Voting Method for Stable Range Optical Flow Computation
For the non-invasive imaging of moving organs, in this paper, we develop statistically accurate methods for the computation of optical flow. We formalise the linear flow field detection as a model-fitting problem which is solved by the least squares method. Then, we show random-ssampling-and-voting method for the computation of optical flow as model-fitting problem. We show some numerical examples which shows the performance of our method.
KeywordsOptical Flow Spatial Gradient Structure Tensor Range Image Angle Error
Unable to display preview. Download preview PDF.
- 1.Song, S.M., Leathy, R.M.: Computation of 3-D verocity fields from 3-D cine CT images of a human heart. IEEE, Tr. Medical Imaging 10, 285–306 (1991)Google Scholar
- 3.Kälviäinen, H., Oja, E., Xu, L.: Randomized Hough transform applied to translation and rotation motion analysis. In: 11th IAPR Proceedings of International Conference on Pattern Recognition, pp. 672–675 (1992)Google Scholar
- 5.Oja, E., Xu, L., Kultanen, P.: Curve detection by an extended self-organization map and related RHT method. In: Proc. International Neural Network Conference, vol. 1, pp. 27–30 (1990)Google Scholar