SAR ATR with full-angle data augmentation and feature polymerisation

Abstract

Utilising neural networks to learn and extract valuable features has achieved satisfactory performance for synthetic aperture radar automatic target recognition (SAR ATR). However, such target recognition capability could be seriously limited by severe image rotation. To greatly improve the performance of convolutional neural networks-based SAR ATR, a data augmentation method combining region of interest (ROI) extraction and full-angle rotation method is firstly proposed in this study. Then, an inception-SAR NET is presented to polymerise multi-branch feature maps. The superior performance of inception-SAR NET structures is obtained by comprehensive experiments. Finally, the results based on MSTAR dataset demonstrate that authors’ methods could achieve the most advanced performance.

Keywords

• radar imaging
• synthetic aperture radar
• image recognition
• radar target recognition
• feature extraction
• object recognition
• convolutional neural nets
• radar computing
• feature polymerisation
• synthetic aperture radar automatic target recognition
• target recognition capability
• convolutional neural networks-based SAR ATR
• full-angle rotation method
• multibranch feature maps
• inception-SAR NET structures
• image rotation
• data augmentation method