The GIOTTO System: a Parallel Computer for Image Processing

This paper presents the GIOTTO system, a parallel computer based on a scalable single instruction, multiple data (SIMD) array of processors specially conceived for image processing. The system is characterized by a reduced-size array and a novel organization of the memory subsystem, designed to support transparent processing of images larger than the array. The system is designed to meet the computational requirements of machine vision, together with the compactness, ease of integration and flexibility called for by industrial robotic environments. The paper describes the system architecture in detail, focussing on original solutions conceived to endow the system with flexibility and performance. As proof of GIOTTO's suitability for robotic application, its use in a robot vision experiment is presented, showing the approach to the vision problem, the parallel algorithms, and performance analysis.

[1]  Jake K. Aggarwal,et al.  A Sliding Memory Plane Array Processor , 1993, IEEE Trans. Parallel Distributed Syst..

[2]  Mounir Hamdi,et al.  Parallel Image Processing Applications on a Network of Workstations , 1995, Parallel Comput..

[3]  John R. Nickolls,et al.  The design of the MasPar MP-1: a cost effective massively parallel computer , 1990, Digest of Papers Compcon Spring '90. Thirty-Fifth IEEE Computer Society International Conference on Intellectual Leverage.

[4]  Kenneth E. Batcher,et al.  Design of a Massively Parallel Processor , 1980, IEEE Transactions on Computers.

[5]  Sartaj Sahni,et al.  Image Template Matching on MIMD Hypercube Multicomputers , 1990, J. Parallel Distributed Comput..

[6]  Rita Cucchiara,et al.  Detection of Circular Objects by Wave Propagation on a Mesh-Connected Computer , 1995, J. Parallel Distributed Comput..

[7]  L. Di Stefano,et al.  A parallel vision subsystem for robotic inspection and manipulation , 1994, Proceedings of IECON'94 - 20th Annual Conference of IEEE Industrial Electronics.

[8]  Azriel Rosenfeld,et al.  Hough transform algorithms for mesh-connected SIMD parallel processors , 1988, Comput. Vis. Graph. Image Process..

[9]  K. T. Lua,et al.  A preliminary evaluation of a massively parallel processor: GAPP , 1990 .

[10]  T. J. Fountain,et al.  Processor Arrays: Architecture and Applications , 1987 .

[11]  J. Strikwerda.  Finite Difference Schemes and Partial Differential Equations , 1989 .

[12]  S. F. Reddaway.  DAP—a distributed array processor , 1973, ISCA 1973.

[13]  Howard Jay Siegel,et al.  Mapping computer-vision-related tasks onto reconfigurable parallel-processing systems , 1992, Computer.

[14]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[15]  S. S. Wilson,et al.  The AIS-5000 Parallel Processor , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Virginio Cantoni,et al.  Multiprocessor computing for images , 1988, Proc. IEEE.

[17]  Edward W. Davis,et al.  BLITZEN: a highly integrated massively parallel machine , 1988, Proceedings., 2nd Symposium on the Frontiers of Massively Parallel Computation.

[18]  Rita Cucchiara,et al.  Reconfiguring the boundaries of a mesh-connected array of processors with run-time programmable logic , 1993, Microprocess. Microsystems.