Abstract
We discuss briefly a number of areas where epipolar geometry is currently central in carrying out visual tasks. In contrast we demonstrate configurations for which 3D projective invariants can be computed from perspective stereo pairs, but epipolar geometry (and full projective structure) cannot. We catalogue a number of these configurations which generally involve isotropies under the 3D projective group, and investigate the connection with camera calibration. Examples are given of the invariants recovered from real images. We also indicate other areas where a strong reliance on epipolar geometry should be avoided, in particular for image transfer.
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Beardsley, P., Sinclair, D., Zisserman, A., Ego-motion from six points, Insight meeting, Catholic University Leuven, Feb. 1992.
Buchanan, T., The twisted cubic and camera calibration. Computer Vision, Graphics, and Image Processing, 42, 130–132, 1988.
Demey, S., Zisserman, A., and Beardsley, P., Affine and projective structure from motion, Proc. BMVC92, Springer-Verlag, 1992
Faugeras, O.D. and Maybank, S.J., Motion from point matches: multiplicity of solutions, IJCV-4, 225–246, 1990.
Faugeras, O.D., Luong, Q.T., and Maybank, S.J., Camera self-calibration: theory and experiments, Proc. ECCV-92, Springer-Verlag, 321–334, 1992.
Faugeras, O.D., What can be seen in three dimensions with an uncalibrated stereo rig?, Proc. ECCV-92, Springer-Verlag, 563–578, 1992.
Faugeras, O.D. and Robert, L., What can two images tell us about a third one? Proc. ECCV-94, Springer-Verlag, 485–492, 1994.
Gros, P. and Quan, L., Présentation de la théorie des invariants sous une forme utilisable en vision par ordinateur, TR, LIFIA, 1991.
Hartley, R.I., Invariants of points seen in multiple images, G.E. Internal Report 1992, also to appear PA MI.
Hartley, R.I., Gupta, R. and Chang, T., Stereo from uncalibrated cameras, Proc. of CVPR-92, 1992.
Hartley, R.I., Self-calibration of stationary cameras. Proc. ECCV-94, 1994.
Longuet-Higgins, H.C., A computer algorithm for reconstructing a scene from two projections, Nature, Vol., 293, 10, Sept. 1981.
Luong, Q.T., Matrice Fondamentale et Autocalibration en Vision par Ordinateur. PhD thesis, Université de Paris-Sud, France, 1992.
Luong, Q.T. and T. Viéville. Canonic representations for the geometries of multiple projective views. Tech. Report UCB/CSD-93-772, University of California, Berkeley, USA, 1993.
Maybank, S.J., The projective geometry of ambiguous surfaces, Phil. Trans. Roy. Soc. Lond. Series A Vol. 332, 1–47, 1990.
Maybank, S.J., Properties of essential matrices, Int. J. Imaging Systems and Technology, 2, 380–384, 1990.
Maybank, S.J. and Faugeras, O.D., A theory of self-calibration of a moving camera. International Journal of Computer Vision, 8:123–151, 1992.
Maybank, S.J., Theory of Reconstruction from Image Motion. Springer Series in Information Science vol 28. Springer-Verlag: Berlin, 1993.
Mohr, R., Projective geometry and computer vision, Handbook of Pattern Recognition and Computer Vision, Chen, Pau and Wang editors, 1992.
Mohr, R., Sparr, R. and Faugeras, O., Multiple image invariants, Proc. ESPRIT Workshop on Invariants in Vision, Santa Margherita Ligure, 1992.
Mundy, J. L. and Zisserman, A. (editors), Geometric Invariance in Computer Vision, MIT Press, Cambridge Ma, 1992.
Quan, L. and Mohr, R., Towards structure from motion for linear features through reference points, Proc. IEEE Workshop on Visual Motion, 1991.
Semple, J.G. & Kneebone, G.T., Algebraic Projective Geometry. Oxford: Clarendon Press, 1953 (reprinted 1979).
Shapiro, L.S., Zisserman, A. and Brady, J.M., Motion from point matches using affine epipolar geometry, Proc. ECCV-94, 1994.
Shapiro, L.S., Affine analysis of image sequences, PhD thesis, Oxford University, 1993.
Shashua, A., Trilinearity in visual recognition by alignment, Proc. ECCV-94, 1994.
Szeliski, R. and Kang, S.B., Recovering 3D shape and motion from image streams using non-linear least squares, DEC Tech. Rep., 93/3, 1993.
Torr, P.H.S. and Murray, D.W., Stochastic motion clustering, Proc. ECCV-94, Springer-Verlag, 328–337, 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zisserman, A., Maybank, S.J. (1994). A case against epipolar geometry. In: Mundy, J.L., Zisserman, A., Forsyth, D. (eds) Applications of Invariance in Computer Vision. AICV 1993. Lecture Notes in Computer Science, vol 825. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58240-1_4
Download citation
DOI: https://doi.org/10.1007/3-540-58240-1_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58240-3
Online ISBN: 978-3-540-48583-4
eBook Packages: Springer Book Archive