Abstract
We present a variational approach for segmenting the image plane into regions of piecewise parametric motion given two or more frames from an image sequence. Our model is based on a conditional probability for the spatio-temporal image gradient, given a particular velocity model, and on a geometric prior on the estimated motion field favoring motion boundaries of minimal length.
We cast the problem of motion segmentation as one of Bayesian inference, we derive a cost functional which depends on parametric motion models for each of a set of domains and on the boundary separating them. The resulting functional can be interpreted as an extension of the Mumford-Shah functional from intensity segmentation to motion segmentation. In contrast to most alternative approaches, the problems of segmentation and motion estimation are jointly solved by continuous minimization of a single functional. Minimization results in an eigenvalue problem for the motion parameters and in a gradient descent evolution for the motion boundary. The evolution of the motion boundaries is implemented by a multiphase level set formulation which allows for the segmentation of an arbitrary number of multiply connected moving objects.
We further extend this approach to the segmentation of space-time volumes of coherent motion from video sequences. To this end, motion boundaries are represented by a set of surfaces in space-time. An implementation by a higher-dimensional multiphase level set model allows the evolving surfaces to undergo topological changes. In contrast to an iterative segmentation of consecutive frame pairs, a constraint on the area of these surfaces leads to an additional temporal regularization of the computed motion boundaries.
Numerical results demonstrate the capacity of our approach to segment objects based exclusively on their relative motion.
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
Bigün, J., Granlund, G.H., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE PAMI 13(8), 775–790 (1991)
Black, M.J., Anandan, P.: The robust estimation of multiple motions: Parametric and piecewise–smooth flow fields. Comp. Vis. Graph. Image Proc.: IU 63(1), 75–104 (1996)
Bouthemy, P., Francois, E.: Motion segmentation and qualitative dynamic scene analysis from an image sequence. Int. J. of Comp. Vis. 10(2), 157–182 (1993)
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)
Caselles, V., Coll, B.: Snakes in movement. SIAM J. Numer. Anal. 33, 2445–2456 (1996)
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. In: Proc. IEEE Intl. Conf. on Comp. Vis., Boston, USA, pp. 694–699. IEEE, Los Alamitos (1995)
Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Processing 10(2), 266–277 (2001)
Cremers, D.: A multiphase level set framework for variational motion segmentation. In: Griffin, L.D, Lillholm, M. (eds.) Scale Space Methods in Computer Vision. LNCS, vol. 2695, pp. 599–614. Springer, Heidelberg (2003)
Cremers, D.: A variational framework for image segmentation combining motion estimation and shape regularization. In: Dyer, C., Perona, P. (eds.) IEEE Conf. on Comp. Vis. and Patt. Recog, vol. 1, pp. 53–58. IEEE Computer Society Press, Los Alamitos (June 2003)
Cremers, D., Schnörr, C.: Motion Competition: Variational integration of motion segmentation and shape regularization. In: Van Gool, L. (ed.) DAGM 2002. LNCS, vol. 2449, pp. 472–480. Springer, Heidelberg (2002)
Cremers, D., Soatto, S.: Variational space-time motion segmentation. In: Triggs, B., Zisserman, A. (eds.) IEEE Int. Conf. on Computer Vision, Nice, pp. 886–892. IEEE, Los Alamitos (Oct. 2003)
Cremers, D., Soatto, S.: Motion Competition: A variational framework for piecewise parametric motion segmentation. Int. J. of Comp. Vis. (to appear, 2004)
Cremers, D., Yuille, A.L.: A generative model based approach to motion segmentation. In: Michaelis, B., Krell, G. (eds.) Pattern Recognition. LNCS, vol. 2781, pp. 313–320. Springer, Heidelberg (2003)
Farnebäck, G.: Very high accuracy velocity estimation using orientation tensors, parametric motion, and segmentation of the motion field. In: ICCV, vol. 1, pp. 171–177 (2001)
Heitz, F., Bouthemy, P.: Multimodal estimation of discontinuous optical flow using markov random fields. IEEE PAMI 15(12), 1217–1232 (1993)
