Abstract
We present a novel variational approach for segmenting the image plane into a set of regions of piecewise constant motion on the basis of only two consecutive frames from an image sequence.
To this end, we formulate the problem of estimating a motion field in the framework of Bayesian inference. Our model is based on a conditional probability for the spatio-temporal image gradient, given a particular velocity vector, and on a prior on the estimated motion field favoring motion boundaries of minimal length. The corresponding negative log likelihood is a functional which depends on motion vectors for a set of regions and on the boundary separating these regions. It can be considered an extension of the Mumford-Shah functional from intensity segmentation to motion segmentation.
We propose an implementation of this functional by a multiphase level set framework. Minimizing the functional with respect to its dynamic variables results in an evolution equation for a vector-valued level set function and in an eigenvalue problem for the motion vectors. Compared to most alternative approaches, we jointly solve the problems of segmentation and motion estimation by minimizing a single functional. Numerical results both for simulated ground truth experiments and for real-world sequences demonstrate the capacity of our approach to segment several — possibly multiply connected — objects based on their relative motion.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
S. Ayer and H.S. Sawhney. Layered representation of motion video using robust maximum likelihood estimation of mixture models and MDL encoding. In Proc. of the Int. Conf. on Comp. Vis., pages 777–784, Boston, USA, 1995.
M. J. Black and P. Anandan. The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Comp. Vis. Graph. Image Proc.: IU, 63(1):75–104, 1996.
V. Caselles and B. Coll. Snakes in movement. SIAM J. Numer. Anal., 33:2445–2456, 1996.
V. Caselles, R. Kimmel, and G. Sapiro. Geodesic active contours. In Proc. IEEE Internat. Conf. on Comp. Vis., pages 694–699, Boston, USA, 1995.
T. Chan and L. Vese. Active contours without edges. IEEE Trans. Image Processing, 10(2):266–277, 2001.
D. Cremers. A variational framework for image segmentation combining motion estimation and shape regularization. In C. Dyer and P. Perona, editors, IEEE Int. Conf. on Comp. Vis. and Patt. Recog., Madison, Wisconsin, June 2003. To appear.
D. Cremers and C. Schnörr. Motion Competition: Variational integration of motion segmentation and shape regularization. In L. van Gool, editor, Pattern Recognition, volume 2449 of LNCS, pages 472–480, Zürich, Sept. 2002. Springer.
D. Cremers and C. Schnörr. Statistical shape knowledge in variational motion segmentation. Image and Vision Computing, 21(1):77–86, 2003.
G. Farnebäck. Very high accuracy velocity estimation using orientation tensors, parametric motion, and segmentation of the motion field. In Proc. 8th ICCV, volume 1, pages 171–177, 2001.
J. Gomes and O. D. Faugeras. Level sets and distance functions. In D. Vernon, editor, Proc. of the Europ. Conf. on Comp. Vis., volume 1842 of LNCS, pages 588–602, Dublin, Ireland, 2000. Springer.
B.K.P. Horn and B.G. Schunck. Determining optical flow. Artif. Intell., 17:185–203, 1981.
A. Jepson and M.J. Black. Mixture models for optic flow computation. In Proc. IEEE Conf. on Comp. Vision Patt. Recog., pages 760–761, New York, 1993.
S. Kichenassamy, A. Kumar, P. J. Olver, A. Tannenbaum, and A. J. Yezzi. Gradient flows and geometric active contour models. In Proc. IEEE Internat. Conf. on. Comp. Vis., pages 810–815, Boston, USA, 1995.
P. Kornprobst, R. Deriche, and G. Aubert. Image sequence analysis via partial differential equations. J. Math. Im. Vis., 11(1):5–26, 1999.
B. D. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision. In Proc.7th International Joint Conference on Artificial Intelligence, pages 674–679, Vancouver, 1981.
A. Mansouri, B. Sirivong, and J. Konrad. Multiple motion segmentation with level set. In Proc. SPIE Conf. on Image and Video Communications and Processing, pages 584–595, Santa Fe, 2000.
E. Memin and P. Perez. Dense estimation and object-based segmentation of the optical flow with robust techniques. IEEE Trans. on Im. Proc., 7(5):703–719, 1998.
J.-M. Morel and S. Solimini. Variational Methods in Image Segmentation. Birkhäuser, Boston, 1995.
D. Mumford and J. Shah. Optimal approximations by piecewise smooth functions and associated variational problems. Comm. Pure Appl. Math., 42:577–685, 1989.
J.-M. Odobez and P. Bouthemy. Robust multiresolution estimation of parametric motion models. J. of Visual Commun. and Image Repr., 6(4):348–365, 1995.
J.-M. Odobez and P. Bouthemy. Direct incremental model-based image motion segmentation for video analysis. Signal Proc., 66:143–155, 1998.
S. J. Osher and J. A. Sethian. Fronts propagation with curvature dependent speed: Algorithms based on Hamilton-Jacobi formulations. J. of Comp. Phys., 79:12–49, 1988.
N. Paragios and R. Deriche. Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE Trans. on Patt. Anal. and Mach. Intell., 22(3):266–280, 2000.
C. Samson, L. Blanc-Féraud, G. Aubert, and J. Zerubia. A level set model for image classification. Int. J. of Comp. Vis., 40(3):187–197, 2000.
C. Schnörr. Computation of discontinuous optical flow by domain decomposition and shape optimization. Int. J. of Comp. Vis., 8(2):153–165, 1992.
M. Sussman and E. Fatemi. An efficient, interface-preserving level set redistancing algorithm and its application to interfacial incompressible fluid flow. SIAM J. Sci. Comput., 20(4):1165–1191, 1999.
M. Sussman, Smereka P., and S. J. Osher. A level set approach for computing solutions to incompressible twophase flow. J. of Comp. Phys., 94:146–159, 1994.
J. Weickert and C. Schnörr. A theoretical framework for convex regularizers in PDE-based computation of image motion. Int. J. of Comp. Vis., 45(3):245–264, 2001.
Y. Weiss. Smoothness in layers: Motion segmentation using nonparametric mixture estimation. In Proc. IEEE Conf. on Comp. Vision Patt. Recog., pages 520–527, Puerto Rico, 1997.
H.-K. Zhao, T. Chan, B. Merriman, and S. Osher. A variational level set approach to multiphase motion. J. of Comp. Phys., 127:179–195, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cremers, D. (2003). A Multiphase Level Set Framework for Motion Segmentation. In: Griffin, L.D., Lillholm, M. (eds) Scale Space Methods in Computer Vision. Scale-Space 2003. Lecture Notes in Computer Science, vol 2695. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44935-3_42
Download citation
DOI: https://doi.org/10.1007/3-540-44935-3_42
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40368-5
Online ISBN: 978-3-540-44935-5
eBook Packages: Springer Book Archive