Abstract
In this work, we address the problem of segmenting multiple objects, with possible occlusions, in a variational setting. Most segmentation algorithms based on low-level features often fail under uncertainties such as occlusions and subtle boundaries. We introduce a segmentation algorithm incorporating high-level prior knowledge which is the shape of objects of interest. A novelty in our approach is that prior shape is introduced in a selective manner, only to occluded boundaries. Further, a direct application of our framework is that it solves the segmentation with depth problem that aims to recover the spatial order of overlapping objects for certain classes of images. We also present segmentation results on synthetic and real images.
Supported by ONR grant N00014-06-1-0345 and NSF grant DMS-0610079.
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
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. In: ICCV, pp. 694–699 (1995)
Chan, T., Zhu, W.: Level set based shape prior segmentation. In: Proc. CVPR’05, pp. 20–26 (2005)
Chan, T.F., Vese, L.A.: Active contours without edges. IEEE Trans. Image Processing 10(2), 266–277 (2001)
Chen, Y., Tagare, H., et al.: Using prior shapes in geometric active contours in a variational framework. IJCV 50(3), 315–328 (2002)
Cootes, T., et al.: Active shape models-their training and application. CVIU 61(1), 38–59 (1995)
Cremers, D., Sochen, N., Schnörr, C.: Towards recognition-based variational segmentation using shape priors and dynamic labeling. In: Proceedings of International Conference on Scale Space Theories in Computer Vision (2003)
Esedoglu, S., March, R.: Segmentation with depth but without detecting junctions. J. Mathematical Imaging and Vision 18(1), 7–15 (2003)
Kichenassamy, S., et al.: Gradient flows and geometric active contour models. In: ICCV, pp. 810–815 (1995)
Leventon, M., Grimson, W.L., Faugeras, O.: Statistical shape influence in geodesic active contours. In: CVPR, vol. 1, pp. 316–323 (2000)
Malladi, R., Sethian, J.A., Vemuri, B.C.: Shape modeling with front propagation: A level set approach. IEEE Trans. on PAMI 17, 158–175 (1995)
Rousson, M., Paragios, N., Deriche, R.: Active shape models from a level set perspective. Technical Report 4984, INRIA (October 2003)
Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Comm. on Pure and App. Math. 42, 577–684 (1989)
Nitzberg, M., Mumford, D.: The 2.1-d sketch. In: ICCV (1990)
Nitzberg, M., Shiota, T., Mumford, D. (eds.): Filtering, Segmentation and Depth. LNCS, vol. 662. Springer, Heidelberg (1993)
Osher, S., Sethian, J.: Fronts propagating with curvature dependent speed: algorithms based on the Hamilton–Jacobi formulation. J. of Comp. Phy. 79, 12–49 (1988)
Paragios, N., Deriche, R.: Geodesic active regions and level set methods for supervised texture segmentation. IJCV 46(3), 223–247 (2002)
Tsai, A., A.,, Yezzi, o.: Model-based curve evolution technique for image segmentation. In: Proc. CVPR’01, vol. 1, Dec. 2001, pp. 463–468 (2001), http://csdl.computer.org/comp/proceedings/cvpr/2001/1272/01/1272toc.htm
Vese, L., Chan, T.: Multiphase level set framework for image segmentation using the mumford and shah model. IJCV 50(3), 271–293 (2002)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Thiruvenkadam, S.R., Chan, T.F., Hong, BW. (2007). Segmentation Under Occlusions Using Selective Shape Prior. 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_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-72823-8_17
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)