Higher Order Active Contours
- 368 Downloads
We introduce a new class of active contour models that hold great promise for region and shape modelling, and we apply a special case of these models to the extraction of road networks from satellite and aerial imagery. The new models are arbitrary polynomial functionals on the space of boundaries, and thus greatly generalize the linear functionals used in classical contour energies. While classical energies are expressed as single integrals over the contour, the new energies incorporate multiple integrals, and thus describe long-range interactions between different sets of contour points. As prior terms, they describe families of contours that share complex geometric properties, without making reference to any particular shape, and they require no pose estimation. As likelihood terms, they can describe multi-point interactions between the contour and the data. To optimize the energies, we use a level set approach. The forces derived from the new energies are non-local however, thus necessitating an extension of standard level set methods. Networks are a shape family of great importance in a number of applications, including remote sensing imagery. To model them, we make a particular choice of prior quadratic energy that describes reticulated structures, and augment it with a likelihood term that couples the data at pairs of contour points to their joint geometry. Promising experimental results are shown on real images.
Keywordsactive contour shape prior geometric higher-order polynomial quadratic road network remote sensing
Unable to display preview. Download preview PDF.
- Bossavit, A. 2002.Applied differential geometry: A compendium, http://www.icm.edu.pl/edukacja/mat/Compendium.php.
- Chen, Y., Thiruvenkadam, S., Tagare, H. D., Huang, F., Wilson, D., and Geiser, E. 2001.On the incorporation of shape priors into geometric active contours. Proc. IEEE Workshop VLSM, pp. 145–152Google Scholar
- Cremers, D., Schnorr, C., and Weickert, J. 2001.Diffusion-snakes: combining statistical shape knowledge and image information in a variational framework. Proc. IEEE Workshop VLSM, pp. 137–144Google Scholar
- Foulonneau, A., Charbonnier, P., and Heitz, F. 2003.Geometric shape priors for region-based active contours. Proc. IEEE ICIP., 3:413– 416Google Scholar
- Jermyn, I. H. and Ishikawa, H. 2001.Globally optimal regions and boundaries as minimum ratio cycles. IEEE Trans. Patt. Anal. Mach. Intell. (Special Section on Graph Algorithms and Computer Vision), 23(10):1075–1088Google Scholar
- Kass, M., Witkin, A., and Terzopoulos, D. 1988.Snakes: Active contour models. Int’l J. Comp. Vis., pp. 321–331Google Scholar
- Kichenassamy, S., Kumar, A., Olver, P., Tannenbaum, A., and Yezzi, A. 1995.Gradient flows and geometric active contour models. Proc. ICCV, pp. 810–815.Google Scholar
- Lacoste, C., Descombes, X., and Zerubia, J. 2002.A comparative study of point processes for line network extraction in remote sensing.Research Report 4516, INRIA, France.Google Scholar
- Leventon, M. E., Grimson, W. E. L., and Faugeras, O. 2000.Statistical shape influence in geodesic active contours. Proc. IEEE CVPR, 1:316–322Google Scholar
- Paragios, N. and Rousson, M. 2002.Shape priors for level set representations. Proc. ECCV, pp. 78–92Google Scholar
- Pavlidis, T. 1982. Algorithms for Graphics and Image Processing, chapter 7.Computer Science Press, Inc.Google Scholar
- Rochery, M., Jermyn, I. H. and Zerubia, J. 2003.Higher order active contours and their application to the detection of line networks in satellite imagery.In Proc. IEEE Workshop VLSM, at ICCV, Nice, France.Google Scholar
- Sethian, J. A. 1999. Level Set Methods and Fast Marching Methods: Evolving Interfaces in Geometry Fluid Mechanics, Computer Vision and Materials Science.Cambridge University Press.Google Scholar