Abstract
This paper proposes an ortho-diffusion decomposition of graphs for estimating motion from image sequences. Orthonormal decompositions of the adjacency matrix representations of image data are alternated with diffusions and data subsampling in order to robustly represent image features using undirected graphs. Modified Gram-Schmidt with pivoting the columns algorithm is applied recursively for the orthonormal decompositions at various scales. This processing produces a set of ortho-diffusion bases and residual diffusion wavelets at each image representation scale. The optical flow is estimated using the similarity in the ortho-diffusion bases space extracted from regions of two different image frames.
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
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation 15(6), 1373–1396 (2003)
Robles-Kelly, A., Bors, A.G., Hancock, E.R.: Hierarchical iterative eigendecomposition for motion segmentation. In: Proc. IEEE Inter. Conf. on Image Processing, vol. II, pp. 363–366 (2001)
Xiao, B., Hancock, E.R., Wilson, R.C.: Graph characteristics from the heat kernel trace. Pattern Recognition 42(11), 2589–2606 (2009)
Coifman, R.R., Lafon, S.: Diffusion maps. Applied Comput. Harmon. Anal. 21(1), 5–30 (2006)
Singer, A., Coifman, R.R.: Non-linear independent component analysis with diffusion maps. Applied Comput. Harmon. Anal. 25(1), 226–239 (2008)
Wartak, S., Bors, A.G.: Optical Flow Estimation Using Diffusion Distances. In: Proc. Int. Conf on Pattern Recognition, pp. 189–192 (2010)
Magioni, M., Mahadevan, S.: Fast direct policy evaluation using multiscale analysis of Markov diffusion processes. In: Proc. Int. Conf. Machine Learn., pp. 601–608 (2005)
Black, M.B., Anandan, P.: The robust estimation of multiple motions: parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding 63(1), 75–104 (1996)
Bouguet, J.: Pyramidal Implementation of the Lucas-Kanade Feature Tracker: Description of the Algorithm Technical Report TR2004-196, Intel Microprocessor Research Labs (2000)
Bruhn, A., Weickert, J., Schnorr, C.: Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. Int. Jour. of Computer Vision 61(3), 211–231 (2005)
Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. Jour. of Computer Vision 92(1), 1–31 (2011)
Doshi, A., Bors, A.G.: Robust processing of optical flow of fluids. IEEE Trans. Image Processing 19(9), 2332–2344 (2010)
Zitnick, C.L., Jojic, N., Kang, S.B.: Consistent segmentation for optical flow estimation. In: Proc. IEEE Int. Conf. on Computer Vision, vol. 2, pp. 1308–1315 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gudivada, S., Bors, A.G. (2013). Orthonormal Diffusion Decompositions of Images for Optical Flow Estimation. In: Wilson, R., Hancock, E., Bors, A., Smith, W. (eds) Computer Analysis of Images and Patterns. CAIP 2013. Lecture Notes in Computer Science, vol 8048. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40246-3_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-40246-3_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40245-6
Online ISBN: 978-3-642-40246-3
eBook Packages: Computer ScienceComputer Science (R0)