Radar HRRP Feature Fusion Recognition Method Based on ConvLSTM Network with Multi-Input Gate Recurrent Unit

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2024-12, Vol.16 (23), p.4533
• Main Authors: Yang, Wei, Chen, Tianqi, Lei, Shiwen, Zhao, Zhiqin, Hu, Haoquan, Hu, Jun
• Format: Article
• Language: English
• Subjects: Accuracy; Automatic target recognition; convolutional long short-term memory; Datasets; Domains; Feature extraction; feature fusion; Geometrical optics; high-resolution range profile; Information processing; Long short-term memory; Magnetic fields; Methods; Military air strikes; multi-input gate recurrent unit; Radar; Radar systems; ship targets; Simulation; Target acquisition; Target recognition
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs16234533

Recently, the radar high-resolution range profiles (HRRPs) have gained significant attention in the field of radar automatic target recognition due to their advantages of being easy to acquire, having a small data footprint, and providing rich target structural information. However, existing recognition methods typically focus on single-domain features, utilizing either the raw HRRP sequence or the extracted feature sequence independently. To fully exploit the multi-domain information present in HRRP sequences, this paper proposes a novel target feature fusion recognition approach. By combining a convolutional long short-term memory (ConvLSTM) network with a cascaded gated recurrent unit (GRU) structure, the proposed method leverages multi-domain and temporal information to enhance recognition performance. Furthermore, a multi-input framework based on learnable parameters is designed to improve target representation capabilities. Experimental results of 6 ship targets demonstrate that the fusion recognition method achieves superior accuracy and faster convergence compared to methods relying on single-domain sequences. It is also found that the proposed method consistently outperforms the other previous methods. And the recognition accuracy is up to 93.32% and 82.15% for full polarization under the SNRs of 20 dB and 5 dB, respectively. Therefore, the proposed method consistently outperforms the previous methods overall.