Horn, B.K.P., Schunck, B.G.: Determining optical flow. A.I. 17, 185–203 (1981)
Jehan-Besson, S., Barlaud, M., Aubert, G.: DREAM2S: Deformable regions driven by an eulerian accurate minimization method for image and video segmentation. Int. J. of Comp. Vis. 53(1), 45–70 (2003)
Jepson, A., Black, M.J.: Mixture models for optic flow computation. In: Proc. IEEE Conf. on Comp. Vision Patt. Recog., New York, pp. 760–761. IEEE Computer Society Press, Los Alamitos (1993)
Kichenassamy, S., Kumar, A., Olver, P.J., Tannenbaum, A., Yezzi, A.J.: Gradient flows and geometric active contour models. In: Proc. IEEE Intl. Conf. on Comp. Vis., Boston, USA, pp. 810–815. IEEE, Los Alamitos (1995)
Konrad, J., Dubois, E.: Bayesian estimation of motion vector fields. IEEE PAMI 14(9), 910–927 (1992)
Kornprobst, P., Deriche, R., Aubert, G.: Image sequence analysis via partial differential equations. J. Math. Im. Vis. 11(1), 5–26 (1999)
Memin, E., Perez, P.: Dense estimation and object-based segmentation of the optical flow with robust techniques. IEEE Trans. on Im. Proc. 7(5), 703–719 (1998)
Morel, J.-M., Solimini, S.: Variational Methods in Image Segmentation. Birkhäuser, Boston (1995)
Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Comm. Pure Appl. Math. 42, 577–685 (1989)
Nagel, H.H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE PAMI 8(5), 565–593 (1986)
Nestares, O., Fleet, D.J., Heeger, D.J.: Likelihood functions and confidence bounds for total-least-squares problems. In: Proc. Conf. Computer Vis. and Pattern Recog., vol. 1, Hilton Head Island, SC, June, pp. 760–767 (2000)
Odobez, J.-M., Bouthemy, P.: Direct incremental model-based image motion segmentation for video analysis. Signal Proc. 66, 143–155 (1998)
Osher, S.J., Sethian, J.A.: Fronts propagation with curvature dependent speed: Algorithms based on Hamilton–Jacobi formulations. J. of Comp. Phys. 79, 12–49 (1988)
Paragios, N., Deriche, R.: Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE PAMI 22(3), 266–280 (2000)
Schnörr, C.: Computation of discontinuous optical flow by domain decomposition and shape optimization. Int. J. of Comp. Vis. 8(2), 153–165 (1992)
Shi, J., Malik, J.: Motion segmentation and tracking using normalized cuts. In: Intl. Conf. on Comp. Vision, Bombay, India (1998)
Sussman, M., Smereka, P., Osher, S.J.: A level set approach for computing solutions to incompressible twophase flow. J. of Comp. Phys. 94, 146–159 (1994)
Torr, P.H.S., Szeliski, R., Anandan, P.: An integrated bayesian approach to layer extraction from image sequences. IEEE PAMI 23(3), 297–303 (2002)
Vidal, R., Ma, Y., Sastry, S.: Generalized principal component analysis (gpca): an analytic solution to segmentation of mixtures of subspaces. In: Proc. IEEE Conf. on Comp. Vision Patt. Recog., vol. 1, Madison, pp. 621–628. IEEE Computer Society Press, Los Alamitos (2003)
Wang, J.Y.A., Adelson, E.H.: Representating moving images with layers. IEEE Trans. on Image Processing 3(5), 625–638 (1994)
Weickert, J., Schnörr, C.: A theoretical framework for convex regularizers in PDE–based computation of image motion. Int. J. of Comp. Vis. 45(3), 245–264 (2001)
Weiss, Y.: Smoothness in layers: Motion segmentation using nonparametric mixture estimation. In: Proc. IEEE Conf. on Comp. Vision Patt. Recog., Puerto Rico, pp. 520–527. IEEE Computer Society Press, Los Alamitos (1997)
Weiss, Y., Fleet, D.J.: Velocity likelihoods in biological and machine vision. In: Lewicki, M.S., Rao, R.P.N., Olshausen, B.A. (eds.) Probabilistic Models of the Brain: Perception and Neural Function, pp. 81–100. MIT Press, Cambridge (2001)
Zhu, S.C., Yuille, A.: Region competition: Unifying snakes, region growing, and Bayes/MDL for multiband image segmentation. IEEE PAMI 18(9), 884–900 (1996)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Cremers, D. (2007). Bayesian Approaches to Motion-Based Image and Video Segmentation. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds) Complex Motion. IWCM 2004. Lecture Notes in Computer Science, vol 3417. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69866-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-69866-1_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69864-7
Online ISBN: 978-3-540-69866-1
eBook Packages: Computer ScienceComputer Science (R0)