A parallel computing system of remote sensing images based on Global Subdivision Model

Remote sensing images have been widely used in various fields, how to process remote sensing images in real-time has become an important problem. Based on Global Subdivision Model (GSM), this paper presented a framework of a parallel computing system of remote sensing images (GSPCS). GSPCS consists of management nodes, storage nodes and computing nodes. In GSPCS, in order to load image data that need to be processed in parallel, remote sensing images have been divided into sub-images and stored to the related data nodes which are statically associated with global subdivision cells and indexed by EMD. For each image processing task, the available computing resources will be mapped dynamically to relative subdivision cells by the management nodes according to the spatial scale and range of the tasks. The computing nodes could run parallel algorithms separately to achieve more fine-grain parallelism. Experiments indicated that GSPCS has the capability of processing remote sensing images effectively in parallel.