Paper Info
Title
A data-distributed parallel algorithm for wavelet-based fusion of remote sensing images
Abstract
With the increasing importance of multiplatform remote sensing missions, the fast integration or fusion of digital images from disparate sources has become critical to the success of these endeavors. In this paper, to speed up the fusion process, a Data-distributed Parallel Algorithm for wavelet-based Fusion (DPAF for short) of remote sensing images which are not geo-registered remote sensing images is presented for the first time. To overcome the limitations on memory space as well as the computing capability of a single processor, data distribution, data-parallel processing and load balancing techniques are integrated into DPAF. To avoid the inherent communication overhead of a wavelet-based fusion method, a special design called redundant partitioning is used, which is inspired by the characteristics of wavelet transform. Finally, DPAF is evaluated in theory and tested on a 32-CPU cluster of workstations. The experimental results show that our algorithm has good parallel performance and scalability.
Year
DOI
Venue
2007
10.1007/s11704-007-0024-1
Frontiers of Computer Science in China
Keywords
Field
DocType
image fusion,image registration,data distribution,load balancing,redundant partitioning
Image fusion,Parallel algorithm,Computer science,Load balancing (computing),Remote sensing,Digital image,Wavelet transform,Wavelet,Speedup,Scalability
Journal
Volume
Issue
ISSN
1
2
16737466
Citations 
PageRank 
References 
0
0.34
15
Authors
4
Name
Order
Citations
PageRank
Xuejun Yang167873.26
Panfeng Wang2346.12
Yunfei Du37214.62
Haifang Zhou4359.33