A Divided-and-Conquer Algorithm Based on Guided Selection for Two-View Motion Segmentation

Abstract:

Motion segmentation for dynamic scene is a fundamental problem in computer vision due to its well-known chicken-and-egg character. The key issue is to estimate both numbers and parameters of motions simultaneously. Different from global clustering method and random sampling scheme, in this paper, we propose a divided-and-conquer algorithm to solve the motion segmentation problem. A guided selection is used to choose the most creditable hypothetical motion as a candidate seed and then make it grow larger. Compared to previous works such as expectation maximization and factorization approaches, there is no need for any pre-knowledge of the number of motions. To global non-parametric clustering method, it is fast because each time we only do cluster process in a partitioned sub-set. Experiments have shown that the proposal method can give a satisfying result for motion segmentation.

• Periodical: Applied Mechanics and Materials (Volumes 20-23)
• Pages: 452-458
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.20-23.452
• Online since: January 2010
• Authors: Hui Jing Wang, Kai Chen, Yi Zhou, Yan Zhang, Hai Bing Guan
• Keywords: Conquer, Divided, Guided Selection, Motion Segmentation

References

[1] David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision 60(2), 91-110, 2004. Springer.

DOI: 10.1023/b:visi.0000029664.99615.94

[2] O. Tuzel, and P. Meer, Simultaneous multiple 3D motion estimation via mode finding on Lie groups, in Proc. 8th Intl. Conf. on Computer Vision, Beijing, China, vol. 1, 2005, pp.18-25.

DOI: 10.1109/iccv.2005.226

[3] Jeffrey S. Beis and David G. Lowe, Shape Indexing Using Approximate Nearest Neighor Search in High-Dimensional Spaces, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages: 1000-1006, June (1997).

DOI: 10.1109/cvpr.1997.609451

[4] Yan Zhang, Kai Chen and Huijing Wang, Two-View Motion Segmentation by Gaussian Blurring Mean Shift with Fitness Measure, in Computer Image and Signal Processing (CISP), 2009, Accepted.

DOI: 10.1109/cisp.2009.5303801

[5] Miguel A, Carreira-Perpinan, Generalised Blurring Mean-Shift Algorithms for Nonparametric Clustering, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008).

DOI: 10.1109/cvpr.2008.4587435

[6] Yong-Dian Jian and Chu-Song Chen, Two-View Motion Segmentation by Mixtures of Dirichlet Process with Model Selection and Outlier Removal, IEEE 11th International Conference on Computer Vision, pages: 1-8, Oct (2007).

DOI: 10.1109/iccv.2007.4408974

[7] Raghav Subbarao and Peter Meer, Nonlinear Mean Shift for Clustering over Analytic Manifolds, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages: 1168-1175, (2006).

DOI: 10.1109/cvpr.2006.210

[8] Ninad Thakoor and Jean Gao, Branch-and-bound Hypothesis Selection for Two-view Multiple Structure and Motion Segmentation, IEEE Conference on Computer Vision and Pattern Recognition, pages: 1-6, June (2008).

DOI: 10.1109/cvpr.2008.4587469

[9] M. A. Fischler and R. C. Bolles, Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM, 24(6): 381-395, (1981).

DOI: 10.1145/358669.358692

[10] R. Vidal and Y. Ma, A unified algebraic approach to 2-d and 3-d motion segmentation, In Proceedings of ECCV, (2004).

[11] R. I. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, second edition, (2004).

[12] J. P. Costeira and T. Kanade, A multibody factorization method for independently moving objects, International Journal of Computer Vision, 29(3): 159-179, (1998).

[13] A. Gruber, Incorporating non-motion cues into 3d motion segmentation, ECCV, (2006).

[14] R. Vidal, Y. Ma, S. Soatto, and S. Sastry, Two-view multibody structure from motion, International Journal of Computer Vision, 68(1): 7-25, (2006).

DOI: 10.1007/s11263-005-4839-7

[15] K. Huang, R. Vidal, and Y. Ma, Minimum effective dimension for mixtures of subspaces: A robust gpca algorithm and its applications, CVPR, (2004).

DOI: 10.1109/cvpr.2004.1315223

[16] J. Y. Yan and M. Pollefeys, A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate, In European Conference on Computer Vision, (2006).

DOI: 10.1007/11744085_8

[17] N. Vasconcelos and A. Lippman, Empirical bayesian embased motion segmentation, CVPR, 00: 527, (1997).

[18] Z Zhang, R Deriche, O Faugeras and QT Luong, A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry, Artificial Intelligence - Elsevier, (1995).

DOI: 10.1016/0004-3702(95)00022-4