Vol. 11, No. 4 (November 1998) 181-190   

downloaded Downloaded: 50   viewed Viewed: 1548

S. Negahdaripour

Department of ECE
University of Miami
A. Shokrollahi
Inter Systems Corporation

Abstract    Accurate estimation of motion from time-varying imagery has been a popular problem in vision studies, This information can be used in segmentation, 3D motion and shape recovery, target tracking, and other problems in scene analysis and interpretation. We have presented a dynamic image model for estimating image motion from image sequences, and have shown how the solution can be obtained from a set of partial differential equations. In this paper, we have investigated a relaxation type algorithm for obtaining a numerical solution to these equations, and considered the implementation of the algorithm on a variation of the general pipeline interconnection scheme using transputers. This architecture is compared against two others based on flexibility and efficiency. It is observed that with respect to computation, a mesh connected architecture has advantages over the proposed pipeline scheme. However, the pipeline configuration is easily expandable and more robust to changes in the algorithms parameters and image size.


Keywords    Vision. Image Motion, Optical Flow, Pipeline, Mesh



1. Negahdaripour, S. and Jain, A. K., "Finite Report of the NFS Workshop on Grand Challenges in Computer Vision, Future Research Direction in Computer Vision, (November.1991).
2. Prasanna-Kumar, V. K. and Reisis, D., "Parallel Architectures for Image Processing and Vision"; Proc. DARPA Image Understanding Workshop, (April 1988).
3. Duin, R. P. W. and Jonker, P. P., "Processor Arrays Compared to Pipelines for Cellular Image Operations," Multicomputer Vision, S. Levidaldi (ed.), Academic Press, (1988).
4. Van, H. Helmohltz, "Helmohltz's Traetsie on Physiological Optics"; Journal Optical Society of America, Southall, J. P., (1925).
5. Bron, J. L., Fleet, D. J., Beauchemin, S. S. and Burkitt, T. A., "Performance of Optical Flow Techniques," TR-299, Dept. Comp. Science, University of Western Ontario, (March.1993).
6. Horn, B. K. P. and Schunk, B. G., "Determining Optical Flow," Artificial Intelligence, Vol. 17, (1981).
7. Negahdaripour, S., Shokrollahi, A. and Gennert, M., "Relaxing the Brightness Constancy Assumption in Computing Optical Flow"; Proc. Int. Conf. Image Processing, Singapore, (September.1989).
8. Negahdaripour, S. and Yu, C. H., "A Generalized Brightness Change Model for Computing Optical Flow"; Proc. 4th International Conference on Computer Vision, Berlin, Germany, (May.1993).
9. Shokrollahi, A., "Computing Optical Flow,A Parallel Implementation for Transputers", M. S. Thesis, Department of Electrical Engineering, University of Hawaii, (December.1990).
10. Terzopoulos, D., "Image Analysis Using Multigrid Relaxation Methods"; IEEE Trans. PAMI, Vol. 8, No 2, (March.1986).
11. Bruss, A. R. and Horn, B. K. P., "Passive Navigation," CVIGIP, Vol. 21, No. 1, (January.1983).

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir