Abstract
A new method for optical flow computation by means of a coupled set of non-linear diffusion equations is presented. This approach integrates the classical differential approach with the correlation type of motion detectors. A measure of inconsistency within the optical flow field which indicates optical flow boundaries. This information is fed back to the optical flow equations in a non-linear way and allows the flow field to be reconstructed while preserving the discontinuities. The whole scheme is also applicable to stereo matching. The model is applied to a set of synthetic and real image sequences to illustrate the behaviour of the coupled diffusion equations.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Aisbett J.: Optical flow with an intensity-weighted smoothing. IEEE Transactions on PAMI. 11.5 (1989) 512–522
Barron J.L., Fleet D.J., Beauchemin S.S., and Burkitt T.A.: Performance of optical flow techniques. IEEE Proceedings of CVPR, Illinois. (1992) 236–242
Campani M. and Verri A.: Computing Optical Flow from an Overconstrained Sytem of Linear Algebraic Equations. Proc. Third Int. Conf. on Comp. Vision. Osaka, Japan. (1990) 22–26.
Cohen I.: Nonlinear Variational Method for Optical flow computation. Proc. of the 8th Scandinavian Conf. on Image Analysis. 1 (1993) 523–530
Horn B.K.P. and Schunck G.: Determining optical flow. Artificial Intelligence. 17 (1981) 185–203
Nagel H.H. and Enkelmann W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequence. IEEE Transactions on PAMI. 8.5 (1986) 565–593
Nagel H.H.: Displacement Vectors Derived from Second-Order Intensity Variations in Image Sequences. Comp. Vision, Graphics, and Image Proc. 21 (1983) 85–117
Negahdaripour S. and Yu C.: A generalized Brightness Change Model for Computing Optical Flow. 4th Int. Conf. on Comp. Vision. (1993) 2–11
Perona P. and J. Malik J.: Scale-Space and Edge Detection Using Anisotropic Diffusion. IEEE Transactions on PAMI. 12.7 (1990)
Pauwels E.J., Proesmans M., Van Gool L.J., T. Moons and Oosterlinck A.: Image Enhancement using coupled anisotropic diffusion equations. Proc. on the 11th European Conf. on circuit theory and design, 2 (1993) 1459–1464
Reichardt W.E. and Poggio T.: Figure-ground discrimination by relative movement in the visual system of the fly. Part I: Experimental results. Biological Cybernetics. 35 (1980) 81–100
Shah J.: Segmentation by non-linear diffusion. Proc. IEEE CVPR Hawai (1991)
Shah J.: (1993) A Nonlinear Diffusion Model for Discontinuous Disparity and Half-Occlusion in Stereo. Proc. IEEE CVPR NY (1993)
Weber J. and J. Malik J.: Robust Computation of Optical Flow in a Multi-Scale Differential Framework. 4th Int. Conf. on Comp. Vision. (1993) 12–20
Willick D. and Yang Y.: Experimental Evaluation of Motion Constraint Equations. CVGIP: Image Understanding. 54.2 (1991) 206–214
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Proesmans, M., Van Gool, L., Pauwels, E., Oosterlinck, A. (1994). Determination of optical flow and its discontinuities using non-linear diffusion. In: Eklundh, JO. (eds) Computer Vision — ECCV '94. ECCV 1994. Lecture Notes in Computer Science, vol 801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0028362
Download citation
DOI: https://doi.org/10.1007/BFb0028362
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57957-1
Online ISBN: 978-3-540-48400-4
eBook Packages: Springer Book Archive