Implementation of multispectral image classification on a remote adaptive computer

As the demand for higher performance computers for the processing of remote sensing science algorithms increases, the need to investigate:new computin g paradigms is justified. Field Programmable Gate Arrays enable the impleme ntation of algorithms at the hardware gate level, leading to orders of magn itude performance increase over microprocessor based systems. The automatic classification of spaceborne multispectral images is an example of a compu tation intensive application that can benefit from implementation on an FPG A-based custom computing machine (adaptive or reconfigurable computer). A p robabilistic neural network is used here to classify pixels of a multispect ral LANDSAT-2 image, The implementation described utilizes Java client/serv er application programs to access the adaptive computer from a remote site. Results verify that a remote hardware version of:the algorithm (implemente d on an adaptive computer) is significantly faster than a local software ve rsion of the same algorithm (implemented on a typical general-purpose compu ter).