Abstract
Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. These tasks can be formulated as energy minimization problems. In this paper, we consider a natural class of energy functions that permits discontinuities. Computingthe exact minimum is NP-hard. We have developed a new approximation algorithm based on graph cuts. The solution it generates is guaranteed to be within a factor of 2 of the energy function’s global minimum. Our method produces a local minimum with respect to a certain move space. In this move space, a single move is allowed to switch an arbitrary subset of pixels to one common label. If this common label is á then such a move expands the domain of á in the image. At each iteration our algorithm efficiently chooses the expansion move that gives the largest decrease in the energy. We apply our method to the stereo matching problem, and obtain promisingex perimental results. Empirically, the new technique outperforms our previous algorithm [6] both in terms of runningti me and output quality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Ravindra K. Ahuja, Thomas L. Magnanti, and James B. Orlin. Network Flows: Theory, Algorithms, and Applications. Prentice Hall, 1993.
Stephen Barnard. Stochastic stereo matchingo ver scale. International Journal of Computer Vision, 3(1):17–32, 1989.
Stan Birchfield and Carlo Tomasi. A pixel dissimilarity measure that is insensitive to image sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(4):401–406, April 1998.
A. Blake and A. Zisserman. Visual Reconstruction. MIT Press, 1987.
Andrew Blake. Comparison of the efficiency of deterministic and stochastic algorithms for visual reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(1):2–12, January 1989.
Yuri Boykov, Olga Veksler, and Ramin Zabih. Energy minimization with discontinuities. In review. Available from http://www.cs.cornell.edu/home/rdz. An earlier version of this paper appeared in CVPR’ 98.
P. B. Chou and C. M. Brown. The theory and practice of Bayesian image labeling. International Journal of Computer Vision, 4(3):185–210, 1990.
L. Ford and D. Fulkerson. Flows in Networks. Princeton University Press, 1962.
S. Geman and D. Geman. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6:721–741, 1984.
D. Greig, B. Porteous, and A. Seheult. Exact maximum a posteriori estimation for binary images. Journal of the Royal Statistical Society, Series B, 51(2):271–279, 1989.
W. Eric L. Grimson and Theo Pavlidis. Discontinuity detection for visual surface reconstruction. Computer Vision, Graphics and Image Processing, 30:316–330, 1985.
B. K. P. Horn and B. Schunk. Determiningo ptical flow. Artificial Intelligence, 17:185–203, 1981.
H. Ishikawa and D. Geiger. Segmentation by grouping junctions. In IEEE Conference on Computer Vision and Pattern Recognition, pages 125–131, 1998.
David Lee and Theo Pavlidis. One dimensional regularization with discontinuities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 10(6):822–829, November 1988.
Tomaso Poggio, Vincent Torre, and Christof Koch. Computational vision and regularization theory. Nature, 317:314–319, 1985.
A. Rosenfeld, R. A. Hummel, and S.W. Zucker. Scene labelingb y relaxation operations. IEEE Transactions on Systems, Man, and Cybernetics, 6(6):420–433, June 1976.
R. S. Szeliski. Bayesian modelingof uncertainty in low-level vision. International Journal of Computer Vision, 5(3):271–302, December 1990.
Demetri Terzopoulos. Image analysis using multigrid relaxation methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(2):129–139, 1986.
Demetri Terzopoulos. Regularization of inverse visual problems involving discontinuities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(4):413–424, 1986. 206
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Boykov, Y., Veksler, O., Zabih, R. (1999). A New Algorithm for Energy Minimization with Discontinuities. In: Hancock, E.R., Pelillo, M. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 1999. Lecture Notes in Computer Science, vol 1654. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48432-9_15
Download citation
DOI: https://doi.org/10.1007/3-540-48432-9_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66294-5
Online ISBN: 978-3-540-48432-5
eBook Packages: Springer Book Archive