Discrete wavelet analysis: A new framework for fast optic flow computation
This paper describes a new way to compute the optical flow based on a discrete wavelet basis analysis. This approach has thus a low complexity (O(N) if one image of the sequence has N pixels) and opens the way to efficient and unexpensive optical flow computation. Features of this algorithm include multiscale treatment of time aliasing and estimation of illumination changes.
KeywordsAnalytic wavelets Image compression Optic flow Illumination Discrete wavelets
Unable to display preview. Download preview PDF.
- 1.E. H. Adelson and J. R. Bergen, “Spatiotemporal Energy Models for the Perception of Vision,” J. Opt. Soc. Amer., Vol A2, pp. 284–299, 1985.Google Scholar
- 6.C.W.G. Clifford, K. Langley and D.J. Fleet, “Centre-Frequency Adaptive IIR Temporal Filters for Phase-Based Image Velocity Estimation,” Image Processing and its Applications, Vol. 4–6, pp. 173–177, 1995.Google Scholar
- 11.M. Gökstorp and P-E. Danielsson, “Velocity Tuned Generalized Sobel Operators for Multiresolution Computation of Optical Flow,” IEEE, pp. 765–769, 1994.Google Scholar
- 13.B.K.P Horn and B.G. Schunck, “Determining Optical Flow,” A.I. Memo No. 572, Massachusetts Institute of Technology, 1980.Google Scholar
- 15.B. JÄhne, “Spatio-Temporal Image Processing,” Lecture Notes in Computer Science vol. 751, Springer Verlag, 1993.Google Scholar
- 16.B. D. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,” Proc. DARPA Image Understanding Workshop, pp. 121–130, 1981.Google Scholar
- 18.E.P. Simoncelli, W.T. Freeman, “The Steerable Pyramid: a Flexible Architecture for Multi-Scale Derivative Computation,” 2nd Annual IEEE International Conference on Image Processing, Washington DC, 1995.Google Scholar
- 19.A.B. Watson, “The Cortex Transform: Rapid Computation of Simulated Neural Images,” Computer Vision, Graphics, and Image Processing, Vol. 39:3, pp. 311–327, 1987.Google Scholar