Computer Vision - ECCV 2004

We present an analytic solution to the problem of estimating multiple 2-D and 3-D motion models from two-view correspondences or optical flow. The key to our approach is to view the estimation of multiple motion models as the estimation of a single multibody motion model. This is possible thanks to two important algebraic facts. First, we show that all the image measurements, regardless of their associated motion model, can be fit with a real or complex polynomial. Second, we show that the parameters of the motion model associated with an image measurement can be obtained from the derivatives of the polynomial at the measurement. This leads to a novel motion segmentation algorithm that applies to most of the two-view motion models adopted in computer vision. Our experiments show that the proposed algorithm outperforms existing algebraic methods in terms of efficiency and robustness, and provides a good initialization for iterative techniques, such as EM, which is strongly dependent on correct initialization.

[1]  Nathan Intrator,et al.  Complex cells and Object Recognition , 1997 .

[2]  Andrea J. van Doorn,et al.  Generic Neighborhood Operators , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Andrew W. Fitzgibbon,et al.  Joint manifold distance: a new approach to appearance based clustering , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[4]  Andrew Zisserman,et al.  Viewpoint invariant texture matching and wide baseline stereo , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[5]  Stefano Soatto,et al.  Multi-view stereo beyond Lambert , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  Andrew Zisserman,et al.  Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?" , 2002, ECCV.

[7]  Padhraic Smyth,et al.  Towards scalable support vector machines using squashing , 2000, KDD '00.

[8]  Adam Baumberg,et al.  Reliable feature matching across widely separated views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[9]  Nello Cristianini,et al.  Learning the Kernel Matrix with Semidefinite Programming , 2002, J. Mach. Learn. Res..

[10]  Tony Lindeberg,et al.  Scale-Space Theory in Computer Vision , 1993, Lecture Notes in Computer Science.

[11]  Ivor W. Tsang,et al.  The pre-image problem in kernel methods , 2003, IEEE Transactions on Neural Networks.

[12]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

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

[14]  K. Walker,et al.  View-based active appearance models , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[15]  Michael Lindenbaum,et al.  Sequential Karhunen-Loeve basis extraction and its application to images , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[16]  Gunnar Rätsch,et al.  Input space versus feature space in kernel-based methods , 1999, IEEE Trans. Neural Networks.

[17]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[18]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

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

[20]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[21]  Cordelia Schmid,et al.  Matching images with different resolutions , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[22]  Gustavo Carneiro,et al.  Phase-Based Local Features , 2002, ECCV.

[23]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[24]  Bernhard Schölkopf,et al.  Fast Approximation of Support Vector Kernel Expansions, and an Interpretation of Clustering as Approximation in Feature Spaces , 1998, DAGM-Symposium.

[25]  J. Bunch,et al.  Updating the singular value decomposition , 1978 .

[26]  Andrew Zisserman,et al.  Wide baseline stereo matching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

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

[28]  C. Schmid,et al.  Indexing based on scale invariant interest points , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[29]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Luc Van Gool,et al.  Wide-baseline multiple-view correspondences , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[31]  Stefan Carlsson,et al.  Wide Baseline Point Matching Using Affine Invariants Computed from Intensity Profiles , 2000, ECCV.

[32]  Cordelia Schmid,et al.  3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[33]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Luc Van Gool,et al.  Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions , 2000, BMVC.

[35]  Brendan J. Frey,et al.  Transformed component analysis: joint estimation of spatial transformations and image components , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.