基于多路径特征融合的非视距目标识别方法OA

The accurate classification of targets concealed in non-line-of-sight(NLOS)regions,such as armed person-nel or unmanned aerial vehicles behind building corners,holds significant value for modern urban warfare and intelli-gent driving systems.However,the complexity of electromagnetic wave propagation in NLOS scenarios often intro-duces multipath interference,blurred path boundaries,and signal distortion in echoes,thereby undermining the reliabil-ity of traditional classification methods that rely on geometric modeling or handcrafted features.To address these chal-lenges,this study proposes a multipath feature fusion network for NLOS target classification.First,the echo characteris-tics of four representative target types were analyzed:pedestrians,soldiers carrying anti-tank weapons,quadrotor drones,and tank models.Given the variability in multipath returns and boundary blurring,an adaptive multi-scale fea-ture extraction module was designed.Specifically,small-scale convolutional kernels were employed to capture fine-grained,high-amplitude features in single-path echoes,whereas large-scale kernels were used to extract global struc-tural information related to multiple propagation paths.Additionally,an attention mechanism was incorporated to effec-tively fuse salient multipath features with local scattering information,thereby enhancing classification accuracy under NLOS conditions.Finally,real-world measurements collected with a multipath radar sensing system were used for vali-dation.The experimental results demonstrate that the proposed network achieved a target classification accuracy of 99.6%.Comparative experiments confirmed the effectiveness and robustness of the proposed method.