Abstract
This paper evaluates and compares uniform and non-uniform algorithms that implement the estimation of motion, focusing on the finite element method as a framework for the development of techniques. The finite element approach has the advantages of a rigorous mathematical formulation, speed of reconstruction, conceptual simplicity and ease of implementation via well-established finite element procedures in comparison to finite volume or finite difference techniques. The finite element techniques are implemented through a variety of grid discretisations, with results presented and compared. An important advantage of the non-uniform technique is the capacity to tackle problems in which non-uniform sampling of the image sequence is appropriate.
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
Cohen, I., Herlin, I.: Non-Uniform Multiresolution Method for Optical Flow and Phase Portrait Models. Int. J. Computer Vision 33(1), 1–22 (1999)
Condell, J.V.: Motion Tracking in Digital Images. PhD thesis, Faculty of Informatics, University of Ulster (2002)
Condell, J.V., Scotney, B.W., Morrow, P.J.: Estimation of Motion Through Inverse Finite Element Methods with Triangular Meshes. In: Skarbek, W. (ed.) CAIP 2001. LNCS, vol. 2124, pp. 333–340. Springer, Heidelberg (2001)
Condell, J.V., Scotney, B.W., Morrow, P.J.: Detection and Estimation of Motion using Adaptive Grids. In: IEEE Proc. 14th Int. Confer. Digital Signal Processing (DSP 2002) (2002)
Graham, J.V., Scotney, B.W., Morrow, P.J.: Evaluation of Inverse Finite Element Techniques for Gradient Based Motion Estimation. In: Image Processing III: Mathematical Methods, Algorithms and Applications. Mathematics and Applications, pp. 200–220. Horwood Publishing Ltd., England (2001)
Horn, B.K.P., Schunck, B.G.: Determining Optical Flow. A.I 17, 185–203 (1981)
Ong, E.P., Spann, M.: Robust Optical Flow Computation based on Least-Median-of- Squares Regression. Int. J. Computer Vision 31(1), 51–82 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Condell, J., Scotney, B., Morrow, P. (2003). Evaluation of Uniform and Non-uniform Optical Flow Techniques Using Finite Element Methods. In: Michaelis, B., Krell, G. (eds) Pattern Recognition. DAGM 2003. Lecture Notes in Computer Science, vol 2781. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45243-0_16
Download citation
DOI: https://doi.org/10.1007/978-3-540-45243-0_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40861-1
Online ISBN: 978-3-540-45243-0
eBook Packages: Springer Book Archive