Communications of the ACM
Researchers Develop Fast Image Processing For Industry
Lule University of Technology researcher Matthew Thurley, left, and student Victor Danell who developed LTU-CUDA, which is possible to use in combination with commonly available graphics cards, such as the one shown here.
Credit: Lule University of Technology
Researchers at Sweden's Lulea University of Technology (LTU) have developed LTU-CUDA, software for fast image-processing tasks.
"Image processing on a graphics card with LTU-CUDA would mean fast feedback in seconds of particle size, computing the size fractions of material on a conveyor belt," says LTU's Matthew Thurley. "This in turn means that the mills and crushers in an industrial process could be automatically regulated according to the input and output material sizes."
LTU-CUDA enables split-second image analysis of size fractions using morphological image processing, via a mathematical technique for analyzing and processing geometrical structures, such as structures of diverse large and small rock fragments on a conveyor. The resulting automatic control of industry processes could save energy, increase production capacity, and reduce maintenance and downtime. LTU-CUDA can be downloaded for free from the Internet.
From Lulea University of Technology (Sweden)
View Full Article
Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA
No entries found