There are many types of radar active deception false target jamming that are highly correlated with the real target.Recognizing the real and false targets under a low Signal-to-Noise Ratio(SNR)is difficult.To solve th...There are many types of radar active deception false target jamming that are highly correlated with the real target.Recognizing the real and false targets under a low Signal-to-Noise Ratio(SNR)is difficult.To solve the above problem,this article proposes a real/false target recognition method based on the features of multi-pulse joint frequency response by analyzing the differences in the scattering characteristics and modeling real target echoes as a synthesis of multi-scattering center echoes.Firstly,in the range-doppler domain,the real and false targets are truncated along the range dimension,and a fast Fourier transform is performed to extract the features of multi-pulse joint frequency response.Then,a two-channel feature fusion network is designed for real and false target recognition.Finally,a Multi-Coherent Processing Interval Joint Decision Method(M-CPIJDM)based on temporal information is proposed to improve the recognition performance.Experiments using the measured data show that the proposed method can well recognize real and false target signals under four jamming backgrounds:distance false target,velocity false target,distance-velocity composite false target,and forwarding dense false target.展开更多
基金supported by the Basic Research Program,China(No.514010503-208)the China Aerospace Science and Technology Corporation Stabilization Support Project(No.ZY0110020009)the Equipment Pre-research Project,China(No.304060201).
文摘There are many types of radar active deception false target jamming that are highly correlated with the real target.Recognizing the real and false targets under a low Signal-to-Noise Ratio(SNR)is difficult.To solve the above problem,this article proposes a real/false target recognition method based on the features of multi-pulse joint frequency response by analyzing the differences in the scattering characteristics and modeling real target echoes as a synthesis of multi-scattering center echoes.Firstly,in the range-doppler domain,the real and false targets are truncated along the range dimension,and a fast Fourier transform is performed to extract the features of multi-pulse joint frequency response.Then,a two-channel feature fusion network is designed for real and false target recognition.Finally,a Multi-Coherent Processing Interval Joint Decision Method(M-CPIJDM)based on temporal information is proposed to improve the recognition performance.Experiments using the measured data show that the proposed method can well recognize real and false target signals under four jamming backgrounds:distance false target,velocity false target,distance-velocity composite false target,and forwarding dense false target.