Two-View Motion Segmentation by Gaussian Blurring Mean Shift with Fitness Measure

Motion segmentation for dynamic scene is fundamental in computer vision. The key issue is to estimate number and parameters of transformations simultaneously. However, transformations cannot be measured by general Euclidean distance because of them not lying in vector space. In this paper, we convert transformations into fitness vectors which can be easily measured by cosine similarity. Then we apply Gaussian Blurring Mean Shift (GBMS) algorithm as a non-parameter clustering for further motion segmentation. Our approach doesn’t need any preknowledge of the number of motions and converges within a few iterations. Experimental results have shown that the method has a good performance for motion segmentation. Keywords-GBMS; motion segmentation; fitness; non-parameter clustering

[1]  Marc Pollefeys,et al.  A General Framework for Motion Segmentation: Independent, Articulated, Rigid, Non-rigid, Degenerate and Non-degenerate , 2006, ECCV.

[2]  René Vidal,et al.  A Unified Algebraic Approach to 2-D and 3-D Motion Segmentation , 2004, ECCV.

[3]  S. Shankar Sastry,et al.  Two-View Multibody Structure from Motion , 2005, International Journal of Computer Vision.

[4]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[5]  Yair Weiss,et al.  Incorporating Non-motion Cues into 3D Motion Segmentation , 2006, ECCV.

[6]  Peter Meer,et al.  Simultaneous multiple 3D motion estimation via mode finding on Lie groups , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[7]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Peter Meer,et al.  Nonlinear Mean Shift for Clustering over Analytic Manifolds , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[9]  A. Carreira-Perpi.  Acceleration Strategies for Gaussian Mean-Shift Image Segmentation , 2006 .

[10]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Miguel Á. Carreira-Perpiñán,et al.  Generalised blurring mean-shift algorithms for nonparametric clustering , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[13]  Miguel Á. Carreira-Perpiñán.  Acceleration Strategies for Gaussian Mean-Shift Image Segmentation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[14]  Chu-Song Chen,et al.  Two-View Motion Segmentation by Mixtures of Dirichlet Process with Model Selection and Outlier Removal , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[15]  Yi Ma,et al.  Minimum effective dimension for mixtures of subspaces: a robust GPCA algorithm and its applications , 2004, CVPR 2004.

[16]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[17]  Nuno Vasconcelos,et al.  Empirical Bayesian EM-based motion segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Miguel Á. Carreira-Perpiñán,et al.  Fast nonparametric clustering with Gaussian blurring mean-shift , 2006, ICML.

[19]  Ilan Shimshoni,et al.  Mean shift based clustering in high dimensions: a texture classification example , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[20]  Ninad Thakoor,et al.  Branch-and-bound hypothesis selection for two-view multiple structure and motion segmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Takeo Kanade,et al.  A Multibody Factorization Method for Independently Moving Objects , 1998, International Journal of Computer Vision.