원문정보
초록
영어
In this paper, we present Compute Unified Device Architecture i.e. CUDA based pyramidal image blending algorithm using an object oriented design patterns. This algorithm is an essential part of an image stitching process for a seamless panoramic mosaic. The CUDA framework is a novel GPU programming framework from NVIDIA. We introduce an object oriented framework for the CUDA based image processing. We illustrate a set of design patterns exploiting programming advantages of an object oriented language; such as encapsulation, code reusability, information hiding, complexity hiding and extensibility. We discuss the framework’s performance in terms of programming efforts, execution overhead and speedup factor achieved over the CPU one. We also talk about programming efforts required for adding the OpenGL Shading Language functionality to the framework.
목차
1. Introduction
2. Pyramidal Image Blending
2.1 Gaussian Blur
2.2 REDUCE Operation
2.3 EXPAND Operation
2.4 Gaussian Pyramid
2.5 Laplacian Pyramid
3. CUDA Framework
4. Implementation
4.1 Implementation Stages
4.2 CPU Implementation
4.3 Simple-CUDA
4.4 IO-CUDA
4.5 Shared-CUDA
4.6.1 Host Code & Device Code
4.7 Extensible Architecture
5. Extending Framework: An Example
5.1 OpenGL Shading Language
5.2 Design
5.3 Managing Image Data
5.4 Code Reuse
6. Results
7. Conclusions
Acknowledgement
References
키워드
- CUDA
- design patterns
- pyramidal image blending
- object oriented programming
- panoramic image stitching