A multiple scale neural system for boundary and surface representation of SAR data

Abstract

A neural network model of boundary segmentation and surface representation is developed to process images containing range data gathered by a synthetic aperture radar (SAR) sensor. SAR sensors can produce range imagery of high spatial resolution under difficult weather conditions but the data presents some interpretation difficulties. These include the large dynamic range of the sensor signal, which requires some type of nonlinear compression. Another problem is image speckle, which is generated by coherent processing of radar signals and has characteristics of random multiplicative noise. Our approach uses the form-sensitive operations of a neural network model in order to detect and enhance structure based on information over large, variably sized and variably shaped regions of the image. In particular, the multiscale implementation of the neural model reported here is capable of exploiting and combining information from several nested neighborhoods of a given image location to determine the final intensity value to be displayed for that pixel. By "neighborhood" is here meant a region whose form varies as a function of nearby image data, not some fixed (weighted) radial function for all pixel locations.