Advances in knowledge discovery and data mining
Advances in knowledge discovery and data mining
Storing a collection of polygons using quadtrees
ACM Transactions on Graphics (TOG)
An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
Orthogonally persistent object systems
The VLDB Journal — The International Journal on Very Large Data Bases - Persistent object systems
ACM-SE 45 Proceedings of the 45th annual southeast regional conference
Dryad: distributed data-parallel programs from sequential building blocks
Proceedings of the 2nd ACM SIGOPS/EuroSys European Conference on Computer Systems 2007
High Performance Computing in Remote Sensing
High Performance Computing in Remote Sensing
OSDI'08 Proceedings of the 8th USENIX conference on Operating systems design and implementation
| Hi-index | 0.00 |
Our capabilities for collecting remote sensing images have greatly outpaced our abilities to analyze and retrieve information from the image databases. This paper presents a distributed framework for information mining from multi-dimensional remotely sensed images using Windows High Performance Computing (HPC) Servers and Dryad distributed computing engine. Land cover and land use types are classified by Support Vector Machines (SVM) and stored in an object-oriented database with region quad-tree indices. DryadLINQ queries, an extended version of the LINQ programming model, are developed for retrieving land cover distribution information and detect the changes of each land cover type at multi levels. A HPC cluster with sixteen computing nodes is implemented and the experiments are conducted on a time series Landsat Thematic Mapper (TM) images. The results show the effectiveness of the framework and its potentials in other remote sensing applications.