Abstract
We present a novel geometric approach for solving the stereo problem for an arbitrary number of images (greater than or equal to 2). It is based upon the definition of a variational principle that must be satisfied by the surfaces of the objects in the scene and their images. The Euler-Lagrange equations which are deduced from the variational principle provide a set of PDE's which are used to deform an initial set of surfaces which then move towards the objects to be detected. The level set implementation of these PDE's potentially provides an efficient and robust way of achieving the surface evolution and to deal automatically with changes in the surface topology during the deformation, i.e. to deal with multiple objects. Results of an implementation of our theory also dealing with occlusion and vibility are presented on synthetic and real images.
Chapter PDF
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
V. Caselles, R. Kimmel, and G. Sapiro. Geodesic active contours. In Proceedings of the International Conference on Computer Vision, pages 694–699, 1995.
V. Caselles, R. Kimmel, G. Sapiro, and C. Sbert. 3d active contours. In M-O. Berger, R. Deriche, I. Herlin, J. Jaffre, and J-M. Morel, editors, Images, Wavelets and PDEs, volume 219 of Lecture Notes in Control and Information Sciences, pages 43–49. Springer, June 1996.
David L. Chopp. Computing minimal surfaces via level set curvature flow. Journal of Computational Physics, 106:77–91, 1993.
R. Deriche. Recursively implementing the gaussian and its derivatives. Technical Report 1893, INRIA, Unité de Recherche Sophia-Antipolis, 1993.
Rachid Deriche, Stéphane Bouvin, and Olivier Faugeras. A level-set approach for stereo. In Fisrt Annual Symposium on Enabling Technologies for Law Enforcement and Security — SPIE Conference 2942: Investigative Image Processing., Boston, Massachusetts USA, November 1996.
M. P. DoCarmo. Differential Geometry of Curves and Surfaces. Prentice-Hall, 1976.
Olivier Faugeras. Three-Dimensional Computer Vision: a Geometric Viewpoint. MIT Press, 1993.
Olivier Faugeras and Renaud Keriven. Variational Principles, Surface Evolution, PDE's. Level Set Methods and the Stereo Problem. Technical Report 3021, INRIA, November 1996.
Olivier Faugeras, Renaud Keriven, and Imahd Eddine Srairi. A first implementation of a complete dense surface reconstruction from 2D images. Technical report, ENPC-CERMICS, October 1997.
L.M.J. Florack. The syntactical structure of scalar images. PhD thesis, Utrecht University, 1993.
Pascal Fua. From multiple stereo views to multiple 3-d surfaces. The International Journal of Computer Vision, 24(1):19–35, August 1997.
Pascal Fua and Yves G. Leclerc. Object-centered surface reconstruction: Combining multi-image stereo and shading. The International Journal of Computer Vision, 16(1):35–56, September 1995.
M. Gage and R.S. Hamilton. The heat equation shrinking convex plane curves. J. of Differential Geometry, 23:69–96, 1986.
M. Grayson. The heat equation shrinks embedded plane curves to round points. J. of Differential Geometry, 26:285–314, 1987.
W.E.L. Grimson. From Images to Surfaces. MIT Press: Cambridge, 1981.
H. L. F. von Helmholtz. Treatise on Physiological Optics. New York: Dover, 1925. Translated by J.P. Southall.
Berthold Klaus Paul Horn. Robot Vision. MIT Press, 1986.
Bela Julesz. Foundations of Cyclopean perception. The University of Chicago Press, Chicago and London, 1971.
M. Kass, A. Witkin, and D. Terzopoulos. SNAKES: Active contour models. The International Journal of Computer Vision, 1:321–332, January 1988.
Renaud Keriven. Equations aux Dérivées Partielles, Evolutions de Courbes et de Surfaces et Espaces d'Echelle: Applications à la Vision par Ordinateur. PhD thesis, Ecole Nationale des Ponts et Chaussées, Dec. 1997.
S. Kichenassamy, A. Kumar, P. Olver, A. Tannenbaum, and A. Yezzi. Gradient flows and geometric active contour models. In Proc. Fifth International Conference on Computer Vision, Boston, MA, June 1995. IEEE Computer Society Press.
P.J. Narayanan, P.W. Rander, and Takeo Kanade. Constructing virtual worlds using dense stereo. In Proceedings of the 6th International Conference on Computer Vision, Bombay, India, January 1998. IEEE Computer Society Press.
S. Osher and J. Sethian. Fronts propagating with curvature dependent speed: algorithms based on the Hamilton-Jacobi formulation. Journal of Computational Physics, 79:12–49, 1988.
L. Robert and R. Deriche. Dense depth map reconstruction: A minimization and regularization approach which preserves discontinuities. In Bernard Buxton, editor, Proceedings of the 4th European Conference on Computer Vision, Cambridge, UK, April 1996.
L. Robert, R. Deriche, and O.D. Faugeras. Dense depth recovery from stereo images. In Proceedings of the European Conference on Artificial Intelligence, pages 821–823, Vienna, Austria, August 1992.
Guillermo Sapiro and Allen Tannenbaum. Affine Invariant Scale Space. The International Journal of Computer Vision, 11(1):25–44, August 1993.
J. A. Sethian. Level Set Methods. Cambridge University Press, 1996.
J.A. Sethian. Numerical algorithms for propagating interfaces: Hamilton-jacobi equations and conservation laws. Journal of Differential Geometry, 31:131–161, 1990.
J.A. Sethian. Theory, algorithms, and applications of level set methods for propagating interfaces. Technical Report PAM-651, Center for Pure and Applied Mathematics, University of California, Berkeley, August 1995. To appear Acta Numerica.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Faugeras, O., Keriven, R. (1998). Complete dense stereovision using level set methods. In: Burkhardt, H., Neumann, B. (eds) Computer Vision — ECCV'98. ECCV 1998. Lecture Notes in Computer Science, vol 1406. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0055679
Download citation
DOI: https://doi.org/10.1007/BFb0055679
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64569-6
Online ISBN: 978-3-540-69354-3
eBook Packages: Springer Book Archive