Dual-Channel BiGRU–Transformer-Graph Fusion Network for Space Micromotion Targets Recognition Based on Radar Network Systems

Abstract

The radar network system (RNS) can provide multiband and multiview target information, which helps improve target recognition ability. A space micromotion targets recognition method based on RNSs with a dual-channel bidirectional gated recurrent unit (BiGRU)–Transformer-graph fusion (DC-BiGT-GF) network is proposed in this article. First, a temporal feature extraction subnetwork based on BiGRU–Transformer is utilized to process the real and imaginary parts of complex-valued radar cross section in parallel to capture the local and global temporal dependencies. Second, a spatial feature extraction subnetwork is designed to extract the potential spatial dependencies, which integrates a predefined graph and an adaptive graph. In the real part channel, the Euclidian distance between radars is used to construct the adjacency matrix to represent the predefined graph structure, and the adaptive adjacency matrix is designed to learn the potential graph structure from end to end. To represent the frequency-domain features, the phase difference is applied to the imaginary part channel to build a predefined adjacency matrix. Meanwhile, the adaptive adjacency matrix is calculated using cosine similarity to obtain the geometric features. Finally, extensive experiments show that the DC-BiGT-GF network can reliably recognize the space micromotion targets under low SNR and low radar pulse repetition frequency conditions. Recognition accuracy is greatly improved compared with the baseline methods.