Transformer-Based Automatic Target Recognition for 3D-InISAR

Abstract

The 3-D interferometric inverse synthetic aperture radar (3D-InISAR) imaging provides a more complete and reliable representation of targets compared to traditional 2D-ISAR, overcoming limitations related to the geometry of the radar-target system and relative motion. This article presents the application of a point cloud transformer (PCT) for automatic target recognition (ATR) using 3D-InISAR data. The PCT model, originally developed to classify LIDAR’s point clouds, is trained on sparse synthetic point cloud datasets representing various military vehicles, including cars, tanks, and trucks. The synthetic data are carefully generated from computer-aided design (CAD) models, incorporating techniques such as voxel downsampling and data augmentation to ensure high fidelity and diversity. Initial testing on synthetic data demonstrates the PCT’s robustness and high accuracy when used for ATR. To bridge the gap between synthetic and real data, a transfer learning approach is employed, which operates a fine-tuning on the pretrained model by using real 3D-InISAR point clouds obtained from the publicly available sensor data management system (SDMS)-Air Force Research Laboratory (AFRL) dataset. Results show significant improvements in classification accuracy post-fine-tuning, validating the effectiveness of the PCT model for real-world ATR applications. The findings highlight the potential of transformer-based models in enhancing target recognition systems for future ATR systems based on 3-D radar images.