Abstract
In this study, we introduce a new cosegmentation approach, MOMI-cosegmentation, to segment multiple objects that repeatedly appear among multiple images. The proposed approach tackles a more general problem than conventional cosegmentation methods. Each of the shared objects may even appear more than one time in one image. The key idea of MOMI-cosegmentation is to incorporate a common pattern discovery algorithm with the proposed Gibbs energy model in a Markov random field framework. Our approach builds upon an observation that the detected common patterns provide useful information for estimating foreground statistics, while background statistics can be estimated from the remaining pixels. The initialization and segmentation processes of MOMI-cosegmentation are completely automatic, while the segmentation errors can be substantially reduced at the same time. Experimental results demonstrate the effectiveness of the proposed approach over state-of-the-art cosegmentation method.
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
Rother, C., Kolmogorov, V., Blake, A.: Grabcut: Interactive foreground extraction using iterated graph cuts. In: ACM SIGGRAPH, p. 314. ACM, New York (2004)
Li, Y., Sun, J., Tang, C.K., Shum, H.Y.: Lazy snapping. ACM Trans. on Graphics 23, 303–308 (2004)
Riklin-Raviv, T., Sochen, N., Kiryati, N.: Shape-based mutual segmentation. IJCV 79, 231–245 (2008)
Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In: CVPR, vol. 1 (2006)
Cheng, D.S., Figueiredo, M.: Cosegmentation for image sequences. In: International Conference on Image Analysis and Processing, pp. 635–640 (2007)
Sun, J., Kang, S.B., Xu, Z.B., Tang, X., Shum, H.Y.: Flash Cut: Foreground Extraction With Flash And No-flash Image Pairs. In: CVPR, pp. 1–8 (2007)
Cao, L., Fei-Fei, L.: Spatially coherent latent topic model for concurrent object segmentation and classification. In: ICCV (2007)
Gallagher, A.C., Chen, T.H.: Clothing cosegmentation for recognizing people. In: CVPR, pp. 1–8 (2008)
Hochbaum, D.S., Singh, V.: An efficient algorithm for co-segmentation. In: ICCV (2009)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in ND images. In: ICCV, vol. 1, pp. 105–112 (2001)
Chen, C.P., Chu, W.S., Chen, C.S.: Common pattern discovery with high-order constraints by density-based cluster discovery (2010) (submitted for publication)
Mukherjee, L., Singh, V., Dyer, C.R.: Half-integrality based algorithms for cosegmentation of images. In: CVPR (2009)
Quack, T., Ferrari, V., Leibe, B., Gool, V.L.: Efficient mining of frequent and distinctive feature configurations. In: ICCV, pp. 1–8 (2007)
Yuan, J., Wu, Y.: Spatial random partition for common visual pattern discovery. In: ICCV, pp. 1–8 (2007)
Yuan, J., Li, Z., Fu, Y., Wu, Y., Huang, T.S.: Common spatial pattern discovery by efficient candidate pruning. In: International Conference on Image Processing (2007)
van de Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. IEEE Trans. on PAMI (2010) (in press)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 60, 63–86 (2004)
Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Knowledge Discovery and Datamining, pp. 226–231 (1996)
Sun, J., Zhang, W., Tang, X., Shum, H.-Y.: Background cut. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 628–641. Springer, Heidelberg (2006)
Guillemaut, J.Y., Kilner, J., Hilton, A.: Robust graphcut scene segmentation and reconstruction for free-viewpoint video of complex dynamic scenes. In: ICCV (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chu, WS., Chen, CP., Chen, CS. (2011). MOMI-Cosegmentation: Simultaneous Segmentation of Multiple Objects among Multiple Images. In: Kimmel, R., Klette, R., Sugimoto, A. (eds) Computer Vision – ACCV 2010. ACCV 2010. Lecture Notes in Computer Science, vol 6492. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19315-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-19315-6_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19314-9
Online ISBN: 978-3-642-19315-6
eBook Packages: Computer ScienceComputer Science (R0)