GPU-Based Image Pyramid Transform Algorithm

Article Preview

Abstract:

With the development of semiconductor technology, the GPU's floating point computing capacity improves rapidly. How to GPU rendering from the traditional video game applied to the general computing has become a highlight in the research field of high performance computing.Pyramid transform is commonly used image processing algorithms. The experiment proves that NVIDIA GPU-based pyramid transform of image and rebuilding the image, as opposed to CPU platform acceleration achieved good results.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

422-427

Citation:

Online since:

January 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] http: /www. nvidia. cn/object/product_geforce_gtx_480_cn. html[OL].

Google Scholar

[2] PETER J. BURT , EDWARD H. ADELSON . The Laplacian Pyramid as a Compact Image Code[C], APRIL 1983, IEEE TRANSACTIONS ON COMMUNICATIONS, VOL. COM-31, NO. 4.

DOI: 10.1109/tcom.1983.1095851

Google Scholar

[3] Sain-Zee Ueng, Melvin Lathara, Sare S. Baghsorkhi. et al. CUDA-Lite: Reducing GPU Programming Complexity[OL], /http: /citeseerx. ist. psu. edu/viewdoc/download?doi=10. 1. 1. 163. 641&rep=rep1&type=pdf.

DOI: 10.1007/978-3-540-89740-8_1

Google Scholar

[4] NVIDIA Corporation, CUDA Programming Guide 2. 3[OL] , http: /www. nvidia. cn.

Google Scholar

[5] NVIDIA Corporation, CUDA Reference Manual Version 2. 3[OL].

Google Scholar

[6] Zhang Yujin, Image Engineering(1) Image Processing(Second Edition)[M], Beijing, Tsinghua University publishing house, (2006).

Google Scholar

[7] Yan Zhiyi, Zhu Yating, Pu Yong, Study on Parallel Image Processing Based on Compute Unified Device Architecture[J], Computer Measurement & Control, 2009, 17(2), P734-737(ch).

Google Scholar