Parallel implementation and communication of low-level vision operations on a hypercube machine
Abstract
Several commercial hypercube parallel processors with the potential to deliver massive parallelism cost-effectively have appeared in the computer market. Hypercube machines open the door to a wide variety of application areas that could benefit from parallelism. Computer vision and image processing is one of these application areas. This thesis develops a general model for hypercube machines to show how three low-level computer vision algorithms and related communications can be implemented on a new generation hypercube machine, nCUBE 2 supercomputer, in parallel. The primary objective is to design an efficient algorithm, which runs on a network based on the hypercube topology, to carry out the communication tasks that are very important in parallel processing of low-level vision operations. Specific schemes are developed for data exchange among processors, which is indispensable in window convolution operations. Results reveal the relationship between communication and efficiency in parallel processing and illustrate the potential use of such a machine.
Notes
This item is only available in print in the UCF Libraries. If this is your thesis or dissertation, you can help us make it available online for use by researchers around the world by STARS for more information.
Graduation Date
1992
Semester
Summer
Advisor
DeCatrel, John M.
Degree
Master of Science (M.S.)
College
College of Engineering
Department
Computer Engineering
Format
Pages
84 p.
Language
English
Length of Campus-only Access
None
Access Status
Masters Thesis (Open Access)
Identifier
DP0029741
Subjects
Dissertations, Academic -- Engineering; Engineering -- Dissertations, Academic
STARS Citation
Shi, Yuanlin, "Parallel implementation and communication of low-level vision operations on a hypercube machine" (1992). Retrospective Theses and Dissertations. 4508.
https://stars.library.ucf.edu/rtd/4508
Accessibility Statement
This item was created or digitized prior to April 24, 2027, or is a reproduction of legacy media created before that date. It is preserved in its original, unmodified state specifically for research, reference, or historical recordkeeping. In accordance with the ADA Title II Final Rule, the University Libraries provides accessible versions of archival materials upon request. To request an accommodation for this item, please submit an accessibility request form.