The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.05 - May (2008 vol.30)
pp: 851-864
ABSTRACT
Recently proposed Sobolev active contours introduced a new paradigm for minimizing energies defined on curves by changing the traditional cost of perturbing a curve and thereby redefining their gradients. Sobolev active contours evolve more globally and are less attracted to certain intermediate local minima than traditional active contours, and it is based on a well-structured Riemannian metric. In this paper, we analyze Sobolev active contours using scale-space analysis in order to understand their evolution across different scales. This analysis shows an extremely important and useful behavior of Sobolev contours, namely, that they move successively from coarse to increasingly finer scale motions in a continuous manner. This property illustrates that one justification for using the Sobolev technique is for applications where coarse-scale deformations are preferred over fine scale deformations. Along with other properties to be discussed, the coarse-to-fine observation reveals that Sobolev active contours are, in particular, ideally suited for tracking algorithms that use active contours. We will also justify our assertion that the Sobolev metric should be used over the traditional metric for active contours in tracking problems by experimentally showing how a variety of active contour based tracking methods can be significantly improved merely by evolving the active contour according to the Sobolev method.
INDEX TERMS
Active contours, segmentation, coarse-to-fine segmentation, tracking, gradient flows, global flows
CITATION
Ganesh Sundaramoorthi, Anthony Yezzi, Andrea Mennucci, "Coarse-to-Fine Segmentation and Tracking Using Sobolev Active Contours", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.30, no. 5, pp. 851-864, May 2008, doi:10.1109/TPAMI.2007.70751
REFERENCES
[1] G. Sundaramoorthi, J.D. Jackson, A.J. Yezzi, and A. Mennucci, “Tracking with Sobolev Active Contours,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 674-680, 2006.
[2] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Int'l J. Computer Vision, vol. 1, pp. 321-331, 1987.
[3] A. Blake and M. Isard, Active Contours. Springer, 1998.
[4] V. Caselles, R. Kimmel, and G. Sapiro, “Geodesic Active Contours,” Proc. Fifth Int'l Conf. Computer Vision, pp. 694-699, June 1995.
[5] S. Kichenassamy, A. Kumar, P. Olver, A. Tannenbaum, and A. Yezzi, “Gradient Flows and Geometric Active Contour Models,” Proc. Fifth Int'l Conf. Computer Vision, pp. 810-815, 1995.
[6] R. Goldenberg, R. Kimmel, E. Rivlin, and M. Rudzsky, “Fast Geodesic Active Contours,” IEEE Trans. Image Processing, vol. 10, no. 10, pp. 1467-1475, 2001.
[7] D. Mumford and J. Shah, “Optimal Approximations by Piecewise Smooth Functions and Associated Variational Problems,” Comm. Pure and Applied Math., vol. 42, pp. 577-685, 1989.
[8] S.C. Zhu, T.S. Lee, and A.L. Yuille, “Region Competition: Unifying Snakes, Region Growing, Energy/Bayes/MDL for Multi-Band Image Segmentation,” Proc. Fifth Int'l Conf. Computer Vision, pp.416-423, 1995.
[9] A. Yezzi, A. Tsai, and A. Willsky, “A Statistical Approach to Snakes for Bimodal and Trimodal Imagery,” Proc. Int'l Conf. Computer Vision, pp. 898-903, Oct. 1999.
[10] N. Paragios and R. Deriche, “Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 3, pp.266-280, Mar. 2000.
[11] T. Chan and L. Vese, “Active Contours without Edges,” IEEE Trans. Image Processing, vol. 10, no. 2, pp. 266-277, Feb. 2001.
[12] N. Paragios and R. Deriche, “Geodesic Active Regions: A New Paradigm to Deal with Frame Partition Problems in Computer Vision,” Int'l J. Visual Comm. and Image Representation, special issue on partial differential equations in image processing, computer vision, and computer graphics, vol. 13, no. 2, pp. 249-268, June 2002.
[13] D. Terzopoulos and R. Szeliski, “Tracking with Kalman Snakes,” Active Vision, MIT Press, 1992.
[14] J. Jackson, A. Yezzi, and S. Soatto, “Tracking Deformable Moving Objects under Severe Occlusions,” Proc. 43rd IEEE Conf. Decision and Control, Dec. 2004.
[15] A. Blake and R. Brockett, “On Snakes and Estimation Theory,” Proc. 33rd IEEE Conf. Decision and Control, 1994.
[16] M. Isard and A. Blake, “Condensation—Conditional Density Propagation for Visual Tracking,” Int'l J. Computer Vision, vol. 1, no. 29, pp. 5-28, 1998.
[17] N. Peterfreund, “Robust Tracking of Position and Velocity with Kalman Snakes,” IEEE Trans. Pattern Analysis Machine Intelligence, vol. 21, no. 6, pp. 564-569, June 1999.
[18] M. Niethammer and A. Tannenbaum, “Dynamic Geodesic Snakes for Visual Tracking,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 660-667, 2004.
[19] Y. Rathi, N. Vaswani, A. Tannenbaum, and A. Yezzi, “Particle Filtering for Geometric Active Contours and Application to Tracking Deforming Objects,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2005.
[20] G. Sundaramoorthi, A. Yezzi, and A. Mennucci, “Sobolev Active Contours,” Proc. Third Int'l Workshop Variational, Geometric, and Level Set Methods in Computer Vision, pp. 109-120, 2005.
[21] G. Sundaramoorthi, A. Yezzi, and A. Mennucci, “Sobolev Active Contours,” Int'l J. Computer Vision, vol. 73, no. 3, pp. 345-366, July 2007.
