This Article 
 Bibliographic References 
 Add to: 
A System Design/Scheduling Strategy for Parallel Image Processing
February 1990 (vol. 12 no. 2)
pp. 194-204

A system design/scheduling strategy is described for a real-time parallel image processing system. A parallel image processing model based on the spatial and temporal parallelisms extractable in image processing tasks is formulated. This model consists of linear pipeline stages, each of which is a multiprocessing module. The strategy is discussed for two cases: static and dynamic. The description of the detailed hardware structure of each module is not attempted because of its dependency on a specific task. In the static case, where the processing time is constant, the processing times of all the stages are adjusted to be identical. In the dynamic case, where the processing time varies with each image, the strategy needs to be modified to achieve the maximum possible processing speed. The strategy is demonstrated for the static case by implementing image processing tasks on two different multiprocessor systems.

[1] S. Yalamanchili, K. V. Palem, L. S. Davis, A. J. Welch, and J. K. Aggarwal, "Image processing architectures: A taxonomy and survey," inProgress in Pattern Recognition, Vol. II. Amsterdam: North-Holland, 1985, pp. 1-37.
[2] M. J. B. Duff, "Review of the CLIP image processing system," inProc. Nat. Comput Conf., 1978, pp. 1055-1060.
[3] K. E. Batcher, "Design of a massively parallel processor,"IEEE Trans. Comput., vol. C-29, pp. 836-840, 1980.
[4] K. Luetjen, P. Gummar, and H. Ischen, "FLIP: A flexible multiprocessor system for image processing," inProc. 5th Int. Conf. Pattern Recognition, Miami Beach, FL, Dec. 1980, pp. 326-328.
[5] P. Narendra, "VLSI architectures for real time processing," inProc. COMPCON, Spring 1981, pp. 303-306.
[6] S. R. Sternberg, "Architectures for neighborhood processing," inProc. Pattern Recognition Image Processing Conf., Dallas, TX, Aug. 1981, pp. 374-380.
[7] D. Antonssonet al., "PICAP--A system approach to image processing," inProc. Workshop Picture Data Description and Management, Hot Springs, VA, Nov. 1981, pp. 295-299.
[8] S.-Y. Lee and J. K. Aggarwal, "A problem-driven approach to parallel image processing: System design and scheduling," inProc. IEEE Int. Conf. Syst., Man, Cybern., Tucson, AZ, Nov. 1985, pp. 680- 686.
[9] C. Mead and L. Conway,Introduction to VLSI Systems. Reading, MA: Addison-Wesley, 1980, pp. 150-152.
[10] H. T. Kung and J. A. Webb, "Mapping image processing operations onto a linear systolic machine,"Distributed Comput., pp. 246-257, 1986.
[11] G. Verghese, S. Metha, and C. R. Dyer, "Image processing algorithms for the pipelined image-processing engine," Comput. Sci. Tech. Rep. 668, Univ. Wisconsin, Madison, Sept. 1986.
[12] K. Hwang, Ed., Special Issue on Computer Architectures for Image Processing,IEEE Comput., vol. 16, Jan. 1983.
[13] S. Y. Lee, S. Yalamanchili, and K. Aggarwal, "Parallel image normalization on a mesh connected array processor,"Patt. Recogn., vol. 20, pp. 115-124, 1987.
[14] J. K. Aggarwal, L. S. Davis, and W. N. Martin, "Correspondence processes in dynamic scene analysis,"Proc. IEEE, vol. 69, pp. 562- 572, May 1981.
[15] S.-Y. Lee and J. K. Aggarwal, "Parallel 2-D convolution on a mesh connected array processor,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, pp. 590-594, July 1987.
[16] L. Kleinrock,Queueing Systems, Vol. I. New York: Wiley Interscience, 1975.
[17] C. H. Sauer and K. M. Chandy,Computer Systems Performance Modeling. Englewood Cliffs, NJ: Prentice-Hall, 1981.
[18] S. C. Bruell and G. Balbo,Computational Algorithms for Closed Queueing Networks. Amsterdam: North-Holland.
[19] H. D. Friedman, "Reduction methods for tandem queueing systems,"Oper. Res., pp. 121-131, 1965.
[20] R. R. P. Jackson, "Random queueing processes with phase-type service,"J. Roy. Statist. Soc., ser. B, pp. 129-132, 1956.
[21] E. Reich, "Waiting times when queues are in tandem,"Ann. Math. Statist., pp. 768-773, 1957.
[22] J. R. Jackson, "Networks of waiting lines,"Oper. Res., pp. 518- 521, 1957.
[23] G. C. Hunt, "Sequential array of waiting lines,"Oper. Res., pp. 674-683, 1956.
[24] F. S. Hiller and R. W. Boling, "Finite queues in series with exponential or Erlangen service times--A numerical approach,"Oper. Res., pp. 287-303, 1966.
[25] T. Makino, "On the mean passage time concerning some queueing problems of the tandem type,"J. Oper. Res. Japan, vol. 7, pp. 14- 47, Oct. 1964.
[26] B. Avi-Itzhak and M. Yadin, "A survey of two servers with no intermediate queue,"Management Sci., vol. 11, pp. 553-564, Mar. 1965.
[27] A. G. Konheim and M. Reiser, "A queueing model with finite waiting room and blocking,"J. ACM, vol. 23, pp. 328-341, Apr. 1976.
[28] S.-Y. Lee and J. K. Aggarwal, "Exploitation of image parallelism via the hypercube," inProc. 2nd Conf. Hypercube Multiprocessors, Knoxville, TN, Sept. 1986, pp. 426-437.
[29] J. F. Shoch, Y. K. Dalal, D. D. Redell, and R. C. Crane, "Evolution of the Ethernet local computer network,"IEEE Comput., pp. 10-27, Aug. 1982.
[30] W. Stallings,Local Networks. New York: Macmillan, 1984.
[31] R. C. Gonzalez and P. Wintz,Digital Image Processing. Reading, MA: Addison-Wesley, 1977.

Index Terms:
computerised picture processing; system design/scheduling strategy; parallel image processing; real-time; linear pipeline; multiprocessor systems; computerised picture processing; parallel processing; real-time systems; scheduling
S.Y. Lee, J.K. Aggarwal, "A System Design/Scheduling Strategy for Parallel Image Processing," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 2, pp. 194-204, Feb. 1990, doi:10.1109/34.44405
Usage of this product signifies your acceptance of the Terms of Use.