Abstract
The goal of this paper is to study how the logarithmic-polar mapping affects the spatiotemporal volume and the computation of the optical flow. We propose two new methods for the estimation of the optical flow and its spatial derivatives in the log-polar plane. We study analytically and experimentally the effects of the polar deformation and we qualitatively explain the decimation due to subsampling on the computation of optical flow.
On leave at Lira-Lab, DIST, University of Genova, Via all'Opera Pia 13, 16145 Genova. We greatfully thank Gerald Sommer, Giulio Sandini, Yehoshua Zeevi, and Udo Mahlmeister for the helpful discussions.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
M. Bolduc and M.D. Levine. A foveated retina system for robotic vision. In ECCV-94 Workshop on Natural and Artificial Visual Sensors, 1994.
R.E. Kronauer and Y.Y. Zeevi. Reorganization and Diversification of Signals in Vision. IEEE Trans. Systems, Man, and Cybernetics, 15:91–101, 1985.
B. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision. In DARPA Image Understandig Workshop, pp. 121–130, 1981.
M. Otte and H.-H. Nagel. Optical flow estimation: advances and comparisons. In Proc. Third European Conference on Computer Vision, pp. 51–60. Stockholm, Sweden, May 2–6, 1994.
M. Porat and Y.Y. Zeevi. The Generalized Gabor Scheme of Image Representation in Biological and Machine Vision. IEEE Trans. Pattern Analysis and Machine Intelligence, 10: 452–468, 1988.
R. Schalkoff and E. McVey. A model and tracking algorithm for a class of video targets. IEEE Trans. Pattern Analysis and Machine Intelligence, 4: 2–10, 1982.
E.L. Schwartz. Spatial mapping in the primate sensory projection: analytic structure and relevance to perception. Biological Cybernetics, 25: 181–194, 1977.
M. Tistarelli and G. Sandini. Dynamic aspects in active vision. CVGIP: Image Understanding, 56: 108–129, 1992.
H. Tunley and D. Young. First order optical flow from log-polar sampled images. In Proc. Third European Conference on Computer Vision, pp. 132–137. Stockholm, Sweden, May 2–6, 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Daniilidis, K., Krüger, V. (1995). Optical flow computation in the log-polar plane. In: Hlaváč, V., Šára, R. (eds) Computer Analysis of Images and Patterns. CAIP 1995. Lecture Notes in Computer Science, vol 970. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60268-2_281
Download citation
DOI: https://doi.org/10.1007/3-540-60268-2_281
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60268-2
Online ISBN: 978-3-540-44781-8
eBook Packages: Springer Book Archive