The Grid 2: Blueprint for a New Computing Infrastructure
The Grid 2: Blueprint for a New Computing Infrastructure
MapReduce: simplified data processing on large clusters
Communications of the ACM - 50th anniversary issue: 1958 - 2008
Future Generation Computer Systems
Hadoop: The Definitive Guide
Development of Grid e-Infrastructure in South-Eastern Europe
Journal of Grid Computing
Resources and Services of the EGEE Production Infrastructure
Journal of Grid Computing
Adapting scientific computing problems to clouds using MapReduce
Future Generation Computer Systems
Deploying LiveWN Grids in the Greek School Network
Journal of Grid Computing
Hi-index | 0.00 |
The rapid processing of remote sensing (RS) images is essential in many large-scale real-time monitoring, such as meteorological monitoring and natural disaster warning. However, the computation cost of RS is often expensive, traditional RS processing methods cannot satisfy the time requirement of dynamic monitoring. Fortunately, cloud computing not only provides an effective service for data management, but also offers a convenient way to execute RS computing. It is necessary to integrate the rapid RS processing services in a unified cloud computing architecture. The architecture can provide users with integrated rapid RS image processing service through effective huge data management and distributed parallel processing. This paper explores rapid processing methods and strategies for RS images based on cloud computing. In order to compare with other computing paradigms, we choose the maximum likelihood classification (MLC) as our experimental algorithm and Mahalanobis distance clustering (MDC) as our verifying algorithm to execute comparing. In these experiments, we compare the computation cost of RS processing in three computing paradigms (stand-alone, MPI, and MapReduce). From the intensive experimental results, we find that the RS processing based on cloud computing performs best from the aspects of programming convenience, data management and computational efficiency simultaneously, especially when processing huge amount of data.