In this paper, we present efficient multiscale approaches to the segme
ntation of natural clutter, specifically grass and forest, and to the
enhancement of anomalies in synthetic aperture radar (SAR) imagery, Th
e methods we propose exploit the coherent nature of SAR sensors, In pa
rticular, they take advantage of the characteristic statistical differ
ences in imagery of different terrain types, as a function of scale, d
ue to radar speckle, We employ a recently introduced class of multisca
le stochastic processes that provide a powerful framework for describi
ng random processes and fields that evolve in scale, We build models r
epresentative of each category of terrain of interest (i.e., grass and
forest) and employ them in directing decisions on pixel classificatio
n, segmentation, and anomalous behavior, The scale-autoregressive natu
re of our models allows extremely efficient calculation of likelihoods
for different terrain classifications over windows of SAR imagery, We
subsequently use these likelihoods as the basis for both image pixel
classification and grass-forest boundary estimation, In addition, anom
aly enhancement is possible with minimal additional computation, Speci
fically, the residuals produced by our models in predicting SAR imager
y from coarser scale images are theoretically uncorrelated, As a resul
t, potentially anomalous pixels and regions are enhanced and pinpointe
d by noting regions whose residuals display a high level of correlatio
n throughout scale, We evaluate the performance of our techniques thro
ugh testing on 0.3-m SAR data gathered with Lincoln Laboratory's milli
meter-wave SAR.