FUILTRATION AND CORRELATION PROCESSING OF IMAGES BY THE CUDA TECHNOLOGY
Abstract
The basic concepts and specificity of the programming technology of CUDA video cards are presented. The efficiency of the technology is demonstrated on image processing tasks. Results of a comparative performance analysis of program implementations on the GPU and CPU are adduced for urgent tasks of image processing. It is shown that CUDA allows accelerating computations of image processing tasks by several orders of magnitude. In particular, the use of the CUDA technology has made possible to implement correlation algorithms for tracking objects on video sequences in real time.
About the Authors
E. N. Seredin
United Institute of Informatics Problems of the National Academy of Sciences of Belarus, Minsk
Belarus
Belarus
B. A. Zalesky
United Institute of Informatics Problems of the National Academy of Sciences of Belarus, Minsk
Belarus
Belarus
References
1. https://developer.nvidia.com/category/zone/cuda-zone [Электронный ресурс].
2. Таненбаум Э. Архитектура компьютера. СПб., 2007.
3. Евченко А. И. OpenGL и DirectX: программирование графики. СПб., 2006.
4. http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html [Электронный ресурс].
5. Боресков А. В. Основы работы с технологией CUDA. М., 2010.
6. http://www.nvidia.ru/object/gpu-computing-applications-ru.html [Электронный ресурс].
7. Залесский Б. А., Середин Э. Н. // Информатика. 2014. № 41.
8. Josth R. // J. of Real-Time Image Processing. 2011. Vol. 7.
9. Joaquin F. // J. of Real-Time Image Processing. 2011. Vol. 7.
10. Yoon-Seok Choi. // J. of Real-Time Image Processing. 2014. Vol. 9.
11. GembrisD. // J. of Real-Time Image Processing. 2010.
12. Сандерс Дж. Технология CUDA в примерах: введение в программирование графических процессоров. М., 2011.
13. Гонсалес Р. Цифровая обработка изображений. М., 2005.
14. Сойфер В. А. Методы компьютерной обработки изображений. М., 2003.
Review
Views: 685
Email this article 