Abstract
The methods which compute image flow based on spatiotemporal filters have only used one level of the Gaussian pyramid, and have discarded useful information from other levels. In this paper a method is presented to combine the contributions from all the levels of the Gaussian pyramid to obtain a more refined estimate. The method uses a coarse-to-fine strategy adapted to spatiotemporal Gabor filters. The property of separability of Gabor filters is shown to help the efficiency of the coarse-to-fine strategy. This property allows some computations in parallel at all levels of the pyramid and the complementary computations are done from coarse to fine levels.
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
Adelson, E.H., Bergen, J.R.: Spatiotemporal energy models for the perception of motion. Journal of the Optical Society of America, A. 2 (1985) 284–299
Barron, J.L., Jepson, A.D., Tsotsos, J.K.: The feasibility of motion and structure from noisy time-varying image velocity information. International Journal of Computer Vision. 5 (1990) 239–269
Barron, J.L., Jepson, A.D., Tsotsos, J.K.: Determination of egomotion and environmental layout From noisy time varying velocity in binocular image sequences. Proc. 10th Intern. Joint Conf. Artif. Intell. (1987) 822–825
Burt, P.J.: The pyramid as a structure for efficient computation. In Multiresolution Image Processing and Analysis, A. Rosenfeld (Ed.). Springer Series in Information Sciences, Springer-Verlag. (1984)
Fleet, D.J., Jepson A.D.: Computation of component image velocity from local phase information. International Journal of Computer Vision. 5 (1990) 77–104
Heeger, D.J.: Model for the extraction of image flow. Journal of the Optical Society of America, A. 4 (1987) 1455–1471
Heeger, D. J.: Optical flow from spatiotemporal filters. Proceedings of the First International Conference on Computer Vision. (1987) 181–190
Horn, B.K.P., Schunck, B.G.: Determining optic flow. Artificial Intelligence. 17 (1981) 185–203
Waxman, A.M.: An image flow paradigm. In Readings in Computer Vision: issues, problems, principles and paradigms, Fischler M.A. & O. Firschein, (Eds.). (1987)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ríos, H. (1993). Computing image flow using a coarse-to-fine strategy for spatiotemporal filters. In: Chetverikov, D., Kropatsch, W.G. (eds) Computer Analysis of Images and Patterns. CAIP 1993. Lecture Notes in Computer Science, vol 719. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57233-3_47
Download citation
DOI: https://doi.org/10.1007/3-540-57233-3_47
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57233-6
Online ISBN: 978-3-540-47980-2
eBook Packages: Springer Book Archive