Abstract
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.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Baumberg, A.: Reliable feature matching across widely separated views. In: Proc. CVPR (2000)
Belhumeur, P., Hespanha, J., Kriegman, D.: Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. In: ECCV 1996. LNCS, vol. 1065, Springer, Heidelberg (1996)
Bishop, C.: Neural Networks for Pattern Recognition. Oxford U. Press (1995)
Bunch, J., Nielsen, C.: Updating the singular value decomposition. Numerische Mathematik 31, 111–129 (1978)
Carneiro, G., Jepson, A.: Phase-based local features. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 282–296. Springer, Heidelberg (2002)
Cootes, T., Wheeler, G., Walker, K., Taylor, C.: View-Based Active Appearance Models. Image and Vision Computing 20, 657–664 (2002)
Dufournaud, Y., Schmid, C., Horaud, R.: Matching images with different resolutions. In: Proc. CVPR (2000)
Edelman, S., Intrator, N., Poggio, T.: Complex cells and object recognition (1997) (unpublished manuscript)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Wide-baseline muliple-view correspondences. In: Proc. CVPR, Madison, USA (June 2003)
Fitzgibbon, A., Zisserman, A.: Joint manifold distance: a new approach to appearance based clustering. In: Proc. CVPR (2003)
Frey, B., Jojic, N.: Transformed Component Analysis: Joint Estimation of Spatial Transformations and Image Components. In: Proc. ICCV (1999)
Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference (1988)
Jin, H., Soatto, S., Yezzi, A.: Multi-view stereo beyond Lambert. In: CVPR (2003)
Johnson, A., Herbert, M.: Object recognition by matching oriented points. In: CVPR (1997)
Koenderink, J., van Doorn, A.: Generic neighborhood operators. IEEE Trans. Pattern Analysis and Machine Intell. 14, 597–605 (1992)
Kwok, J., Tsang, I.: The Pre-Image Problem in Kernel Methods. In: Proc. 20th Int. Conf. on Machine Learning (2003)
Lanckriet, G., Cristianini, N., Bartlett, P., El Ghaoui, L., Jordan, M.: Learning the kernel matrix with semi-definite programming. In: Proc. 19th Int. Conf. on Machine Learning, Sydney, Australia (2002)
Levy, A., Lindenbaum, M.: Sequential Karhunen-Loeve Basis Extraction and its Application to Images. IEEE Trans. on Image Processing (August 2000)
Lindeberg, T.: Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, Boston (1994)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Preprint, submitted to IJCV (version date: June 2003)
Lowe, D.: Object recognition from local scale-invariant features. In: Proc. ICCV, Corfu, Greece (September 1999)
Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: Proc. 8th ICCV (2001)
Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proc. CVPR (June 2003)
Pavlov, D., Chudova, D., Smyth, P.: Towards scalable support vector machines using squashing. In: Proc. Int. Conf. on Knowledge Discovery in Databases (2000)
Pritchett, P., Zisserman, A.: Wide baseline stereo matching. In: 6th ICCV (1998)
Rothganger, F., et al.: 3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints. In: Proc. CVPR (June 2003)
Schaffalitzky, F., Zisserman, A.: Viewpoint invariant texture matching and wide baseline stereo. In: Proc. ICCV (July 2001)
Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or ‘How do I organize my holiday snaps?’ ”. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 414–431. Springer, Heidelberg (2002)
Schölkopf, B., Smola, A.: Learning with Kernels. The MIT Press, Cambridge (2002)
Schölkopf, B., Smola, A., Müller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10, 1299–1319 (1998)
Schölkopf, B., et al.: Input Space vs. Feature Space in Kernel-Based Methods. IEEE Transactions on Neural Networks (1999)
Schölkopf, B., Knirsch, P., Smola, A., Burges, C.: Fast Approximation of Support Vector Kernel Expansions, and an Interpretation of Clustering as Approximation in Feature Spaces. In: DAGM Symposium Mustererkennung. LNCS, Springer, Heidelberg (1998)
Schmid, C., Mohr, R.: Local Greyvalue Invariants for Image Retrieval. Pattern Analysis and Machine Intelligence (1997)
Shi, J., Tomasi, C.: Good Features to Track. In: IEEE CVPR (1994)
Tell, D., Carlsson, S.: Wide Baseline Point Matching Using Affine Invariants Computed from Intensity Profiles. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 814–828. Springer, Heidelberg (2000)
Tomasi, C., Kanade, T.: Detection and tracking of point features. Tech. Rept. CMU-CS-91132. Pittsburgh: Carnegie Mellon U. School of Computer Science (1991)
Tuytelaars, T., Van Gool, L.: Wide Baseline Stereo based on Local, Affinely invariant Regions. In: British Machine Vision Conference, pp. 412–422 (2000)
Tuytelaars, T., Van Gool, L.: Matching Widely Separated Views based on Affine Invariant Regions. To appear in Int. J. on Computer Vision (2004)
Zabih, R., Woodfill, J.: Non-Parametric Local Transforms for Computing Visual Correspondence. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 801, Springer, Heidelberg (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Meltzer, J., Yang, MH., Gupta, R., Soatto, S. (2004). Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3021. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24670-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-24670-1_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21984-2
Online ISBN: 978-3-540-24670-1
eBook Packages: Springer Book Archive