Subscribe
Issue No.09 - September (2009 vol.31)
pp: 1708-1714
Amit Adam , Technion - Israel Institute of Technology, Haifa
Ron Kimmel , Technion - Israel Institute of Technology, Haifa
Ehud Rivlin , Technion - Israel Institute of Technology, Haifa
ABSTRACT
We consider curve evolution based on comparing distributions of features, and its applications for scene segmentation. In the first part, we promote using cross-bin metrics such as the Earth Mover's Distance (EMD), instead of standard bin-wise metrics as the Bhattacharyya or Kullback-Leibler metrics. To derive flow equations for minimizing functionals involving the EMD, we employ a tractable expression for calculating EMD between one-dimensional distributions. We then apply the derived flows to various examples of single image segmentation, and to scene analysis using video data. In the latter, we consider the problem of segmenting a scene to spatial regions in which different activities occur. We use a nonparametric local representation of the regions by considering multiple one-dimensional histograms of normalized spatiotemporal derivatives. We then obtain semisupervised segmentation of regions using the flows derived in the first part of the paper. Our results are demonstrated on challenging surveillance scenes, and compare favorably with state-of-the-art results using parametric representations by dynamic systems or mixtures of them.
INDEX TERMS
Segmentation, Earth Mover's Distance, curve evolution, scene analysis.
CITATION
Amit Adam, Ron Kimmel, Ehud Rivlin, "On Scene Segmentation and Histograms-Based Curve Evolution", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 9, pp. 1708-1714, September 2009, doi:10.1109/TPAMI.2009.21
REFERENCES
 [1] G. Aubert, M. Barlaud, O. Faugeras, and S. Jehan-Besson, “Image Segmentation Using Active Contours: Calculus of Variations or Shape Gradients?” SIAM J. Applied Math., vol. 63, no. 6, pp. 2128-2154, 2003. [2] E. Brem, BioSense Webster, Inc., personal communication, http://www.biosensewebster.com/products/ navigationcartosound.aspx, 2007. [3] V. Caselles, F. Catte, T. Coll, and F. Dibos, “A Geometric Model for Active Contours,” Numerische Math., vol. 66, pp. 1-31, 1993. [4] V. Caselles, R. Kimmel, and G. Sapiro, “Geodesic Active Contours,” Int'l J. Computer Vision, vol. 22, no. 1, pp. 61-79, 1997. [5] A. Chan and N. Vasconcelos, “Modeling, Clustering and Segmenting Video with Mixtures of Dynamic Textures,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 5, pp. 909-926, May 2008. [6] T. Chan, S. Esedoglu, and K. Ni, “Histogram Based Segmentation Using Wasserstein Distances,” Proc. Conf. Scale Space Methods and Variational Methods in Computer Vision, 2007. [7] T. Chan and L. Vese, “Active Contours without Edges,” IEEE Trans. Image Processing, vol. 10, no. 2, pp. 266-277, Feb. 2001. [8] L. Cohen, “On Active Contour Models and Balloons,” CVGIP: Image Understanding, vol. 53, no. 2, pp. 211-218, 1991. [9] L. Cooper, J. Liu, and K. Huang, “Spatial Segmentation of Temporal Texture Using Mixture Linear Models,” Workshop Dynamical Vision (in conjunction with Proc. IEEE Int'l Conf. Computer Vision, 2005. [10] D. Cremers, M. Rousson, and R. Deriche, “A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape,” Int'l J. Computer Vision, vol. 72, no. 2, pp. 195-215, 2007. [11] D. Cremers and S. Soatto, “Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation,” Int'l J. Computer Vision, vol. 62, no. 3, pp. 249-265, 2005. [12] D. DeMenthon, “Spatio-Temporal Segmentation of Video by Hierarchical Mean Shift