GPU Implementation of the Affine Transform for 3D Image Registration

Charles Gillan; Daniel Crookes; Paul Miller; Kevin Boyle

doi:10.1109/IMVIP.2009.34

GPU Implementation of the Affine Transform for 3D Image Registration

Charles Gillan, Daniel Crookes, Paul Miller, Kevin Boyle

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

Recent developments in 3D low-light level CCD (L3CCD) image capture have resulted in vast volumes of data being produced in real time which require image registration. The amount of data involved means that acceleration of the processing is essential. One of the key steps in one iterative registration algorithm is the application of an affine transform to all the planes of a 3D image. This paper presents details and performance results for a number of parallelized implementations of the affine transform on the NVIDIA 8800 GPU series, and shows that the transform runs 128 times faster on the GPU than a C++ version on a PC, or 54 times faster when data transfer between the GPU and the host PC is included.

Original language	English
Title of host publication	Proceedings of 2009 13th International Machine Vision and Image Processing Conference
Place of Publication	Piscataway NJ 08855-1331
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	151-155
Number of pages	5
ISBN (Print)	978-1-4244-4875-3
DOIs	https://doi.org/10.1109/IMVIP.2009.34
Publication status	Published - 04 Sep 2009

Access to Document

10.1109/IMVIP.2009.34

Cite this

@inproceedings{bf5ac0acf1cf4b33b1d767da814d4e7a,

title = "GPU Implementation of the Affine Transform for 3D Image Registration",

abstract = "Recent developments in 3D low-light level CCD (L3CCD) image capture have resulted in vast volumes of data being produced in real time which require image registration. The amount of data involved means that acceleration of the processing is essential. One of the key steps in one iterative registration algorithm is the application of an affine transform to all the planes of a 3D image. This paper presents details and performance results for a number of parallelized implementations of the affine transform on the NVIDIA 8800 GPU series, and shows that the transform runs 128 times faster on the GPU than a C++ version on a PC, or 54 times faster when data transfer between the GPU and the host PC is included.",

author = "Charles Gillan and Daniel Crookes and Paul Miller and Kevin Boyle",

year = "2009",

month = sep,

day = "4",

doi = "10.1109/IMVIP.2009.34",

language = "English",

isbn = "978-1-4244-4875-3",

pages = "151--155",

booktitle = "Proceedings of 2009 13th International Machine Vision and Image Processing Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

GPU Implementation of the Affine Transform for 3D Image Registration. / Gillan, Charles; Crookes, Daniel; Miller, Paul et al.

Proceedings of 2009 13th International Machine Vision and Image Processing Conference. Piscataway NJ 08855-1331 : Institute of Electrical and Electronics Engineers Inc., 2009. p. 151-155.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - GPU Implementation of the Affine Transform for 3D Image Registration

AU - Gillan, Charles

AU - Crookes, Daniel

AU - Miller, Paul

AU - Boyle, Kevin

PY - 2009/9/4

Y1 - 2009/9/4

N2 - Recent developments in 3D low-light level CCD (L3CCD) image capture have resulted in vast volumes of data being produced in real time which require image registration. The amount of data involved means that acceleration of the processing is essential. One of the key steps in one iterative registration algorithm is the application of an affine transform to all the planes of a 3D image. This paper presents details and performance results for a number of parallelized implementations of the affine transform on the NVIDIA 8800 GPU series, and shows that the transform runs 128 times faster on the GPU than a C++ version on a PC, or 54 times faster when data transfer between the GPU and the host PC is included.

AB - Recent developments in 3D low-light level CCD (L3CCD) image capture have resulted in vast volumes of data being produced in real time which require image registration. The amount of data involved means that acceleration of the processing is essential. One of the key steps in one iterative registration algorithm is the application of an affine transform to all the planes of a 3D image. This paper presents details and performance results for a number of parallelized implementations of the affine transform on the NVIDIA 8800 GPU series, and shows that the transform runs 128 times faster on the GPU than a C++ version on a PC, or 54 times faster when data transfer between the GPU and the host PC is included.

U2 - 10.1109/IMVIP.2009.34

DO - 10.1109/IMVIP.2009.34

M3 - Conference contribution

SN - 978-1-4244-4875-3

SP - 151

EP - 155

BT - Proceedings of 2009 13th International Machine Vision and Image Processing Conference

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway NJ 08855-1331

ER -

GPU Implementation of the Affine Transform for 3D Image Registration

Abstract

Access to Document

Fingerprint

Cite this