Title :
Fast imaging of vegetation on GPUs based on Non-Uniform FFTs
Author :
Capozzoli, A. ; Curcio, C. ; Iudice, I. ; Liseno, A. ; Savarese, S.
Author_Institution :
Dipt. di Ing. Biomed., Elettron. e delle Telecomun., Univ. di Napoli Federico II, Naples, Italy
Abstract :
We present an ω-k approach based on the use of a 1D Non-Uniform FFT (NUFFT) routine, of NER (Non-Equispaced Results) type, programmed on a GPU by means of a Matlab code speeded-up by Accelereyes Jacket. The implementation of the GPU-based, parallel NUFFT routine is detailed and the computational advantages of the developed approach are highlighted against a multi-core CPU procedure implemented in Matlab language. The GPU-based routine has resulted about 5 times faster than the multicore CPU-based one. Experimental results of vegetation imaging on a box-tree (Buxus tree) are also presented.
Keywords :
computer graphic equipment; coprocessors; fast Fourier transforms; geophysical image processing; parallel processing; vegetation; ω-k approach; Accelereyes Jacket; GPU; Matlab code; box-tree; fast Fourier transforms; graphics processing unit; multicore CPU procedure; nonuniform FFT; parallel NUFFT routine; vegetation imaging; Fourier transforms; Graphics processing unit; Image reconstruction; Imaging; Interpolation; Synthetic aperture radar; Vegetation;
Conference_Titel :
Electromagnetics in Advanced Applications (ICEAA), 2011 International Conference on
Conference_Location :
Torino
Print_ISBN :
978-1-61284-976-8
DOI :
10.1109/ICEAA.2011.6046522
