GPGPU Implementation of a Genetic Algorithm for Stereo Refinement

During the last decade, the general-purpose computing on graphics processing units Graphics (GPGPU) has turned out to be a useful tool for speeding up many scientific calculations. Computer vision is known to be one of the fields with more penetration of these new techniques. This paper explores the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of interactive multimedia and artificial intelligence Ročník 3; číslo 2; s. 69 - 76
Hlavní autoři: Arranz, Álvaro, Alvar, Manuel
Médium: Journal Article
Jazyk:angličtina
Vydáno: IMAI Software 01.03.2015
UNIR-Universidad Internacional de La Rioja
Universidad Internacional de La Rioja (UNIR)
Témata:
Computer vision
genetic algorithm
Genetic Algorithms
GPGPU
Parallel Processing
stereo
Spain
ISSN:1989-1660, 1989-1660
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:During the last decade, the general-purpose computing on graphics processing units Graphics (GPGPU) has turned out to be a useful tool for speeding up many scientific calculations. Computer vision is known to be one of the fields with more penetration of these new techniques. This paper explores the advantages of using GPGPU implementation to speedup a genetic algorithm used for stereo refinement. The main contribution of this paper is analyzing which genetic operators take advantage of a parallel approach and the description of an efficient state-of-the-art implementation for each one. As a result, speed-ups close to x80 can be achieved, demonstrating to be the only way of achieving close to real-time performance. Keywords--Parallel processing, GPGPU, genetic algorithm, stereo.
ISSN:1989-1660
1989-1660
DOI:10.9781/ijimai.2015.329