Abstract
We present an integrated two-level approach to computationally analyzing image sequences of static scenes by variational segmentation. At the top level, estimated models of object appearance and background are probabilistically fused to obtain an a-posteriori probability for the occupancy of each pixel. The data-association strategy handles object occlusions explicitly.
At the lower level, object models are inferred by variational segmentation based on image data and statistical shape priors. The use of shape priors allows to distinguish between recognition of known objects and segmentation of unknown objects. The object models are sufficiently flexible to enable the integration of general cues like advanced shape distances. At the same time, they are highly constrained from the optimization viewpoint: the globally optimal parameters can be computed at each time instant by dynamic programming.
The novelty of our approach is the integration of state-of-the-art variational segmentation into a probabilistic framework for static scene analysis that combines both on-line learning and prior knowledge of various aspects of object appearance.
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
Basri, R., Costa, L., Geiger, D., Jacobs, D.: Determining the similarity of deformable shapes. Vision Res. 38, 2365–2385 (1998)
Bergtholdt, M., Cremers, D., Schnörr, C.: Variational Segmentation with Shape Priors. In: Mathematical Models in Computer Vision: The Handbook (Spring 2005)
Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Processing 10(2), 266–277 (2001)
Chan, T., Zhu, W.: Level set based shape prior segmentation. Technical Report 03-66, Computational Applied Mathematics, UCLA, Los Angeles (2003)
Chen, Y., Tagare, H.D., Thiruvenkadam, S., Huang, F., Wilson, D., Gopinath, K.S., Briggs, R.W., Geiser, E.A.: Using prior shapes in geometric active contours in a variational framework. Intl. J. of Computer Vision 50(3), 315–328 (2002)
Cox, T.F., Cox, M.A.A.: Multidimensional Scaling. Chapman & Hall, London (2001)
Cremers, D., Sochen, N., Schnörr, C.: Towards recognition-based variational segmentation using shape priors and dynamic labeling. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, pp. 388–400. Springer, Heidelberg (2003)
Cremers, D., Tischhäuser, F., Weickert, J., Schnörr, C.: Diffusion Snakes: Introducing statistical shape knowledge into the Mumford–Shah functional. Intl. J. of Computer Vision 50(3), 295–313 (2002)
Gavrila, D.: Multi-feature hierarchical template matching using distance transforms. In: Proc. of IEEE International Conference on Pattern Recognition, Brisbane, Australia, pp. 439–444 (1998)
Gavrila, D.: Sensor-based pedestrian protection. IEEE Intelligent Systems 16, 77–81 (2001)
Heiler, M., Schnörr, C.: Natural image statistics for natural image segmentation. Intl. J. of Computer Vision 63(1), 5–19 (2005)
Jehan-Besson, S., Barlaud, M., Aubert, G.: Dream2s: Deformable regions driven by an eularian accurate minimization method for image and video segmentation. Int. J. Computer Vision 53(1), 45–70 (2003)
Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Comm. Pure Appl. Math. 42, 577–685 (1989)
Paragios, N., Deriche, R.: Geodesic active regions and level set methods for supervised texture segmentation. Intl. J. of Computer Vision 46(3), 223–247 (2002)
Riklin-Raviv, T., Kiryati, N., Sochen, N.: Unlevel sets: Geometry and prior-based segmentation. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 50–61. Springer, Heidelberg (2004)
Rousson, M., Paragios, N.: Shape priors for level set representations. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 78–92. Springer, Heidelberg (2002)
Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Proceedings of the IEEE Computer Science Conference on Computer Vision and Pattern Recognition (CVPR 1999), pp. 246–252. IEEE, Los Alamitos (1999)
Tsai, A., Yezzi, A.J., Willsky, A.S.: Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification. IEEE Trans. on Image Processing 10(8), 1169–1186 (2001)
Vese, L.A., Chan, T.F.: A multiphase level set framework for image segmentation using the mumford and shah model. Intl. J. of Computer Vision 50(3), 271–293 (2002)
Wahba, G.: Spline models for observational data. SIAM, Philadelphia (1990)
Yang, J., Duncan, J.S.: 3d image segmentation of deformable objects with joint shape-intensity prior models using level sets. Medical Image Analysis 8(3), 285–294 (2004)
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
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bergtholdt, M., Schnörr, C. (2005). Shape Priors and Online Appearance Learning for Variational Segmentation and Object Recognition in Static Scenes. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds) Pattern Recognition. DAGM 2005. Lecture Notes in Computer Science, vol 3663. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550518_43
Download citation
DOI: https://doi.org/10.1007/11550518_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28703-2
Online ISBN: 978-3-540-31942-9
eBook Packages: Computer ScienceComputer Science (R0)