-135.

DOI: 10.1109/34.574792

[5] B. Triggs, Auto calibration and the Absolute Quadric, Proc. Conf. Computer Vision and Pattern Recognition, pp.609-614, (1997).

[6] S.D. Ma, A Self-calibration Technique for Active Vision System[J], IEEE Trans. on Robot Automation, 12(1), 114-120, (1996).

DOI: 10.1109/70.481755

[7] Marta Wilczkowiak, Peter Sturm, and Edmond Boyer Using Geometric Constraints through Parallelepipeds for Calibration and 3D Modeling[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, pp.194-207, (2005).

DOI: 10.1109/tpami.2005.40

[8] Guangjun Zhang. Computer vision[M]. ed. Changfang Ma , Beijing: Science Press，2004: 33-36 (In Chinese).

[9] R. Y. Tsai. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf tv cameras and lenses. IEEE Journal of Robotics and Automation, 3(4): 323–344, Aug. (1987).

DOI: 10.1109/jra.1987.1087109

[10] Caprile, B., Torre, V.: Using Vanishing Points for Camera Calibration. IJCV 4 (1990) 127–140.

[11] Capril Rother A new approach to vanishing point detection in architecture environments . Image and Vision Computering 20(2002)Vol: 20, Issue: 9-10, pp.647-655.

DOI: 10.1016/s0262-8856(02)00054-9

[12] Richard Szeliski: computer vision: algorithms and applications, Springer, (2010).