Object oriented framework for real-time image processing on GPU
School of Information and Communication Engineering, Inha University, Incheon 402-751, Korea
17th IEEE International Conference on Image Processing (ICIP), 2010
@inproceedings{seiller2010object,
title={Object oriented framework for real-time image processing on GPU},
author={Seiller, N. and Singhal, N. and Park, I.K.},
booktitle={Image Processing (ICIP), 2010 17th IEEE International Conference on},
pages={4477–4480},
organization={IEEE},
year={2010}
}
In this paper, we present a framework for efficiently integrating programming resources of both GPU and CPU. We introduce an object oriented framework for GPGPU-based image processing. We illustrate a set of classes exploiting the design and programming advantages of an object oriented language, such as code reusability/extensibility, flexibility, information hiding, and complexity hiding. This class structure is supplemented with shader (GLSL) and kernel (CUDA) programming to facilitate full functionality. We demonstrate the potential of our approach with application scenarios and discuss the framework’s performance in terms of programming effort, execution overhead, and speedup factor achieved over CPU.
May 15, 2011 by hgpu