Analysis,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2006. [13] G. Doretto, A. Chiuso, Y. Wu, and S. Soatto, “Dynamic Textures,” Int'l J. Computer Vision, vol. 51, no. 2, pp. 91-109, 2003. [14] G. Doretto, D. Cremers, P. Favaro, and S. Soatto, “Dynamic Texture Segmentation,” Proc. IEEE Int'l Conf. Computer Vision, pp. 1236-1242, 2003. [15] C. Fowlkes, S. Belongie, and J. Malik, “Efficient Spatiotemporal Grouping Using the Nystrom Method,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2001. [16] D. Freedman and T. Zhang, “Active Contours for Tracking Distributions,” IEEE Trans. Image Processing, vol. 13, no. 4, pp. 518-526, Apr. 2004. [17] H. Greenspan, J. Goldberger, and A. Mayer, “Probabilistic Space-Time Video Modeling via Piecewise GMM,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 3, pp. 384-396, Mar. 2004. [18] S. Jehan-Besson, M. Barlaud, and G. Aubert, “Video Object Segmentation Using Eulerian Region-Based Active Contours,” Proc. IEEE Int'l Conf. Computer Vision, 2001. [19] S. Jehan-Besson, M. Barlaud, and G. Aubert, “Dream$^2$ s: Deformable Regions Driven by an Eulerian Accurate Minimization Method for Image and Video Segmentation,” Int'l J. Computer Vision, vol. 53, no. 1, pp.45-70, 2003. [20] S. Kahn and M. Shah, “Object Based Segmentation of Video Using Color, Motion and Spatial Information,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2001. [21] Z. Lu, W. Xie, J. Pei, and J. Huang, “Dynamic Texture Recognition by Spatio-Temporal Multiresolution Histograms,” Proc. IEEE Workshop Applications of Computer Vision, pp. 241-246, 2005. [22] R. Malladi, J. Sethian, and B. Vemuri, “Shape Modeling with Front Propagation: A Level Set Approach,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 2, pp. 158-175, Feb. 1995. [23] R. Megret and D. DeMenthon, “A Survey of Spatio-Temporal Grouping Techniques,” Technical Report LAMP 094, LAMP—Univ. of Maryland, Aug. 2002. [24] O. Michaelovich, Y. Rathi, and A. Tannenbaum, “Image Segmentation Using Active Contours Driven by the Bhattacharyya Gradient Flow,” IEEE Trans. Image Processing, vol. 16, no. 11, pp. 2787-2801, Nov. 2007. [25] S. Osher and R. Fedkiw, Level Set Methods and Dynamic Implicit Surfaces. Springer-Verlag, 2002. [26] F. Porikli, “Integral Histogram: A Fast Way to Extract Histograms in Cartesian Spaces,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005. [27] R. Ronfard, “Region-Based Strategies for Active Contour Models,” Int'l J. Computer Vision, vol. 13, no. 2, pp. 229-251, 1994. [28] M. Rousson and D. Cremers, “Efficient Kernel Density Estimation of Shape and Intensity Priors for Level Set Segmentation,” Proc. Conf. Medical Image Computing and Computer Assisted Intervention, pp. 757-764, 2005. [29] Y. Rubner, C. Tomasi, and L. Guibas, “The Earth Mover's Distance as a Metric for Image Retrieval,” Int'l J. Computer Vision, vol. 40, no. 2, pp.91-121, 2000. [30] J. Sethian, Level Sets Methods and Fats Marching Methods: Evolving Interfaces in Computational Geometry, Fluid Mechanics, Computer Vision and Materials Science, second ed. Cambridge Univ. Press, 1999. [31] L. Zelnik-Manor and M. Irani, “Statistical Analysis of Dynamic Actions,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 9, pp. 1530-1535, Sept. 2006. [32] Y. Zhai and M. Shah, “A General Framework for Temporal Video Scene Segmentation,” Proc. IEEE Int'l Conf. Computer Vision, 2005. [33] S.-C. Zhu and A. Yuille, “Region Competition: Unifying Snakes, Region Growing and Bayes/MDL for Multiband Image Segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 9, pp. 884-900, Sept. 1996.