This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Algorithmic Techniques for Computer Vision on a Fine-Grained Parallel Machine
March 1989 (vol. 11 no. 3)
pp. 244-257

The authors describe several fundamentally useful primitive operations and routines and illustrate their usefulness in a wide range of familiar version processes. These operations are described in terms of a vector machine model of parallel computation. They use a parallel vector model because vector models can be mapped onto a wide range of architectures. They also describe implementing these primitives on a particular fine-grained machine, the connection machine. It is found that these primitives are applicable in a variety of vision tasks. Grid permutations are useful in many early vision algorithms, such as Gaussian convolution, edge detection, motion, and stereo computation. Scan primitives facilitate simple, efficient solutions of many problems in middle- and high-level vision. Pointer jumping, using permutation operations, permits construction of extended image structures in logarithmic time. Methods such as outer products, which rely on a variety of primitives, play an important role of many high-level algorithms.

[1] A. Aggarwal, B. Chazelle, L. Guibas, C. O'Dunlaing, and C. Yap, "Parallel computational geometry," inProc. Symp. Found. Comp. Sci., Oct. 1985, pp. 468-477.
[2] M. J. Atallah, R. Cole, and M. T. Goodrich, "Cascading divide-and-conquer: A technique for designing parallel algorithms," inProc. Symp. Found. Comp. Sci., Oct. 1987, pp. 151-160.
[3] M. J. Atallah and M. T. Goodrich, "Efficient parallel solutions to geometric problems," inProc. Int. Conf. Parallel Process., 1985, pp. 411-417.
[4] W. C. Athas and C. L. Seitz, "Multicomputers: Message passing concurrent computers,"IEEE Comput., pp. 9-24, Aug. 1988.
[5] G. E. Blelloch, "Scans as primitive parallel operations," inProc. Int. Conf. Parallel Process., Aug. 1987, pp. 355-362.
[6] G. E. Blelloch, "Scans primitives and parallel vector models," Ph.D. dissertation, Art. Intell. Lab., Massachusetts Inst. Technol., Cambridge, MA, Oct. 1988.
[7] G. E. Blelloch and J. J. Little, "Parallel solutions to geometric problems on the scan model of computation," inProc. Int. Conf. Parallel Process., 1988, pp. 218-222.
[8] J. F. Canny, "A computational approach to edge detection,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, pp. 679-697, 1986.
[9] T. A. Cass, "Parallel computation in model-based recognition," Master's thesis, Massachusetts Inst. Technol., Cambridge, MA, June 1988.
[10] D. T. Clemens, "The recognition of two-dimensional modeled objects in images," Master's thesis, Massachusetts Inst. Technol., Cambridge, MA, 1986.
[11] T. M. Corporation, "*Lisp reference manual," Thinking Machines Corporation, Cambridge, MA, Tech. Rep., 1987.
[12] R. Cypher, J. L. C. Sanz, and L. Synder, "EREW PRAM and mesh connected computer algorithms for image component labeling," inProc. 1987 Workshop Comp. Arch. Pattern Anal. Machine Intell., Oct. 1987, pp. 122-128.
[13] R. Cypher, J. L. C. Sanz, and L. Synder, "Hypercube and shuffle-exchange algorithms for image component labeling," inProc. 1987 Workshop Comp. Arch. Pattern Anal. Machine Intell., Oct. 1987, pp. 5-10.
[14] R.O. Duda and P.E. Hart, "Use of the Hough transformation to detect lines and curves in pictures,"Commun. Ass. Comput. Mach., vol. 15, no. 1, pp. 11-15, Jan. 1972.
[15] S. Fortune and J. Wyllie, "Parallelism in random access machines," inProc. 10th Annu. ACM Symp. Theory Comput., 1978, pp. 114-118.
[16] W. Gillett, J. J. Little, P. Oppenheimer, and T. Poggio, "Learning stereo calibration," Art. Intell. Lab., Massachusetts Inst. Technol., Tech. Rep., in progress.
[17] A. Gottlieb, B. D. Lubachevsky, and L. Rudolph, "Basic techniques for the efficient coordination of very large numbers of cooperating sequential processors,"ACM Trans. Programming Languages Syst., vol. 5, no. 2, pp. 164-189, Apr. 1993.
