An Algorithm for Optical Flow
The analysis of time-varying image sequences is a classical problem of machine vision (Aggarwal & Nandhakumar, 1988; Ullman, 1979), but is likely to be very useful in robotics, passive navigation and several other fields. Two major approaches have been proposed for the analysis of image sequences: one based on differential techniques aims at computing a dense optical flow, and the other recovers the displacement of selected tokens on the images, by tracking tokens from one image to the next one.
Unable to display preview. Download preview PDF.
- 1.Aggarwal, J.K. & Nandhakumar, N.: On the Computation of Motion from Sequences of Images — A Review. Proceedings of the IEEE, Vol. 76, No. 8, pp.917–935.Google Scholar
- 2.Ullmann, S.: The Interpretation of Visual Motion. MIT Press, Cambridge and London 1979.Google Scholar
- 3.Girosi, F., Verri, A., & Torre, V.: Constraints in the Computation of Optical Flow. Proceedings of the IEEE Workshop on Visual Motion, Irvine CA 1989.Google Scholar
- 4.Lanczos, C.: Linear Differential Operators. D. Van Nostrand Company, London 1961.Google Scholar
- 5.Verri, A., Girosi, F. & Torre, V.: Mathematical Properties of the 2D Motion Fields: from Singular Points to Motion Parameters. Proceedings of the IEEE Workshop on Visual Motion, Irvine CA 1989.Google Scholar