基于角度引导Transformer融合网络的多站协同目标识别方法

Multistation Cooperative Radar Target Recognition Based on an Angle-guided Transformer Fusion Network

多站协同雷达目标识别旨在利用多站信息的互补性提升识别性能。传统多站协同目标识别方法未直接考虑站间数据差异问题,且通常采用相对简单的融合策略,难以取得准确、稳健的识别性能。该文针对多站协同雷达高分辨距离像(HRRP)目标识别问题,提出了一种基于角度引导的Transformer融合网络。该网络以Transformer作为特征提取主体结构,提取单站HRRP的局部和全局特征。并在此基础上设计了3个新的辅助模块促进多站特征融合学习,角度引导模块、前级特征交互模块以及深层注意力特征融合模块。首先,角度引导模块使用目标方位角度对站间数据差异进行建模,强化了所提特征与多站视角的对应关系,提升了特征稳健性与一致性。其次,前级特征交互模块和深层注意力特征融合模块相结合的融合策略,实现了对各站特征的多阶段层次化融合。最后,基于实测数据模拟多站场景进行协同识别实验,结果表明所提方法能够有效地提升多站协同时的目标识别性能。

Multistation cooperative radar target recognition aims to enhance recognition performance by utilizing the complementarity between multistation information.Conventional multistation cooperative target recognition methods do not explicitly consider the issue of interstation data differences and typically adopt relatively simple fusion strategies,which makes it difficult to obtain accurate and robust recognition performance.In this study,we propose an angle-guided transformer fusion network for multistation radar High-Resolution Range Profile(HRRP)target recognition.The extraction of the local and global features of the single-station HRRP is conducted via feature extraction,which employs a transformer as its main structure.Furthermore,three new auxiliary modules are created to facilitate fusion learning:the angle-guided module,the prefeature interaction module,and the deep attention feature fusion module.First,the angle guidance module enhances the robustness and consistency of features via modeling data differences between multiple stations and reinforces individual features associated with the observation perspective.Second,the fusion approach is optimized,and the multilevel hierarchical fusion of multistation features is achieved by combining the prefeature interaction module and the deep attention feature fusion module.Finally,the experiments are conducted on the basis of the simulated multistation scenarios with measured data,and the outcomes demonstrate that our approach can effectively enhance the performance of target recognition in multistation coordination.