Abstract
This paper examines the fundamental ambiguities and uncertainties inherent in recovering structure from motion. By examining the eigenvectors associated with null or small eigenvalues of the Hessian matrix, we can quantify the exact nature of these ambiguities and predict how they will affect the accuracy of the reconstructed shape. Our results for orthographic cameras show that the bas-relief ambiguity is significant even with many images, unless a large amount of rotation is present. Similar results for perspective cameras suggest that three or more frames and a large amount of rotation are required for metrically accurate reconstruction.
Chapter PDF
Similar content being viewed by others
References
H. C. Longuet-Higgins. A computer algorithm for reconstructing a scene from two projections. Nature, 293:133–135, 1981.
M. E. Spetsakis and J. Y. Aloimonos. Optimal motion estimation. In IEEE Workshop on Visual Motion, pp. 229–237, 1989.
J. Weng, N. Ahuja, and T. S. Huang. Optimal motion and structure estimation. IEEE Trans. Pattern Analysis and Machine Intelligence, 15(9):864–884, 1993.
R. Szeliski and S. B. Kang. Recovering 3D shape and motion from image streams using nonlinear least squares. J. Vis. Commun. and Image Repr., 5(1):10–28, 1994.
C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: A factorization method. Int'l J. of Computer Vision, 9(2):137–154, 1992.
O. D. Faugeras. What can be seen in three dimensions with an uncalibrated stereo rig? In Second European Conf. Computer Vision (ECCV'92), pp. 563–578, 1992
R. Hartley, R. Gupta, and T. Chang. Stereo from uncalibrated cameras. In IEEE Conf. Computer Vision and Pattern Recognition (CVPR'92), pp. 761–764, 1992.
R. Mohr, L. Veillon, and L. Quan. Relative 3D reconstruction using multiple uncalibrated images. In IEEE Conf. Computer Vision and Pattern Recognition (CVPR'93), pp. 543–548, 1993.
H. C. Longuet-Higgins. Visual motion ambiguity. Vision Research, 26(1):181–183, 1986.
R. Szeliski and S. B. Kang. Shape ambiguities in structure from motion. Technical Report 96/1, Digital Equipment Corporation, Cambridge Research Lab, Cambridge, MA, 1996.
N. Cui, J. Weng, and P. Cohen. Extended structure and motion analysis from monocular image sequences. In Third, Int'l Conf. Computer Vision (ICCV'90), pp. 222–229, 1990.
C. J. Taylor, D. J. Kriegman, and P. Anandan. Structure and motion in two dimensions from multiple images: A least squares approach. In IEEE Workshop on Visual Motion, pp. 242–248, 1991.
A. Azarbayejani and A. P. Pentland. Recursive estimation of motion, structure, and focal length. IEEE Trans. Pottern Analysis and Machine Intelligence, 17(6):562–575, 1995.
J. J. Koenderink and A. J. van Doorn. Affine structure from motion. J. of the Optical Society of America A, 8:377–385538, 1991.
G. Adiv. Inherent ambiguities in recovering 3-D motion and structure from a noisy flow field. IEEE Trans. Pattern Analysis and Machine Intelligence, 11(5):477–490, 1989.
G.-S. Y. Young and R. Chellappa. Statistical analysis of inherent ambiguities in recovering 3-d motion from a noisy flow field. IEEE Trans. Pattern Analysis and Machine Intelligence, 14(10):995–1013, 1992.
J. Oliensis and J. I. Thomas. Incorporating motion error in multi-frame structure from motion. In IEEE Workshop on Visual Motion, pp. 8–13, 1991.
N. Ayache. Artificial Vision for Mobile Robots: Stereo Vision and Multisensory Perception. MIT Press, Cambridge, MA, 1991.
W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling. Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press, Cambridge, England, 1992.
Stephen Wolfram. Mathematica: A System for Doing Mathematics by Computer. Addison-Wesley, Redwood City, CA, 1991.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Szeliski, R., Kang, S.B. (1996). Shape ambiguities in structure from motion. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015580
Download citation
DOI: https://doi.org/10.1007/BFb0015580
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61122-6
Online ISBN: 978-3-540-49949-7
eBook Packages: Springer Book Archive
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.