Abstract
This paper deals with video segmentation based on motion and spatial information. Classically, the nucleus of the motion term is the motion compensation error (MCE) between two consecutive frames. Defining a motion-based energy as the integral of a function of the MCE over the object domain implicitly results in making an assumption on the MCE distribution: Gaussian for the square function, Laplacian for the absolute value, or other parametric distributions for functions used in robust estimation. However, these assumptions are generally false. Instead, it is proposed to integrate a function of (an estimation of) the MCE distribution. The function is taken such that the integral is the Ahmad-Lin entropy of the MCE, the purpose being to be more robust to outliers. Since a motion-only approach can fail in homogeneous areas, the proposed energy is the joint entropy of the MCE and the object color. It is minimized using active contours.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Weickert, J., Schnörr, C.: Variational optic flow computation with a spatio-temporal smoothness constraint. Journal of Mathematical Imaging and Vision 14, 245–255 (2001)
Weickert, J., Álvarez, L., Sánchez, J.: A Scale-Space Approach to Nonlocal Optical Flow Calculations. In: Nielsen, M., et al. (eds.) Scale-Space 1999. LNCS, vol. 1682, Springer, Heidelberg (1999)
Wu, S.F., Kittler, J.: A gradient-based method for general motion estimation and segmentation. Journal of Visual Com. Image Repr. 4, 25–38 (1993)
Black, M.J., Anandan, P.: The robust estimation of multiple motions: parametric and piecewise-smooth flow fields. Comput. Vis. Image Underst. 63, 75–104 (1996)
Comaniciu, D., Meer, P.: Mean shift analysis and applications. In: International Conference on Computer Vision, vol. 2, pp. 1197–1203 (1999)
Kim, J., et al.: A nonparametric statistical method for image segmentation using information theory and curve evolution. IEEE Trans. on Image Processing 14(10), 1486–1502 (2005)
Mittal, A., Paragios, N.: Motion-based background subtraction using adaptive kernel density estimation. Computer Vision and Pattern Recognition 2, 302–309 (2004)
Mitiche, A., El-Feghali, R., Mansouri, A.R.: Motion tracking as spatio-temporal motion boundary detection. Robotics and Autonomous Sys. 43, 39–50 (2003)
Brox, T., et al.: Unsupervised segmentation incorporating colour, texture, and motion. In: Petkov, N., Westenberg, M.A. (eds.) CAIP 2003. LNCS, vol. 2756, pp. 353–360. Springer, Heidelberg (2003)
Cremers, D., Soatto, S.: Motion competition: A variational framework for piecewise parametric motion segmentation. International Journal of Computer Vision 62(3), 249–265 (2005)
Goria, M., et al.: A new class of random vector entropy estimators and its applications in testing statistical hypotheses. Journal of Nonparametric Statistics 17(3), 277–297 (2005)
Silverman, B.: Density Estimation for Statistics and Data Analysis. Chapman and Hall, London (1986)
Ahmad, I., Lin, P.: A nonparametric estimation of the entropy for absolutely continuous distributions. IEEE Trans. on Information Theory 36, 688–692 (1989)
Delfour, M.C., Zolésio, J.P.: Shapes and geometries: Analysis, differential calculus and optimization. In: Advances in Design and Control, Society for Industrial and Applied Mathematics, Philadelphia (2001)
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. International Journal of Computer Vision 22(1), 61–79 (1997)
Hintermuller, M., Ring, W.: A second order shape optimization approach for image segmentation. SIAM Journal on Applied Mathematics 64(2), 442–467 (2004)
Cremers, D., Rousson, M., Deriche, R.: A review of statistical approaches to level set segmentation: integrating color, texture, motion and shape. International Journal of Computer Vision 72(2) (2007)
Schoenemann, T., Cremers, D.: Near real-time motion segmentation using graph cuts. In: Franke, K., et al. (eds.) DAGM 2006. LNCS, vol. 4174, pp. 455–464. Springer, Heidelberg (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Herbulot, A., Boltz, S., Debreuve, E., Barlaud, M., Aubert, G. (2007). Space-Time Segmentation Based on a Joint Entropy with Estimation of Nonparametric Distributions. In: Sgallari, F., Murli, A., Paragios, N. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2007. Lecture Notes in Computer Science, vol 4485. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72823-8_62
Download citation
DOI: https://doi.org/10.1007/978-3-540-72823-8_62
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72822-1
Online ISBN: 978-3-540-72823-8
eBook Packages: Computer ScienceComputer Science (R0)