Title
Research on CUDA-Based SIFT Registration of SAR Image.
Abstract
This paper proposes an implementation and optimization of SIFT algorithm for SAR (Synthetic Aperture Radar) images. It improves the SIFT algorithm efficiency using the graphics processing unit (GPU) architecture based on Compute Unified Device Architecture (CUDA) framework, to attend the request of real-time remote sensing image processing. The experiments of large-size SAR image demonstrate that the algorithms achieve 57.8 times speedup.
Year
DOI
Venue
2011
10.1109/PAAP.2011.21
PAAP
Keywords
Field
DocType
large-size sar image,synthetic aperture radar,image processing,times speedup,cuda-based sift registration,compute unified device architecture,sar image,sift algorithm efficiency,sift algorithm,algorithm design and analysis,algorithm design,image registration,optimization,radar imaging,computer architecture,feature extraction,instruction sets,real time
Computer vision,Radar imaging,Algorithm design,Computer graphics (images),Synthetic aperture radar,Computer science,CUDA,Feature extraction,Artificial intelligence,Graphics processing unit,Image registration,Speedup
Conference
Citations 
PageRank 
References 
1
0.37
3
Authors
5
Name
Order
Citations
PageRank
Yang Huang1165.62
Jinshuo Liu274.62
Meisheng Tu310.37
Siyuan Li443.54
Juan Deng511.04