Pattern Recognition and Image Processing in Physics, NATO Advanced Study Institute, Proceedings of the Thirty-Seventh Scottish Universities Summer School in Physics, Dundee, United Kingdom, July 29-August 18, 1990, R.A. Vaughan, Ed., Adam Hilger, Bristol, pp. 129-166.
The topic of this paper is the automatic analysis of motion by machines. The goal is to present some of the techniques used to solve the problem of motion detection and measurement. After a short introduction, the concept of the optical flow field is defined. Some ways to compute it are shown. First the author considers two domains of transformation (Fourier and Hadamard), and shows how to pass from these domains to motion estimation. Then a method based on intensity gradients is presented which allows the computation of a dense optical flow field. Unfortunately, this optical flow field is not fully specified and needs some assumptions for its full recovery; some possible assumptions are discussed. The next method is based on token correspondences between two images, and produces a sparse optical flow field. The determination of this flow field is complete, but the problems encountered in establishing the correspondences are similar to the problems found in stereo vision.
BOOKTITLE="Pattern Recognition and Image Processing in Physics",
series="NATO Advanced Study Institute",
month="July 29-August 18,",
note="Proceedings of the Thirty-Seventh Scottish Universities Summer
School in Physics, Dundee, United Kingdom")
Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.