[22] G. Charpiat, R. Keriven, J.-P. Pons, and O.D. Faugeras, “Designing Spatially Coherent Minimizing Flows for Variational Problems Based on Active Contours,” Proc. 10th Int'l Conf. Computer Vision, pp. 1403-1408, 2005.
[23] G. Charpiat, R. Keriven, J.-P. Pons, and O.D. Faugeras, “Generalized Gradients: Priors on Minimization Flows,” Int'l J. Computer Vision, vol. 73, no. 3, pp. 325-344, July 2007.
[24] P. Michor and D. Mumford, Riemannian Geometries on the Space of Plane Curves, ESI Preprint 1425, arXiv:math.DG/0312384, Dec. 2003.
[25] A. Yezzi and A. Mennucci, Metrics in the Space of Curves, Preprint, arXiv:math.DG/0412454, May 2005.
[26] J.W. Neuberger, “Sobolev Gradients and Differential Equations,” Lecture Notes in Math., vol. 1670, 1997.
[27] M. Burger, “A Framework for the Construction of Level Set Methods for Shape Optimization and Reconstruction,” Interfaces and Free Boundaries, vol. 5, pp. 301-329, 2003.
[28] L. Younes, “Computable Elastic Distances between Shapes,” SIAM J. Applied Math., vol. 58, no. 2, pp. 565-586, 1998.
[29] A.C.G. Mennucci, A. Yezzi, and G. Sundaramoorthi, Properties of Sobolev-Type Metrics in the Space of Curves, Preprint, arXiv: math.DG/0605017, Apr. 2006.
[30] P.W. Michor and D. Mumford, An Overview of the Riemannian Metrics on Spaces of Curves Using the Hamiltonian Approach, Applied and Computational Harmonic Analysis (ACHA), arXiv:math.DG/0605009, 2006.
[31] W. Mio and A. Srivastava, “Elastic-String Models for Representation and Analysis of Planar Shapes,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 10-15, 2004.
[32] B. Leroy, I. Herlin, and L. Cohen, “Multi-Resolution Algorithms for Active Contour Models,” Proc. 12th Int'l Conf. Analysis and Optimization of Systems: Images, Wavelets and PDE's, 1996.
[33] D. Cremers, F. Tischhäuser, J. Weickert, and C. Schnörr, “Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah Functional,” Int'l J. Computer Vision, vol. 50, no. 3, pp. 295-313, 2002.
[34] G.B. Unal, A.J. Yezzi, and H. Krim, “Information-Theoretic Active Polygons for Unsupervised Texture Segmentation,” Int'l J. Computer Vision, vol. 62, no. 3, pp. 199-220, 2004.
[35] G.B. Unal, H. Krim, and A.J. Yezzi, “Fast Incorporation of Optical Flow into Active Polygons,” IEEE Trans. Image Processing, vol. 14, no. 6, pp. 745-759, 2005.
[36] T. McInerney and D. Terzopoulos, “Topologically Adaptable Snakes,” Proc. Fifth Int'l Conf. Computer Vision, pp. 840-845, 1995.
[37] A. Yezzi, L. Zollei, and T. Kapur, “A Variational Framework for Joint Segmentation and Registration,” Proc. IEEE Workshop Math. Methods Biomedical Image Analysis, 2001.
[38] S. Soatto and A.J. Yezzi, “DEFORMOTION: Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images,” Proc. Seventh European Conf. Computer Vision, vol. 3, pp.32-57, 2002.
[39] A.-R. Mansouri, D.P. Mukherjee, and S.T. Acton, “Constraining Active Contour Evolution via Lie Groups of Transformation,” IEEE Trans. Image Processing, vol. 13, no. 6, pp. 853-863, 2004.
[40] A. Tsai, A.J. Yezzi, C. Tempany, D. Tucker, A. Fan, W.E.L. Grimson, and A.S. Willsky, “Model-Based Curve Evolution Technique for Image Segmentation,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 463-468, 2001.
[41] G. Charpiat, O.D. Faugeras, and R. Keriven, “Approximations of Shape Metrics and Application to Shape Warping and Empirical Shape Statistics,” Foundations of Computational Math., vol. 5, no. 1, pp. 1-58, 2005.
[42] M. Leventon, E. Grimson, and O. Faugeras, “Statistical Shape Influence in Geodesic Active Contours,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 316-323, 2000.
[43] M. Rousson and N. Paragios, “Shape Priors for Level Set Representations,” Proc. Seventh European Conf. Computer Vision, vol. 2, pp. 78-93, 2002.
[44] Y. Chen, H. Tagare, S. Thiruvenkadam, F. Huang, D. Wilson, K. Gopinath, R. Briggs, and E. Geiser, “Using Prior Shapes in Geometric Active Contours in a Variational Framework,” Int'l J. Computer Vision, vol. 50, no. 3, pp. 315-328, Dec. 2002.
[45] D. Cremers, S.J. Osher, and S. Soatto, “Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation,” Int'l J. Computer Vision, vol. 69, no. 3, pp. 335-351, Sept. 2006.
[46] M. Grayson, “The Heat Equation Shrinks Embedded Planes Curves to Round Points,” J. Differential Geometry, no. 26, pp. 285-314, 1987.
[47] M. Gage and R.S. Hamilton, “The Heat Equation Shrinking Convex Plane Curves,” J. Differential Geometry, vol. 23, pp. 69-96, 1986.
[48] A. Tsai, A.J.Y. Jr., and A.S. Willsky, “Curve Evolution Implementation of the Mumford-Shah Functional for Image Segmentation, Denoising, Interpolation, and Magnification,” IEEE Trans. Image Processing, vol. 10, no. 8, pp. 1169-1186, 2001.
[49] L.A. Vese and T.F. Chan, “A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model,” Int'l J. Computer Vision, vol. 50, no. 3, pp. 271-293, 2002.
22 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool