Complete Dense Stereovision Using Level Set Methods

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.

[1]  Rachid Deriche,et al.  Dense Depth Recovery From Stereo Images , 1992, European Conference on Artificial Intelligence.

[2]  M. Gage,et al.  The heat equation shrinking convex plane curves , 1986 .

[3]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[4]  James A. Sethian,et al.  Theory, algorithms, and applications of level set methods for propagating interfaces , 1996, Acta Numerica.

[5]  Olivier D. Faugeras,et al.  Variational principles, surface evolution, PDEs, level set methods, and the stereo problem , 1998, IEEE Trans. Image Process..

[6]  P. Fua.  From Multiple Stereo Views to Multiple 3-D Surfaces , 2022 .

[7]  J. Sethian.  Numerical algorithms for propagating interfaces: Hamilton-Jacobi equations and conservation laws , 1990 .

[8]  D. Chopp.  Computing Minimal Surfaces via Level Set Curvature Flow , 1993 .

[9]  Olivier D. Faugeras,et al.  Level Set Methods and the Stereo Problem , 1997, Scale-Space.

[10]  Hermann von Helmholtz,et al.  Treatise on Physiological Optics , 1962 .

[11]  Renaud Keriven.  Equations aux dérivées partielles, Evolutions de courbes et de surfaces et espaces d'echelle: Applications à la vision par ordinateur , 1997 .

[12]  Anthony J. Yezzi,et al.  Gradient flows and geometric active contour models , 1995, Proceedings of IEEE International Conference on Computer Vision.

[13]  Rachid Deriche,et al.  Level-set approach for stereo , 1997, Defense + Security.

[14]  Rachid Deriche,et al.  Dense Depth Map Reconstruction: A Minimization and Regularization Approach which Preserves Discontinuities , 1996, ECCV.

[15]  J. P. Southall.  Helmholtz's Treatise on Physiological Optics, Translated from the Third German Edition. Vol. I , 1925 .

[16]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[17]  R. Deriche.  Recursively Implementing the Gaussian and its Derivatives , 1993 .

[18]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[19]  S. Osher,et al.  Algorithms Based on Hamilton-Jacobi Formulations , 1988 .

[20]  W. Eric L. Grimson,et al.  From images to surfaces , 1981 .

[21]  Manfredo P. do Carmo,et al.  Differential geometry of curves and surfaces , 1976 .

[22]  M. Grayson.  The heat equation shrinks embedded plane curves to round points , 1987 .

[23]  Guillermo Sapiro,et al.  3D active contours , 1996 .

[24]  Takeo Kanade,et al.  Constructing virtual worlds using dense stereo , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[25]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[26]  B. Julesz.  Foundations of Cyclopean Perception , 1971 .