Pose estimation based on exploration of geometrical information in SAR images

Abstract

Pose normalization is beneficial for improving the accuracy of Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). In fact, pose normalization can be achieved by rotating the given images according to the estimated pose of the target of interest. However, the partial defect targets in SAR images caused by the shadow effect affects the accuracy of pose estimation. This paper proposes a pose estimation method based on the exploration of the geometrical information of the target of interest in SAR images. The proposed method is evaluated with the moving and stationary target acquisition and recognition (MSTAR) public release dataset. Experimental results verify the effectiveness of the proposed method.