Abstract
An accurate estimate of the epipole (direction of camera translation) is necessary if image motion is to be decomposed into rotational and translational components, which give the camera rotation and feature depths respectively. In this paper we introduce the Linearised Subspace Method to find direct constraints on the epipole which are independent of camera rotation and scene structure. We present methods to compute reliable constraints and their uncertainties from image motion. We show how erroneous constraints due to errors in tracking can be rejected and how the valid constraints should be combined to form accurate estimates of the direction of translation. Experimental results show these methods lead to improvements in the recovery of camera motion and that the uncertainty estimates are accurate and useful in detecting degenerate scene structure or camera motions.
Chapter PDF
References
R. Cipolla, Y. Okamoto, and Y. Kuno. Robust structure from motion using motion parallax. In Proc. 4th International Conf. on Computer Vision, pages 374–382, 1993.
O.D. Faugeras, Q.-T. Luong, and S.J. Maybank. Camera self-calibration: Theory and experiments. In G. Sandini, editor, Proc. 2rd European Conf. on Computer Vision, pages 321–334. Springer-Verlag, 1992.
M. A. Fischler and R. C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381–395, 1981.
G.H. Golub and CF. van Loan. Matrix Computations. North Oxford Academic, 1986.
C.G. Harris. Geometry from visual motion. In A. Blake and A. Yuille, editors, Active Vision, chapter 16. MIT Press, 1992.
R.I. Hartley and P. Sturm. Triangulation. In Proceedings of the DARPA Image Understanding Workshop, pages 957–966, 1994.
A.D. Jepson and D.E. Heeger. Linear subspace methods for recovering translational direction. In L. Harris and M. Jenkin, editors, Spatial vision in humans and robots. Cambridge University Press, 1993. Also, University of Toronto, Department of Computer Science, Technical Report: RBCV-TR-92-40, April 1992.
K. Kanatani. Computational projective geometry. Computer Vision, Graphics and Image Processing (Image Understanding), 54(3):333–348, 1991.
K. Kanatani. Renormalization for unbiased estimation. In Proc. 4th International Conf. on Computer Vision, pages 599–606, 1993.
J.M. Lawn and R. Cipolla. Robust egomotion estimation from affine motion-parallax. In Proc. 3rd European Conf. on Computer Vision, pages I.205–210, 1994.
J.M. Lawn and R. Cipolla. Reliable extraction of the camera motion using constraints on the epipole. Technical Report CUED/F-INFENG/TR.240, University of Cambridge, 1995.
H.C. Longuet-Higgins and K. Prazdny. The interpretation of a moving retinal image. Proc. of the Royal Society of London, Series B, 208:385–397, 1980.
C. Rothwell, G. Csurka, and O. Faugeras. A comparison of projective reconstruction methods for pairs of views. In Proc. 5th International Conf. on Computer Vision, pages 932–937, 1995.
P.H.S. Torr. Motion Segmentation and Outlier Detection. PhD thesis, Department of Engineering Science, University of Oxford, 1995.
D.H. Wolpert. Combining generalizers using partitions of the learning set. In L.Nadel and D.Stein, editors, 1992 Lectures in Complex Systems. Addison-Wesley, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lawn, J., Cipolla, R. (1996). Reliable extraction of the camera motion using constraints on the epipole. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1065. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61123-1_136
Download citation
DOI: https://doi.org/10.1007/3-540-61123-1_136
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61123-3
Online ISBN: 978-3-540-49950-3
eBook Packages: Springer Book Archive