Feasibility of employing artificial neural networks for emergent crop monitoring in SAR systems

摘要

An investigation into the feasibility of using high-resolution synthetic aperture radar (SAR) data and artificial neural networks for monitoring the stage of growth of a crop is. presented. The high resolution data sets representing an experimentally simulated crop at three different stages of growth are acquired at X- band by means of a ground-based synthetic aperture radar (GB-SAR) system under development at the University of Sheffield. A hybrid classification system, developed in recent studies, is then applied to these image sets, providing very high training and test data accuracy (95.8/100 and 94.4/100, respectively) for differences in growth of the order of a quarter of a wavelength, and acceptable results (79.9/100 and 71.9/100, respectively) for differences of the order of a tenth of a wavelength. The procedures developed for the high-resolution data acquisition are described and the results obtained by applying the hybrid classification system to the acquired data are discussed.