Abstract
As the demand for higher performance computers for the processing of remote sensing science algorithms increases, the need to investigate new computing paradigms is justified. Field Programmable Gate Arrays enable the implementation of algorithms at the hardware gate level, leading to orders of magnitude performance increase over microprocessor based systems. The automatic classification of spaceborne multispectral images is an example of a computation intensive application that can benefit from implementation on an FPGA-based custom computing machine (adaptive or reconfigurable computer). A probabilistic neural network is used here to classify pixels of a multispectral LANDSAT-2 image. The implementation described utilizes Java client/server application programs to access the adaptive computer from a remote site. Results verify that a remote hardware version of the algorithm (implemented on an adaptive computer) is significantly faster than a local software version of the same algorithm (implemented on a typical general-purpose computer).