Decoupling Fourier components of dynamic image sequences: A theory of signal separation, image segmentation, and optical flow estimation
This paper presents a new Fourier-based approach to the separation or decoupling of m additive images from a time-sequence of the sum of these images where at least m−1 images are translating with distinct and unique velocity. A closed-form solution is presented for the case where m=2. A generalization is then presented which extends the theory to embrace situations where the images are not additive but are, instead, formed by the superposition of an occluding object or objects on an occluded background. That is, the approach is generalized to effect a model-free segmentation of objects undergoing translatory fronto-parallel motion in dynamic image sequences. Object velocities of one pixel per frame are sufficient to guarantee segmentation.
We also show how the technique can be applied on a local basis to compute a dense instantaneous optical flow field for the image sequence, even in relatively featureless regions. The technique is evaluated using Otte's and Nagel's benchmark image sequence, for which ground-truth data is available, and results comparable with the ground-truth flow field are achieved. RMS errors of velocity magnitude and direction are computed and reported.
KeywordsSpatial Frequency Optical Flow Fourier Component Occlude Object Optical Flow Field
Unable to display preview. Download preview PDF.
- 1.D. Vernon, Machine Vision Prentice-Hall International, London (1991).Google Scholar
- 2.D. Vernon and G. Sandini, Parallel Computer Vision — The VIS a VIS System, Ellis Horwood, London (1992).Google Scholar
- 9.S.A. Rajala, A. N. Riddle, and W.E. Snyder, “Application of one-dimensional Fourier transform for tracking moving objects in noisy environments”, Computer Vision, Graphics, and Image Processing, 21, 280–293 (1983).Google Scholar
- 10.D. Vernon, “Phase-Based Measurement of Object Velocity in Image Sequences using the Hough Transform”, Optical Engineering (1996).Google Scholar
- 15.M. Otte and H.-H. Nagel, “Optical flow estimation: advances and comparisons”, Lecture Notes in Computer Science, J.O. Eklundh (Ed.), Computer Vision — ECCV '94, Springer-Verlag, Berlin, 51–60 (1994).Google Scholar
- 16.M. Tistarelli, “Multiple constraints for optical flow”, Lecture Notes in Computer Science, J.O. Eklundh (Ed.), Computer Vision — ECCV '94, Springer-Verlag, Berlin, 61–70 (1994).Google Scholar
- 17.L. Jacobson and H. Wechsler, “Derivation of optical flow using a spatiotemporal-frequency approach”, Computer Vision, Graphics, and Image Processing, 38, 29–65 (1987).Google Scholar
- 18.D. Vernon, “Decoupling Fourier Components of Dynamic Image Sequences: Theory and Application to Segmentation and Estimation of Optical Flow”, Technical Report, Department of Computer Science, National University of Ireland, Maynooth (1997).Google Scholar
- 19.D. Vernon, “Segmentation in Dynamic Image Sequences by Isolation of Coherent Wave Profiles”, Proceedings of the 4th European Conference on Computer Vision, Springer-Verlag, 293–303 (1996).Google Scholar
- 20.P.V.C. Hough, ‘Method and Means for Recognising Complex Patterns’ U.S. Patent 3,069,654, (1962).Google Scholar