Multi-View Laplacian Propagation Fusion Network for Radar Image Target Recognition

Although deep learning-based approaches have significantly advanced intelligent radar image interpretation, existing methods predominantly rely on single-view inputs, which inherently limits target recognition performance. In practical scenarios, multi-view radar imagery provides richer structural and feature representations of targets compared to single-view observations. To effectively exploit this comprehensive information, we propose a new Multi-view Laplacian Propagation Fusion Network (MLPFN) for radar image target recognition. First, a Reparameterization Perspective-Aware (RPA) backbone is designed, incorporating a Dual-level Multi-path Rep-Kernel (DMPK) and a Multi-level Dual-path Attention Module (MDAM). This architecture mitigates the sensitivity of recognition performance to aspect angle variations and enhances the extraction of discriminative target features. Second, a Laplacian Multi-view Feature Propagation Algorithm (LMFPA) is introduced to encode structural correlations among different views, thereby augmenting the feature discriminability for multi-view targets. Third, a Multi-view Feature Adaptive Fusion Module (MFAFM) is developed to integrate global contextual information across views into a unified representation, reducing redundancy while maximizing feature distinctiveness. Furthermore, a Stage-wise Guided Constraint Training Mechanism (SGCTM) is devised to supervise the feature extraction process across different network layers during training, refining the network’s feature learning and recognition capabilities. Extensive experiments conducted on multi-view radar image datasets demonstrate the effectiveness of the proposed MLPFN.