Multipolar SAR ATR: Experiments with the GTRI dataset

Multipolar radar data is a rich source of information. Even though multipolar synthetic aperture radar (SAR) images have been used extensively for remote sensing applications, the use of the same for airborne radar systems has been limited. With the release of the GTRI turn table multipolar data in public domain, the scopes to experiment with real multipolar data has increased. The current work reports the experiments done with the GTRI dataset to examine the effect of using multipolar data for SAR based target classification. The results indicate that multipolar data may give better classification performance and may also be useful to make the classifier less sensitive to minor variations between the training and test target images.