Abstract
Motion problems in which the scene motion largely conforms to a low order global motion model are called global motion problems, examples of which are stabilization, mosaicking and motion superresolution. In this paper, we propose a two-step solution for robustly estimating the global motion parameters that characterize global motion problems. Our primary contribution is an improved estimation algorithm for modeling the optical flow field of a sequence using overlapped basis functions. Moreover, we show that the parametrized flow estimates can be consolidated through an iterative process that estimates global deformation while ensuring robustness to systematic errors such as those caused by moving foreground objects or occlusion. We demonstrate the validity of our model and accuracy of the algorithm on synthetic and real data. Our technique is computationally efficient, and is ideally suited for the application areas discussed here, viz. stabilization, mosaicking and super-resolution.
The support of this research by the Defense Advanced Research Projects Agency (DARPA Order No. C635) and the Office of Naval Research under Contract N00014-95-1-0521 is gratefully acknowledged. We also thank the anonymous reviewers for their valuable comments and criticism.
Chapter PDF
References
G. Adiv, “Determining 3-D Motion and Structure from Optical Flow Generated by Several Moving Objects”, IEEE PAMI, vol. 7, no. 4, 1985.
M. S. Alam et. al., “High-resolution Infrared Image Reconstruction using Multiple Randomly Shifted Low-resolution Aliased Frames”, Proc. SPIE 3063, 1997.
P Anandan, “Measuring Visual Motion from Image Sequences”, Ph. D. dissertation, University of Massachusetts, Amherst, 1987.
P. Anandan et. al., “Real-time Scene Stabilization and Mosaic Construction”, ARPA Image Understanding Workshop, 1994.
O. Axelsson, Iterated Solution Methods, Cambridge University Press, 1994.
J. L. Barron, D. J. Fleet and S. S. Beauchemin, “Performance of Optical Flow Techniques”, Int. Jour. of Comp. Vision, vol. 12:1, pp. 43–77.
P. J. Burt and P. Anandan, “Image Stabilization by Registration to a Reference Mosaic”, ARPA Image Understanding Workshop, 1994.
D. J. Heeger, “Model for the Extraction of Image Flow”, Jour. Opt. Soc. Amer., vol. 4, pp. 1455–1471.
B. K. P. Horn and B. G. Schunck, “Determining Optical Flow”, Artificial Intelligence, vol. 17, pp. 185–204, 1981.
D. J. Fleet and A. D. Jepson, “Computation of Component Image Velocity from Local Phase Information”, Int. Jour. Comp. Vision, vol. 5, pp. 77–104.
N. Gupta and L. Kanal, “Recovering 3-D motion from a Motion Field”, Special Issue on Computer Vision, 1995.
S. V. Huffel and J. Vandewalle, The Total Least Squares Problem — Computational Aspects and Analysis, SIAM, 1991.
M. Irani and S. Peleg, “Improving Resolution by Image Registration”, Comp. Vision Graphics Image Proc., vol. 53, pp. 231–239.
H. Liu, “A General Motion Model and Spatio-Temporal Filters for 3-D Motion Interpretations”, Ph. D. dissertation, Univ. of Maryland, 1995.
B. D. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision”, Proc. DARPA IUW, 1991.
C. H. Morimoto and R. Chellappa, “Fast Electronic Digital Image Stabilization”, Proc. of IEEE ICPR, 1996.
H. H. Nagel, “On the Estimation of Optical Flow”, Artificial Intelligence, vol. 33, pp. 299–324, 1987.
S. Negahdaripour and B. K. P. Horn, “Direct Passive Navigation”, IEEE PAMI, vol. 9, no. 1, pp. 168–176, 1987.
W. H. Press et. al., Numerical Recipes in C (2 ed.), Cambridge University Press, 1992.
S. Rakshit and C. H. Anderson, “Computation of Optical Flow Using Basis Functions”, IEEE IP, vol. 6, no. 9, pp. 1246–1254, 1997.
A. Singh, “An Estimation-Theoretic Framework for Image-Flow Computation”, Proc. IEEE ICCV, 1990.
S. Srinivasan and R. Chellappa, “Robust Modeling and Estimation of Optical Flow with Overlapped Basis Functions”, CAR-TR-845, Univ. of Maryland, 1996.
R. Szeliski and J. Coughlan, “Spline-Based Image Registration”, DEC-TR-CRL-94/1, Cambridge Research Laboratory, 1994.
S. Uras et. al., “A Computational Approach to Motion Perception”, Biological Cybernetics, vol. 60, pp. 79–97, 1988.
Y. S. Yao, “Electronic Stabilization and Feature Tracking in Long Image Sequences”, Ph. D. dissertation CAR-TR-790, Univ. of Maryland, 1996.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Srinivasan, S., Chellappa, R. (1998). Optical flow using overlapped basis functions for solving global motion problems. In: Burkhardt, H., Neumann, B. (eds) Computer Vision — ECCV’98. ECCV 1998. Lecture Notes in Computer Science, vol 1407. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0054748
Download citation
DOI: https://doi.org/10.1007/BFb0054748
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64613-6
Online ISBN: 978-3-540-69235-5
eBook Packages: Springer Book Archive