Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis

We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the relative simplicity of small baseline tracking in image sequences to develop descriptors suitable for the more challenging task of wide baseline matching across significant viewpoint changes. The variations in the appearance of each feature are learned using kernel principal component analysis (KPCA) over the course of image sequences. An approximate version of KPCA is applied to reduce the computational complexity of the algorithms and yield a compact representation. Our experiments demonstrate robustness to wide appearance variations on non-planar surfaces, including changes in illumination, viewpoint, scale, and geometry of the scene.

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

[2]  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.

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

[4]  Jang-Gyu Lee,et al.  On updating the singular value decomposition , 1996, Proceedings of International Conference on Communication Technology. ICCT '96.

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

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

[7]  Mads Nielsen,et al.  Computer Vision — ECCV 2002 , 2002, Lecture Notes in Computer Science.

[8]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

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

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

[11]  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).

[12]  Jan-Olof Eklundh,et al.  Computer Vision — ECCV '94 , 1994, Lecture Notes in Computer Science.

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

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

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

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

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

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

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

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

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

[22]  Roberto Cipolla,et al.  Computer Vision — ECCV '96 , 1996, Lecture Notes in Computer Science.

[23]  Pat Langley,et al.  Editorial: On Machine Learning , 1986, Machine Learning.

[24]  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).

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

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

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

[28]  Cordelia Schmid,et al.  Indexing Based on Scale Invariant Interest Points , 2001, ICCV.

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

[30]  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..

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

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

[33]  Christopher M. Bishop,et al.  Non-linear Bayesian Image Modelling , 2000, ECCV.

[34]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

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

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

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

[38]  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..

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

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

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

[42]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.