Abstract
In the recent contribution [9], it was given a unified view of four neural-network-learning-based singular-value-decomposition algorithms, along with some analytical results that characterize their behavior. In the mentioned paper, no attention was paid to the specific integration of the learning equations which appear under the form of first-order matrix-type ordinary differential equations on the orthogonal group or on the Stiefel manifold. The aim of the present paper is to consider a suitable integration method, based on mathematical geometric integration theory. The obtained algorithm is applied to optical flow computation for motion estimation in image sequences.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Celledoni, E., Fiori, S.: Neural Learning by Geometric Integration of Reduced ‘Rigid-Body’ Equations. J. Comp. Appl. Math. (to appear)
Cichocki, A., Unbehauen, R.: Neural networks for computing eigenvalues and eigenvectors. Biological Cybernetics 68, 155–164 (1992)
Costa, S., Fiori, S.: Image Compression Using Principal Component Neural Networks. Image and Vision Computing Journal (special issue on “Artificial Neural Network for Image Analysis and Computer Vision”) 19(9-10), 649–668 (2001)
Deshpande, S.G., Hwang, J.-N.: Fast Motion Estimation Based on Total Least Squares for Video Encoding. In: Proc. International Symposium on Circuits and Systems, vol. 4, pp. 114–117 (1998)
Fiori, S.: A theory for learning by weight flow on Stiefel-Grassman manifold. Neural Computation 13(7), 1625–1647 (2001)
Fiori, S.: A Theory for Learning Based on Rigid Bodies Dynamics. IEEE Trans. on Neural Networks 13(3), 521–531 (2002)
Fiori, S.: Fixed-Point Neural Independent Component Analysis Algorithms on the Orthogonal Group. Fut. Gen. Comp. Syst. (to appear)
Fiori, S.: Unsupervised Neural Learning on Lie Group. International Journal of Neural Systems 12(3-4), 219–246 (2002)
Fiori, S.: Singular Value Decomposition Learning on Double Stiefel Manifold. International Journal of Neural Systems 13(2), 155–170 (2003)
Golub, G.H., Van Loan, C.F.: Matrix Computations, 3rd edn. The John Hopkins University Press, Baltimore (1996)
Helmke, U., Moore, J.B.: Singular value decomposition via gradient and selfequivalent flows. Lin. Alg. Appl. 169, 223–248 (1992)
Hori, G.: A general framework for SVD flows and joint SVD flows. In: Proc. International Conference on Acoustics, Speech and Signal Processing, vol. II, pp. 693–696 (2003)
Liu, L.K., Feig, E.: A Block-Based Gradient Descent Search Algorithm for Block Motion Estimation in Video Coding. IEEE Trans. Circuits and Systems for Video Technology 6(4), 419–422 (1996)
Lu, W.S., Wang, H.P., Antoniou, A.: Design of two-dimensional FIR digital filters by using the singular value decomposition. IEEE Trans. on Circuits and Systems CAS-37, 35–46 (1990)
Moore, B.C.: Principal component analysis in linear systems: Controllability, observability and model reduction. IEEE Trans. on Automatic Control AC-26(1), 17–31 (1981)
Nestares, O., Navarro, R.: Probabilistic estimation of optical flow in multiple bandpass directional channels. Image and Vision Computing journal 19(6), 339–351 (2001)
Sanger, T.D.: Two iterative algorithms for computing the singular value decomposition from input/output samples. In: Cowan, J.D., Tesauro, G., Alspector, J. (eds.) Advances in Neural Processing Systems, vol. 6, pp. 141–151. Morgan- Kauffman Publishers, San Francisco (1994)
Salmeron, M., Ortega, J., Puntonet, C.G., Prieto, A.: Improved RAN sequential prediction using orthogonal techniques. Neurocomputing 41(1-4), 153–172 (2001)
Smith, S.T.: Dynamic system that perform the SVD. Systems and Control Letters 15, 319–327 (1991)
USC-SPC Image Database, Sequences:Walter Cronkite, Signal & Image Processing Institute, Electrical Engineering Department, University of Southern California, http://sipi.usc.edu/service/database/Database.html
Weingessel, A.: An Analysis of Learning Algorithms in PCA and SVD Neural Networks. Ph.D. Dissertation, Technical University of Wien, Austria (1999)
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
Fiori, S., Del Buono, N., Politi, T. (2004). Optical Flow Estimation via Neural Singular Value Decomposition Learning. In: Laganá, A., Gavrilova, M.L., Kumar, V., Mun, Y., Tan, C.J.K., Gervasi, O. (eds) Computational Science and Its Applications – ICCSA 2004. ICCSA 2004. Lecture Notes in Computer Science, vol 3044. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24709-8_101
Download citation
DOI: https://doi.org/10.1007/978-3-540-24709-8_101
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22056-5
Online ISBN: 978-3-540-24709-8
eBook Packages: Springer Book Archive