3-D curve reconstruction from uncalibrated cameras

There has been considerable work recently on the problem of reconstruction of 3D points sets from two images, taken by uncalibrated cameras. However, the point correspondence has to be given. In this paper we deal with reconstruction of curves rather than points. While we need the correspondence between curves, this is an easier problem because curves are far fewer and more distinctive than points. We derive a simple and general reconstruction method, based on an invariant coordinate system. We then apply it to non-coplanar conics and to combinations of a 3D conic with points. 3D cubics are also discussed. Unlike previous work we do not need to know the epipolar geometry; we recover it from the images.

[1]  Isaac Weiss,et al.  Projective invariants of shapes , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Long Quan,et al.  Relative 3D Reconstruction Using Multiple Uncalibrated Images , 1995, Int. J. Robotics Res..

[3]  Long Quan,et al.  Conic Reconstruction and Correspondence From Two Views , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Luc Van Gool,et al.  Affine reconstruction from perspective image pairs obtained by a translating camera , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[5]  Eamon B. Barrett,et al.  Some invariant linear methods in photogrammetry and model-matching , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Amnon Shashua Algebraic Functions For Recognition Amnuon Shashua , .

[7]  Richard I. Hartley,et al.  Projective Reconstruction and Invariants from Multiple Images , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  O. D. Faugeras,et al.  Camera Self-Calibration: Theory and Experiments , 1992, ECCV.