A fundamental assumption made in formulating optical flow algorithms is that motion at any point in an image can be represented as a single pattern component undergoing a simple translation: even complex motion will ‘look like’ uniform displacement when viewed through a sufficiently small window. This assumption fails for a number of situations that commonly occur in real world images. For example, transparent surfaces moving past one another yield multiple motion components at a point.
We propose an alternative formulation of the local motion assumption in which there may be two distinct patterns undergoing different motions within a given local analysis region. We then present an algorithm for the analysis of transparent motion.
KeywordsOptical Flow Multiple Motion Real World Image Pattern Component Optical Flow Computation
- P. Anandan. A unified perspective on computational techniques for the measurement of visual motion. In International Conference on Computer Vision, pages 219–230, London, May 1987.Google Scholar
- J.R. Bergen and E.H. Adelson. Hierarchical, computationally efficient motion estimation algorithm. J. Opt. Soc. Am. A., 4:35, 1987.Google Scholar
- J.R. Bergen, P.J. Burt, R. Hingorani, and S. Peleg. Multiple component motion: Motion estimation. Technical report, David Sarnoff Research Center, January 1990.Google Scholar
- C.L. Fennema and W.B. Thompson. Velocity determination in scenes containing several moving objects. Computer Graphics and Image Processing, 9:301–315, 1979.Google Scholar
- B. Girod and D. Kuo. Direct estimation of displacement histograms. In Image Understanding and Machine Vision, pages 73–76, Cape Cod, June 1989. Optical Society Of America.Google Scholar
- D.J. Heeger. Optical flow using spatiotemporal filters. International Journal of Computer Vision, 1:279–302, 1988.Google Scholar
- B.K.P. Horn. Robot Vision. MIT Press, 1986.Google Scholar
- B.K.P. Horn and E.J. Weldon. Direct methods for recovering motion. International Journal of Computer Vision, 2(1):51–76, June 1988.Google Scholar
- J.O. Limb and J.A. Murphy. Estimating the velocity of moving images in television signals. Computer Graphics and Image Processing, 4(4):311–327, December 1975.Google Scholar