Image and Video Processing on GPU: Implementation Scheme, Applications and Future Directions
Department of Electrical, Electronics and Computer Engineering, Catania University, viale Doria 6, Catania, Italy
Lecture Notes on Electrical Engineering, Proc. International Conference on Mechanical and Electronic Engineering (ICMEE2012), 2012
@article{di2012image,
title={Image and Video Processing on GPU: Implementation Scheme, Applications and Future Directions},
author={Di Salvo, R. and Pino, C.},
year={2012}
}
Most of the recent computer graphic applications are essentially based on multicore general-purpose processors architectures, which include CPUs made up of parallel processors with high elaboration capability. Due to the rapid turning towards high definition multimedia, much more memory space and computational resources are needed to achieve better performance. Recently the GPGPUs (which stands for General-Purpose computing on Graphic Processing Units) architectures have been adopted. Since the GPUs are becoming increasingly programmable and provide a vast number of simple, data-parallel, deeply multithreaded cores and high memory bandwidths, they have been used in several research fields such as image and video processing, medical and human applications. This work aims at providing a meticulous review of the most recent image and video processing techniques and significant applications, highlighting both the advantages of using CUDA in terms of efficiency and the guide line for future development by means of these emerging techniques.
July 6, 2012 by hgpu
