Abstract
The shapes of many natural and man-made objects have curved contours. The images of such contours usually do not have sufficient distinctive features to apply conventional feature-based reconstruction algorithms. This paper shows that both the shape of curves in 3-D space and the camera poses can be accurately reconstructed from their perspective images with unknown point correspondences given that the curves have certain invariant properties such as symmetry. We show that in such cases the minimum number of views needed for a solution is remarkably small: one for planar curves and two for nonplanar curves (of arbitrary shapes), which is significantly less than what is required by most existing algorithms for general curves. Our solutions rely on minimizing the L 2-distance between the shapes of the curves reconstructed via the “epipolar geometry” of symmetric curves. Both simulations and experiments on real images are presented to demonstrate the effectiveness of our approach.
Chapter PDF
Similar content being viewed by others
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
Faugeras, O.: Three-Dimensional Computer Vision, A geometric approach. MIT Press, Cambridge (1993)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)
Schmid, C., Zisserman, A.: The geometry and matching of curves in multiple views. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, p. 394. Springer, Heidelberg (1998)
Papadopoulo, T., Faugeras, O.: Computing structure and motion of general 3D curves from monocular sequences of perspective images. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064. Springer, Heidelberg (1996)
Papadopoulo, T., Faugeras, O.: Computing structure and motion of general 3D curves from monocular sequences of perspective images. Technical Report 2765, INRIA (1995)
Wong, K.Y.K., Cipolla, R.: Structure and motion from silhouettes. In: 8th IEEE International Conference on Computer Vision, Vancouver, Canada, vol. II, pp. 217–222 (2001)
Mendonça, P.R.S., Wong, K.Y.K., Cipolla, R.: Camera pose estimation and reconstruction from image profiles under circular motion. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 864–877. Springer, Heidelberg (2000)
Cipolla, R., Blake, A.: Surface shape from the deformation of apparent contours. In: IEEE International Conference on Computer Vision, pp. 83–112 (1992)
Cross, G., Zisserman, A.W.F.: Parallax geometry of smooth surfaces in multiple views. In: IEEE International Conference on Computer Vision, pp. 323–329 (1999)
François, A., Medioni, G.G.: A human-assisted system to build 3-D models from a single image. In: IEEE International Conference on Multimedia Computing and Systems, pp. 282–288 (1999)
Berthilsson, R., Astrom, K., Heyden, A.: Reconstruction of curves in R3, using factorization and bundle adjustment. In: IEEE International Conference on Computer Vision (1999)
Berthilsson, R., Astrom, K.: Reconstruction of 3D-curves from 2D-images using affine shape methods for curves. In: International Conference on Computer Vision and Pattern Recognition (1997)
Kaminski, J., Fryers, M., Shashua, A., Teicher, M.: Multiple view geometry of non-planar algebraic curves. In: IEEE International Conference on Computer Vision (2001)
Kaminski, J., Shashua, A.: On calibration and reconstruction from planar curves. In: European Conference on Computer Vision (2000)
Hong, W.: Geometry and reconstruction from spatial symmetry. Master Thesis, UIUC (2003)
Hong, W., Yang, A.Y., Ma, Y.: On symmetry: Structure, pose and calibration from a single image. International Journal on Computer Vision (2002) (submitted)
Mitsumoto, H., Tamura, S., Okazaki, K., Fukui, Y.: 3-D reconstruction using mirror images based on a plane symmetry recovering method. IEEE Transactions on Pattern Analysis and Machine Intelligence 14, 941–946 (1992)
Zabrodsky, H., Weinshall, D.: Using bilateral symmetry to improve 3D reconstruction from image sequences. Compupter Vision and Image Understanding 67, 48–57 (1997)
Zabrodsky, H., Peleg, S., Avnir, D.: Symmetry as a continuous feature. IEEE Transactions on Pattern Analysis and Machine Intelligence 17, 1154–1166 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hong, W., Ma, Y., Yu, Y. (2004). Reconstruction of 3-D Symmetric Curves from Perspective Images without Discrete Features. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3023. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24672-5_42
Download citation
DOI: https://doi.org/10.1007/978-3-540-24672-5_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21982-8
Online ISBN: 978-3-540-24672-5
eBook Packages: Springer Book Archive