Sequential ISAR Target Classification Based on Hybrid Transformer

To make full use of the sequential information obtained by continuous inverse synthetic aperture radar (ISAR) imaging, this article proposes a sequential ISAR target classification network based on hybrid transformer (HT). First, a temporal-spatial encoder based on the attention mechanism is designed to extract long-term and global features from sequential images. Meanwhile, a local feature encoder based on the 3-D convolution neural network is designed to extract short-term and local features. Then, the above two features are fused and the classification labels are obtained by a channel encoder-decoder. In 4-satellite target classification experiments, the proposed HT shows high accuracy and robustness to the unknown image scaling, rotation, and combined deformations.

Automated summary

This article proposes a sequential ISAR target classification network based on hybrid transformer (HT), which extracts long-term global features and short-term local features through a temporal-spatial encoder and a local feature encoder, and fuses them to obtain classification labels using a channel encoder-decoder. In target classification experiments, the proposed HT demonstrates high accuracy and robustness to unknown image scaling, rotation, and combined deformations.