|
The most challenging problem of Automatic Target Recognition (ATR) is the extraction of robust and independent target
features which describe the target unambiguously. These features have to be robust and invariant in different senses: in
time, between aspect views (azimuth and elevation angle), between target motion (translation and rotation) and between
different target variants. Especially for ground moving targets in military applications an irregular target motion is
typical, so that a strong variation of the backscattered radar signal with azimuth and elevation angle makes the extraction
of stable and robust features most difficult. For ATR based on High Range Resolution (HRR) profiles and / or Inverse
Synthetic Aperture Radar (ISAR) images it is crucial that the reference dataset consists of stable and robust features,
which, among others, will depend on the target aspect and depression angle amongst others. Here it is important to find
an adequate data grid for an efficient data coverage in the reference dataset for ATR.
In this paper the variability of the backscattered radar signals of target scattering centers is analyzed for different HRR
profiles and ISAR images from measured turntable datasets of ground targets under controlled conditions. Especially the
dependency of the features on the elevation angle is analyzed regarding to the ATR of large strip SAR data with a large
range of depression angles by using available (I)SAR datasets as reference. In this work the robustness of these
scattering centers is analyzed by extracting their amplitude, phase and position. Therefore turntable measurements under
controlled conditions were performed targeting an artificial military reference object called STANDCAM. Measures
referring to variability, similarity, robustness and separability regarding the scattering centers are defined. The
dependency of the scattering behaviour with respect to azimuth and elevation variations is analyzed.
Additionally generic types of features (geometrical, statistical), which can be derived especially from (I)SAR images, are
applied to the ATR-task. Therefore subsequently the dependence of individual feature values as well as the feature
statistics on aspect (i.e. azimuth and elevation) are presented. The Kolmogorov-Smirnov distance will be used to show
how the feature statistics is influenced by varying elevation angles. Finally, confusion matrices are computed between
the STANDCAM target at all eleven elevation angles. This helps to assess the robustness of ATR performance under the
influence of aspect angle deviations between training set and test set.
|
