Abstract
We propose a homography estimation method from the contours of planar regions. Standard projective invariants such as cross ratios or canonical frames based on hot points obtained from local differential properties are extremely unstable in real images suffering from pixelization, thresholding artifacts, and other noise sources. We explore alternative constructions based on global convexity properties of the contour such as discrete tangents and concavities. We show that a projective frame can be robustly extracted from arbitrary shapes with at least one appreciable concavity. Algorithmic complexity and stability are theoretically discussed and experimentally evaluated in a number of real applications including projective shape matching, alignment and pose estimation. We conclude that the procedure is computationally efficient and notably robust given the ill-conditioned nature of the problem.
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
Pizlo, Z., Rosenfeld, A.: Recognition of planar shapes from perspective images using contour-based invariants. Computer Vision, Graphics, and Image Processing 56(3), 330–350 (1992)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)
Faugeras, O., Luong, Q.T., Papadopoulo, T.: The Geometry of Multiple Images. MIT Press, Cambridge (2001)
Mundy, J., Zisserman, A.: Appendix – Projective geometry for machine vision. In: Geometric Invariances in Computer Vision, MIT Press, Cambridge (1992)
Rothwell, C.A., Zisserman, A., Forsyth, D.A., Mundy, J.L.: Canonical frames for planar object recognition. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 757–772. Springer, Heidelberg (1992)
Carlsson, S., Mohr, R., Moons, T., Morin, L., Rothwell, C., Diest, M.V., Gool, L.V., Veillon, F., Zissermann, A.: Semi-local projective invariants for the recognition of smooth plane curve. IJCV 19(3), 211–236 (1996)
Salden, A., Haar, B., Viergever, R.: Affine and projective differential geometric invariants of space curves. In: Vemuri, B. (ed.) Geometric Methods in Computer Vision II, SPIE (1993)
Zisserman, A., Blake, A., Rothwell, C., Van Gool, L., Van Diest, M.: Eliciting qualitative structure from image curve deformations. In: Proc. 4th IEEE ICCV, pp. 340–345 (1993)
Weiss, I.: Noise resistant invariants of curves. IEEE PAMI 15(9), 943–948 (1993)
Lei, Z., Blane, M.M., Cooper, D.B.: 3L fitting of higher degree implicit polynomials. In: Proc. 3rd IEEE WACV, Sarasota, USA (1996)
Tarel, J., Civi, H., Cooper, D.B.: Pose estimation of free-form 3D objects without point matching using algebraic surface models. In: Proc. 1st IEEE Workshop on Model-Based 3D Image Analysis, Mumbai, India, pp. 13–21 (1998)
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, pp. 394–409. Springer, Heidelberg (1998)
Startchik, S., Milanese, R., Pun, T.: Projective and photometric invariant representation of planar disjoint shapes. Image and Vision Comp 16(9-10), 713–723 (1998)
Chesi, G., Malis, E., Cipolla, R.: Collineation estimation from two unmatched views of an unknown planar contour for visual servoing. In: Proc. 10th BMVC, Nottingham, UK (1999)
Sato, J., Cipolla, R.: Extracting group transformations from image moments. Computer Vision and Image Understanding 73(1), 29–42 (1999)
Basri, R., Jacobs, D.: Projective alignment with regions. PAMI 23(5), 519–527 (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)
Wong, K., Cipolla, R.: Structure and motion from silhouettes. In: Proc. 8th IEEE ICCV, Vancouver, Canada, pp. 217–222 (2001)
Cipolla, R., Giblin, P.: Visual Motion of Curves and Surfaces. Cambridge University Press, Cambridge (2000)
Arbter, K., Snyder, W., Burkhardt, H., Hirzinger, G.: Application of affine-invariant fourier descriptors to recognition of 3D objects. PAMI 12(7), 640–647 (1990)
Startchik, S., Milanese, R., Rauber, C., Pun, T.: Planar shape databases with affine invariant search. In: Proc. 1st Int. Workshop on Image Databases and Multimedia Search, Amsterdam, Netherlands (1996)
Vinther, S., Cipolla, R.: Object model acquisition and recognition using 3D affine invariants. In: Proc. 4th BMVC, Guilford, UK, pp. 369–378 (1993)
Stolfi, J.: Oriented Projective Geometry. Academic Press, Boston (1991)
Melkman, A.: On-line construction of the convex hull of a simple polygon. Information Processing Letters 25, 11–12 (1987)
López-de-Teruel, P.E., Ruiz, A., Fernández, L.: Geobot: A high level visual perception architecture for autonomous robots. In: Proc. 4th IEEE ICVS, New York, USA (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ruiz, A., de Teruel, P.E.L., Fernández, L. (2006). Robust Homography Estimation from Planar Contours Based on Convexity. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3951. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744023_9
Download citation
DOI: https://doi.org/10.1007/11744023_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33832-1
Online ISBN: 978-3-540-33833-8
eBook Packages: Computer ScienceComputer Science (R0)