A memory-array architecture for computer vision

Thesis/Dissertation · Sun Jan 01 04:00:00 EST 1989

OSTI ID:6223439

Balsara, P T

With the fast advances in the area of computer vision and robotics there is a growing need for machines that can understand images at a very high speed. A conventional von Neumann computer is not suited for this purpose because it takes a tremendous amount of time to solve most typical image processing problems. Exploiting the inherent parallelism present in various vision tasks can significantly reduce the processing time. Fortunately, parallelism is increasingly affordable as hardware gets cheaper. Thus it is now imperative to study computer vision in a parallel processing framework. The author should first design a computational structure which is well suited for a wide range of vision tasks and then develop parallel algorithms which can run efficiently on this structure. Recent advances in VLSI technology have led to several proposals for parallel architectures for computer vision. In this thesis he demonstrates that a memory array architecture with efficient local and global communication capabilities can be used for high speed execution of a wide range of computer vision tasks. This architecture, called the Access Constrained Memory Array Architecture (ACMAA), is efficient for VLSI implementation because of its modular structure, simple interconnect and limited global control. Several parallel vision algorithms have been designed for this architecture. The choice of vision problems demonstrates the versatility of ACMAA for a wide range of vision tasks. These algorithms were simulated on a high level ACMAA simulator running on the Intel iPSC/2 hypercube, a parallel architecture. The results of this simulation are compared with those of sequential algorithms running on a single hypercube node. Details of the ACMAA processor architecture are also presented.

• Research Organization: Pennsylvania State Univ., University Park, PA (USA)
• OSTI ID: 6223439
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ALGORITHMS
COMPUTER ARCHITECTURE
COMPUTER CALCULATIONS
COMPUTER GRAPHICS
COMPUTERIZED SIMULATION
COMPUTERS
DESIGN
HYPERCUBE COMPUTERS
MATHEMATICAL LOGIC
MEMORY DEVICES
PARALLEL PROCESSING
PROGRAMMING
SEMICONDUCTOR DEVICES
SEMICONDUCTOR STORAGE DEVICES
SIMULATION