Parallel Optical Flow Using Local Voting
- 1 December 1988
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 454-459
- https://doi.org/10.1109/ccv.1988.590023
Abstract
We describe a parallel algorithm for computing optical flow from short-range motion. Regularizing optical flow computation leads to a forruulation which minimizes matching error and, at the same time, maximises smoothness of the optical flow. We develop an approximation to the full regularization computation in which corresponding points are found by comparing local patches of the images. Selection aniong competing matches is performed using a winner-take-all scheme. The algorithm accommodates many different image transformations uniformly, with siniilar results, from brightness to edges. The optical flow computed froni different image transformations, such as edge detection and direct brightness computation, can be simply combined. The algorithm is easily implemented using local operations on a finegrained computer, and has been implemented on a Connection Machine. Experiments with natural images show that the scheme is effective and robust against noise. The algorithm leads to dense optical flow fields ; in addition, inforniation from matching facilitates segmentationKeywords
This publication has 19 references indexed in Scilit:
- Algorithmic techniques for computer vision on a fine-grained parallel machinePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- A computational approach to motion perceptionBiological Cybernetics, 1988
- A computational theory for the perception of coherent visual motionNature, 1988
- Computing motion using analog and binary resistive networksComputer, 1988
- Optical Flow Estimation: An Error Analysis of Gradient-Based Methods with Local OptimizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- An alternative technique for the computation of the designator in the retinex theory of color vision.Proceedings of the National Academy of Sciences, 1986
- On parallel stereoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Displacement vectors derived from second-order intensity variations in image sequencesComputer Vision, Graphics, and Image Processing, 1983
- Determining optical flowArtificial Intelligence, 1981
- Directional selectivity and its use in early visual processingProceedings of the Royal Society of London. B. Biological Sciences, 1981