This Article 
 Bibliographic References 
 Add to: 
A Three-Frame Algorithm for Estimating Two-Component Image Motion
September 1992 (vol. 14 no. 9)
pp. 886-896

A fundamental assumption made in formulating optical-flow algorithms, that motion at any point in an image can be represented as a single pattern component undergoing a simple translation, fails for a number of situations that commonly occur in real-world images. An alternative formulation of the local motion assumption in which there may be two distinct patterns undergoing coherent (e.g. affine) motion within a given local analysis region is proposed. An algorithm for the analysis of two-component motion in which tracking and nulling mechanisms applied to three consecutive image frames separate and estimate the individual components is given. Precise results are obtained, even for components that differ only slightly in velocity as well as for a faint component in the presence of a dominant, masking component. The algorithm provides precise motion estimates for a set of elementary two-motion configurations and is robust in the presence of noise.

[1] G. Adiv, "Determining three-dimensional motion andstructure from optical flow generated by several moving objects,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-7, no. 4, pp. 384-401, July 1985.
[2] P. Anandan, "A unified perspective on computational techniques for the measurement of visual motion," inProc. Int. Conf Comput. Vision(London), May 1987, pp. 219-230.
[3] J. R. Bergen and E. H. Adelson, "Hierarchical, computationally efficient motion estimation algorithm,"J. Opt. Soc. Amer. A., vol. 4, p. 35, 1987.
[4] P. J. Burt, "Fast filter transforms for image processing,"Comput. Graphics Image Processing, vol. 16, pp. 20-51, 1981.
[5] P. J. Burtet al., "Object tracking with a moving camera, An application of dynamic motion analysis," inProc. IEEE Workshop Visual Motion(Irvine, CA), Mar. 1989, pp. 2-12.
[6] P. J. Burt, C. Yen, and X. Xu, "Multi-resolution flow-through motion analysis," inProc. IEEE Conf. Comput. Vision Patt. Recogn.(Washington, DC), June 1983, pp. 246-252.
[7] C. L. Fennema and W. B. Thompson, "Velocity determination in scenes containing several moving objects,"Comput. Graphics Image Processing, vol. 9, pp. 301-315, 1979.
[8] S. Geman and D. Geman, "Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-6, pp. 721-741, Nov. 1984.
[9] B. Girod and D. Kuo, "Direct estimation of displacement histograms," inProc. Image Understanding Machine Vision Opt. Soc. Amer.(Cape Cod), June 1989, pp. 73-76.
[10] D. J. Heeger, "Optical flow using spatiotemporal filters,"Int. J. Comput. Vision, vol. 1, pp. 279-302, 1988.
[11] E. Hildreth,The Measurement of Visual Motion, Cambridge, MA: MIT Press, 1983.
[12] B. K. P. Horn,Robot Vision. Cambridge, MA: M.I.T. Press, 1986.
[13] B. K. P. Horn and B. G. Schunck, "Determining optical flow,"Artificial Intell., vol. 17, pp. 185-203, 1981.
[14] B. K. P. Horn and E. J. Weldon, "Direct methods for recovering motion,"Int. J. Comput. Vision, vol. 2, no. 1, pp. 51-76, June 1988.
[15] D. Keren, S. Peleg, and R. Brada, "Image sequence enhancement using sub-pixel displacements," inProc. IEEE Conf. Comput. Vision Patt. Recogn.(Ann Arbor, MI), pp. 742-746, June 1988.
[16] J. O. Limb and J. A. Murphy, "Estimating the velocity of moving images in television signals,"Comput. Graphics Image Processing, vol. 4, no. 4, pp. 311-327, Dec. 1975.
[17] B. D. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," inProc. Image Understanding Workshop, 1981, pp. 121-130.
[18] D. W. Murray and B. F. Buxton, "Scene segmentation from visual motion using global optimization,"IEEE Trans. Patt. Analy. Machine Intell., vol. PAMI-9, pp. 161-180, 1987.
[19] T. Pavlidis,Structural Pattern Recognition. New York: Springer, 1977.
[20] S. Pele and H. Rom, "Motion based segmentation," inProc. Int. Conf. Patt. Recogn.(Atlantic City, NJ), June 1990, pp. 109-113.
[21] M. Shizawa and K. Mase, "Simultaneous multiple optical flow estimation," inProc. Int. Conf. Patt. Recogn. (Atlantic City, NJ), June 1990, pp. 274-278.

Index Terms:
two component image motion estimation; picture processing; pattern recognition; three-frame algorithm; optical-flow algorithms; tracking; nulling mechanisms; optical information processing; pattern recognition; picture processing
J.R. Bergen, P.J. Burt, R. Hingorani, S. Peleg, "A Three-Frame Algorithm for Estimating Two-Component Image Motion," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 9, pp. 886-896, Sept. 1992, doi:10.1109/34.161348
Usage of this product signifies your acceptance of the Terms of Use.