DMCA
OpenVIDIA: Parallel GPU computer vision (2005)
| Venue: | In ACM Multimedia |
| Citations: | 76 - 1 self |
BibTeX
@INPROCEEDINGS{Fung05openvidia:parallel,
author = {James Fung and Steve Mann and Chris Aimone},
title = {OpenVIDIA: Parallel GPU computer vision},
booktitle = {In ACM Multimedia},
year = {2005},
pages = {849--852}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Graphics and vision are approximate inverses of each other: ordinarily Graphics Processing Units (GPUs) are used to convert \numbers into pictures " (i.e. computer graphics). In this paper, we propose using GPUs in approximately the reverse way: to assist in \converting pictures into numbers" (i.e. computer vision). The OpenVIDIA project uses single or multiple graphics cards to accelerate image analysis and computer vision. It is a library and API aimed at provid-ing a graphics hardware accelerated processing framework for image processing and computer vision. OpenVIDIA ex-plores the creation of a parallel computer architecture con-sisting of multiple Graphics Processing Units (GPUs) built entirely from commodity hardware. OpenVIDIA uses mul-tiple Graphics Processing Units in parallel to operate as a general-purpose parallel computer architecture. It provides a simple API which implements some common computer vi-sion algorithms. Many components can be used immediately and because the project is Open Source, the code is intended to serve as templates and examples for how similar algo-rithms are mapped onto graphics hardware. Implemented are image processing techniques (Canny edge detection, l-tering), image feature handling (identifying and matching features) and image registration, to name a few.
Keyphrases
computer vision parallel gpu computer vision graphic hardware similar algo-rithms general-purpose parallel computer architecture processing framework mul-tiple graphic processing unit image processing open source approximate inverse canny edge detection parallel computer architecture con-sisting multiple graphic card computer graphic common computer vi-sion algorithm simple api multiple graphic processing unit many component reverse way image registration image feature image analysis openvidia project image processing technique commodity hardware
