Clustering and Embedding Using Commute Times

This paper exploits the properties of the commute time between nodes of a graph for the purposes of clustering and embedding and explores its applications to image segmentation and multibody motion tracking. Our starting point is the lazy random walk on the graph, which is determined by the heat kernel of the graph and can be computed from the spectrum of the graph Laplacian. We characterize the random walk using the commute time (that is, the expected time taken for a random walk to travel between two nodes and return) and show how this quantity may be computed from the Laplacian spectrum using the discrete Green's function. Our motivation is that the commute time can be anticipated to be a more robust measure of the proximity of data than the raw proximity matrix. In this paper, we explore two applications of the commute time. The first is to develop a method for image segmentation using the eigenvector corresponding to the smallest eigenvalue of the commute time matrix. We show that our commute time segmentation method has the property of enhancing the intragroup coherence while weakening intergroup coherence and is superior to the normalized cut. The second application is to develop a robust multibody motion tracking method using an embedding based on the commute time. Our embedding procedure preserves commute time and is closely akin to kernel PCA, the Laplacian eigenmap, and the diffusion map. We illustrate the results on both synthetic image sequences and real-world video sequences and compare our results with several alternative methods.

[1]  Ann B. Lee,et al.  Geometric diffusions as a tool for harmonic analysis and structure definition of data: diffusion maps. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Ronald R. Coifman,et al.  Diffusion Maps, Spectral Clustering and Eigenfunctions of Fokker-Planck Operators , 2005, NIPS.

[3]  Kenichi Kanatani,et al.  Outlier removal for motion tracking by subspace separation , 2002 .

[4]  Stéphane Lafon,et al.  Diffusion maps , 2006 .

[5]  Jianbo Shi,et al.  A Random Walks View of Spectral Segmentation , 2001, AISTATS.

[6]  Amnon Shashua,et al.  A unifying approach to hard and probabilistic clustering , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[7]  Ying Wu,et al.  Inference of multiple subspaces from high-dimensional data and application to multibody grouping , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[8]  François Fouss,et al.  The Principal Components Analysis of a Graph, and Its Relationships to Spectral Clustering , 2004, ECML.

[9]  Kim L. Boyer,et al.  Quantitative measures of change based on feature organization: eigenvalues and eigenvectors , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  François Fouss,et al.  An Experimental Investigation of Graph Kernels on a Collaborative Recommendation Task , 2006, Sixth International Conference on Data Mining (ICDM'06).

[12]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Guy L. Scott,et al.  Feature grouping by 'relocalisation' of eigenvectors of the proximity matrix , 1990, BMVC.

[14]  Edwin R. Hancock,et al.  Image Segmentation using Commute Times , 2005, BMVC.

[15]  Naoyuki Ichimura.  Motion segmentation based on factorization method and discriminant criterion , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[16]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[17]  Marcello Pelillo,et al.  Dominant sets and hierarchical clustering , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[18]  Jin Hyeong Park,et al.  Spectral Clustering for Robust Motion Segmentation , 2004, ECCV.

[19]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[20]  Kenichi Kanatani,et al.  Motion segmentation by subspace separation and model selection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[21]  KanadeTakeo,et al.  A Multibody Factorization Method for Independently Moving Objects , 1998 .

[22]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[23]  Ying Wu,et al.  Multibody grouping via orthogonal subspace decomposition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[24]  Ann B. Lee,et al.  Diffusion maps and coarse-graining: a unified framework for dimensionality reduction, graph partitioning, and data set parameterization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[26]  M. Pavan,et al.  A new graph-theoretic approach to clustering and segmentation , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[27]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[28]  Shing-Tung Yau,et al.  Discrete Green's Functions , 2000, J. Comb. Theory A.

[29]  Andrew B. Kahng,et al.  New spectral methods for ratio cut partitioning and clustering , 1991, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[30]  Yair Weiss,et al.  Multibody factorization with uncertainty and missing data using the EM algorithm , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[31]  C. W. Gear,et al.  Multibody Grouping from Motion Images , 1998, International Journal of Computer Vision.

[32]  Takeo Kanade,et al.  A multi-body factorization method for motion analysis , 1995, Proceedings of IEEE International Conference on Computer Vision.

[33]  Lihi Zelnik-Manor,et al.  Degeneracies, dependencies and their implications in multi-body and multi-sequence factorizations , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

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

[35]  Jan Poland,et al.  Amplifying the Block Matrix Structure for Spectral Clustering. , 2005 .

[36]  P. Anandan,et al.  Factorization with Uncertainty , 2000, International Journal of Computer Vision.

[37]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[38]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[39]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[40]  Risi Kondor,et al.  Diffusion kernels on graphs and other discrete structures , 2002, ICML 2002.

[41]  John D. Lafferty,et al.  Diffusion Kernels on Graphs and Other Discrete Input Spaces , 2002, ICML.

[42]  Pietro Perona,et al.  A Factorization Approach to Grouping , 1998, ECCV.

[43]  Yair Weiss,et al.  Segmentation using eigenvectors: a unifying view , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[44]  Kenichi Kanatani,et al.  Multi-Stage Unsupervised Learning for Multi-Body Motion Segmentation , 2004, IEICE Trans. Inf. Syst..

[45]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.