A new polarimetric classification approach evaluated for agricultural crops
Nieuwe Kanaal 11,
Statistical properties of the polarimetric backscatter behaviour for a single homogeneous
area are described by the Wishart distribution or its marginal distributions. These distributions do not necessarily well
describe the statistics for a collection of
homogeneous areas of the same class because of variation in, for
example, biophysical parameters, which often is reflected in variation in
the mean backscatter values. Using Kolmogorov-Smirnov (K-S) tests of fit
it will be shown that, for example, the Beta distribution
is a better descriptor for the coherence magnitude, and the log-normal
distribution for the backscatter level. This will be evaluated for a
number of agricultural crop classes, grasslands and fruit tree plantations at
the Flevoland test site, using AirSAR (C-, L- and P-band polarimetric) data.
Classification improvements will be quantified. Also the effect of azimuthal asymmetric
backscatter behaviour on the classification results will be discussed. A new
reversible transform of the covariance matrix will be introduced in order to
describe the full polarimetric target properties in a mathematically simpler way,
allowing even simpler statistical descriptions. It will be shown that this
transform yields versatile and robust classification approaches and gives new insight in
polarimetric decomposition. A comparison of results for the various classification methods
will be given, using several (combinations) of frequency bands.
To support generalisation of the results the physical relation between vegetation
structure and backscatter mechanisms will be discussed explicitly.