Abstract
Image deformations due to relative motion between an observer and an object may be used to infer 3-D structure. Up to first order these deformations can be written in terms of an affine transform. Here, a novel approach is adopted to measuring affine transforms which correctly handles the problem of corresponding deformed patches. The patches are filtered using gaussians and derivatives of gaussians. The problem of finding the affine transform is reduced to that of finding the appropriate deformed filter to use. The method is local and can handle arbitrarily large affine deformations. Experiments demonstrate that this technique can find scale changes and optical flow in situations where other methods fail.
This research was supported by NSF grants CDA-8922572 and IRI-9113690. The author also thanks IBM Almaden Research Center which hosted him for 6 months.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
J.R. Bergen, P. Anandan, K. J. Hanna, and R. Hingorani. Hierarchical model-based motion estimation. In Proc. 2nd European Conference on Computer Vision, pages 237–252, 1992.
M. Campani and A. Verri. Motion analysis from optical flow. Computer Vision Graphics and Image Processing:Image Understanding, 56(12):90–107, 1992.
D. G. Jones and J. Malik. A computational framework for determining stereo correspondence from a set of linear spatial filters. In Proc. 2nd European Conference on Computer Vision, pages 395–410, 1992.
R. Manmatha. linage matching under affine deformations. In Invited Paper, Proc. of the 27nd Asilomar IEEE Conf. on Signals, Systems and Computers, 1993.
R. Manmatha and J. Oliensis. Measuring the affine transform — i: Scale and rotation. Technical Report Technical Report CMPSCI TR 92–74, University of Massachusetts at Amherst,MA, 1992. Also in Proc. of the Darpa Image Understanding Workshop 1993.
P. Werkhoven and J. J. Koenderinck. Extraction of motion parallax structure in the visual system 1. Biological Cybernetics, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Manmatha, R. (1994). Measuring the affine transform using gaussian filters. In: Eklundh, JO. (eds) Computer Vision — ECCV '94. ECCV 1994. Lecture Notes in Computer Science, vol 801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0028346
Download citation
DOI: https://doi.org/10.1007/BFb0028346
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57957-1
Online ISBN: 978-3-540-48400-4
eBook Packages: Springer Book Archive