Abstract
A method is developed for the computation of depth maps, modulo scale, from one single image of a polyhedral scene. Only affine shape properties of the scene and image are used, hence no metrical information. Results from simple experiments show good performance, both what concerns exactness and robustness. It is also shown how the underlying theory may be used to single out and characterise certain singular situations that may occur in machine interpretation of line drawings.
The work has been supported by the Swedish National Board for Industrial and Technical Development, (NUTEK).
This article was processed using the LATEX macro package with ECCV92 style.
Chapter PDF
Similar content being viewed by others
References
Coxeter, H.M.S., Emmer, M., Penrose, R., Teuber, M.L.: M.C. Escher: Art and Science. Elsevier, Amsterdam (1986)
Faugeras, O.D.: What can be seen in three dimensions with an uncalibrated stereo rig? Proc. ECCV92 (1992) (to appear)
Horn, B.K.P.: Robot Vision. MIT Press, Cambridge, MA. (1986)
Koenderink, J.J., van Doorn, A.J.: Affine Structure from Motion. J. of the Opt. Soc. of America (1992) (to appear)
Lamdan, Y., Schwartz, J.T., Wolfson, H.J.: Affine Invariant Model-Based Object Recognition. IEEE Trans. Robotics and Automation 6 (1990) 578–589
Mohr, R., Morin, L., Grosso, E.: Relative positioning with poorly calibrated cameras. In Proc. DARPA-ESPRIT Workshop on Applications of Invariance in Computer Vision (1991)
Persson, A.: A method for correction of images of origami/polyhedral objects. Proc. Swedish Society for Automated Image Analysis. Uppsala, Sweden. (1992) (to appear)
Sparr, G., Nielsen, L.: Shape and mutual cross-ratios with applications to exterior, interior and relative orientation. Proc. Computer Vision — ECCV90. Springer Verlag, Lect. Notes in Computer Science (1990) 607–609
Sparr, G.: Projective invariants for affine shapes of point configurations. In Proc. DARPA-ESPRIT Workshop on Applications of Invariance in Computer Vision (1991)
Sparr, G.: Depth computations from polyhedral images, or: Why is my computer so distressed about the Penrose triangle. CODEN:LUFTD2(TFMA-91)/7004, Lund (1991)
Sparr, G.: On the “reconstruction” of impossible objects. Proc. Swedish Society for Automated Image Analysis. Uppsala, Sweden. (1992) (to appear)
Sugihara, K.: Mathematical Structures of Line Drawings of Polyhedrons — Toward Man-Machine Communication by Means of Line Drawings. IEEE Trans. Pattern Anal. Machine Intell. 4 (1982) 458–469
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sparr, G. (1992). Depth computations from polyhedral images. In: Sandini, G. (eds) Computer Vision — ECCV'92. ECCV 1992. Lecture Notes in Computer Science, vol 588. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55426-2_43
Download citation
DOI: https://doi.org/10.1007/3-540-55426-2_43
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55426-4
Online ISBN: 978-3-540-47069-4
eBook Packages: Springer Book Archive