[18] W. E. L. Grimson and T. Lozano-Perez, "Model-based recognition and localization from sparse range or tactile data,"Int. J. Robot. Res., vol. 3, no. 3, pp. 3-35, 1984.
[19] W. D. Hillis,The Connection Machine. Cambridge, MA: MIT Press, 1985.
[20] W. D. Hillis and G. L. Steele, Jr., "Data parallel algorithms,"Commun. ACM, vol. 29, no. 12, pp. 1170-1183, Dec. 1986.
[21] R. Hummel, "Connected component labelling in image processing with MIMD architectures," inIntermediate-Level Image Processing. New York: Academic, 1986, pp. 101-127.
[22] C. Jeong and D. Lee, "Parallel geometric algorithms on a mesh connected computer," Northwestern Univ., Tech. Rep. 87-02-FC-01, 1987.
[23] C. P. Kruskal, L. Rudolph, and M. Snir, "The power of parallel prefix," inProc. Int. Conf. Parallel Process., Aug. 1985, pp. 180- 185.
[24] R. E. Ladner and M. J. Fischer, "Parallel prefix computation,"J. ACM, vol. 27, no. 4, pp. 831-838, Oct. 1980.
[25] D. T. Lee, "Two dimensional Voronoi diagram in theLp-metric,"J. ACM, vol. 27, no. 4, pp. 604-618, Oct. 1980.
[26] D. T. Lee and C. Wong, "Voronoi diagrams in L1(L∞) metrics with 2-dimensional storage applications,"SIAM J. Camp., vol. 9, no. 1, pp. 200-211, Feb. 1980.
[27] W. Lim, A. Agrawal, and L. Nekludova, "A fast parallel algorithm for labeling connected components in image arrays," Thinking Machines Corporation, Tech. Rep. NA86-2, Dec. 1986.
[28] J. J. Little, "Automatic registration of Landsat MSS images to digital elevation models," inProc. Workshop Comput. Vision: Represent. Cont., Rindge, NH, Aug. 1982, pp. 178-184.
[29] J. J. Little, "Parallel algorithms for computer vision on the Connection Machine." Art. Intell. Lab., Massachusetts Inst. Technol., A.I. Memo 928, 1986.
[30] D. Marr and E. Hildreth, "Theory of edge detection,"Proc. Royal Soc., London, England, vol. B(207). pp. 187-217, 1980.
[31] R. Miller and Q. Stout, "Geometric algorithms for digitized pictures on a mesh-connected computer,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-7, pp. 216-228, Mar. 1985.
[32] R. Miller and Q. F. Stout, "Data movement techniques for the pyramid computer,"SIAM J. Comput., vol. 16, pp. 38-60, 1987.
[33] D. Nassimi and S. Sahni, "Finding connected components and connected ones on a mesh-connected parallel computer,"SIAM J. Comp., vol. 9, no. 4, pp. 744-757, Nov. 1980.
[34] A. V. Oppenheim and R. W. Schafer,Digital Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1975.
[35] T. Poggio, V. Torre, and C. Koch, "Computational vision and regularization theory,"Nature, vol. 317, pp. 314-319, 1985.
[36] F. P. Preparata and M. I. Shamos,Computational Geometry, an Introduction. New York: Springer-Verlag, 1985.
[37] Y. Shiloach and U. Vishkin, "AnO(logn) parallel connectivity algorithm,"J. Algorithms, vol. 3, pp. 57-67, 1982.
[38] G. Stockman, S. Kopstein, and S. Bennet, "Matching images to models for registration and object detection via clustering,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-4, May 1982.
[39] H. Voorhees and T. Poggio, "Detecting textons and texture boundaries in natural images," inProc. Int. Conf. Comput. Vision, London, England, June 1987; also IEEE, Washington, DC, pp. 250-258.
[40] J. C. Wyllie, "The complexity of parallel computation," TR 79-387, Dep. Comput. Sci., Cornell Univ., Ithaca, NY, 1979.

Index Terms:
parallel algorithm; parallel architectures; grid permutation; pointer jumping; computer vision; fine-grained parallel machine; primitive operations; vector machine model; Gaussian convolution; edge detection; stereo; image structures; computer vision; computerised picture processing; parallel algorithms; parallel architectures; parallel machines
Citation:
J.J. Little, G.E. Blelloch, T.A. Cass, "Algorithmic Techniques for Computer Vision on a Fine-Grained Parallel Machine," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 3, pp. 244-257, March 1989, doi:10.1109/34.21793
Usage of this product signifies your acceptance of the Terms of Use.