Turn off MathJax
Article Contents
Article Navigation >  Journal of Radars  > 2026  > Proofreading [2nd]
WANG Jiahang, LIANG Junli, ZHU Wentao, et al. Aspect-matched waveform-classifier joint optimization for distributed radar target recognition[J]. Journal of Radars, in press. doi: 10.12000/JR25280
Citation: WANG Jiahang, LIANG Junli, ZHU Wentao, et al. Aspect-matched waveform-classifier joint optimization for distributed radar target recognition[J]. Journal of Radars, in press. doi: 10.12000/JR25280
shu

Aspect-matched Waveform-classifier Joint Optimization for Distributed Radar Target Recognition

DOI: 10.12000/JR25280 CSTR: 32380.14.JR25280
  • 1.

    School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710129, China

  • 2.

    AVIC Leihua Electronic Technology Research Institute, Wuxi 214000, China

Funds:  The National Natural Science Foundation of China(61471295, 62271403), China Postdoctoral Science Foundation (2024M764267), National Key Laboratory of Electromagnetic Space Security Open Fund
More Information
  • Corresponding author: LIANG Junli, liangjunli@nwpu.edu.cn
  • Received Date: 2025-12-30
  • Rev Recd Date: 2026-01-24
    • Available Online: 2026-01-31
    Abstract
  • The automatic target recognition performance of radar is critically dependent on the quality of features extracted from target echo signals. As the information carrier that actively shapes echo signals, the transmitted waveform substantially affects the target classification performance. However, conventional waveform design is often decoupled from classifier optimization, thereby ignoring the critical synergy between the two. This disconnect, combined with the lack of a direct link between waveform optimization criteria and task-specific classification metrics, limits the target classification performance. Most existing approaches are confined to monostatic radar models. Further, they fail to establish relationships between the target’s aspect angle, the transmitted waveform, and classification performance, and lack a cooperative waveform design mechanism among nodes. Hence, they are unable to achieve spatial and waveform diversity gains. To overcome these limitations, this paper proposes an end-to-end “waveform aspect matching” optimization framework for target classification in distributed radar systems. This framework parameterizes the waveform as a trainable waveform generation module, cascaded with a downstream classification network. This transforms the isolated waveform design problem into a joint optimization of the waveform and classifier, directly guided by the classification task. Leveraging prior target information, the model is trained to jointly optimize and produce aspect-matched waveforms along with the corresponding classification network. Furthermore, to enhance the classification performance in distributed radar systems, a dual-branch network based on noncausal state-space duality modules is proposed to extract and fuse multiview information. Experimental results demonstrate that the proposed method can synergistically utilize waveform and spatial diversity to improve the target classification performance. It demonstrates robustness against node failures, offering a novel solution for intelligent waveform design in distributed radar systems.

     

    • FullText(HTML)
  • loading
    • References(43)
  • [1]
    HE Hao, LI Jian, and STOICA P. Waveform Design for Active Sensing Systems: A Computational Approach[M]. Cambridge: Cambridge University Press, 2012. doi: 10.1017/CBO9781139095174.
    [2]
    BLUNT S D and MOKOLE E L. Overview of radar waveform diversity[J]. IEEE Aerospace and Electronic Systems Magazine, 2016, 31(11): 2–42. doi: 10.1109/MAES.2016.160071.
    [3]
    WANG Jiahang, LIANG Junli, CHENG Zhiwei, et al. Radar waveform design based on target pattern separability via fractional programming[J]. IEEE Transactions on Signal Processing, 2024, 72: 2543–2559. doi: 10.1109/TSP.2024.3387335.
    [4]
    HU Jinfeng, WEI Zhiyong, LI Yuzhi, et al. Designing Unimodular waveform(s) for MIMO radar by deep learning method[J]. IEEE Transactions on Aerospace and Electronic Systems, 2021, 57(2): 1184–1196. doi: 10.1109/TAES.2020.3037406.
    [5]
    ZHONG Kai, ZHANG Weijian, ZHANG Qiping, et al. MIMO radar waveform design via deep learning[C]. The IEEE Radar Conference, Atlanta, USA, 2021: 1–5. doi: 10.1109/RadarConf2147009.2021.9455163.
    [6]
    PEI Yaya, HU Jinfeng, ZHONG Kai, et al. MIMO radar waveform optimization by deep learning method[C]. The IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, 2022: 811–814. doi: 10.1109/IGARSS46834.2022.9884371.
    [7]
    XIA M, GONG W R, and YANG L C. A novel waveform optimization method for orthogonal-frequency multiple-input multiple-output radar based on dual-channel neural networks[J]. Sensors, 2024, 24(17): 5471. doi: 10.3390/s24175471.
    [8]
    YAN Bo, PAOLINI E, XU Luping, et al. A target detection and tracking method for multiple radar systems[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5114721. doi: 10.1109/TGRS.2022.3183387.
    [9]
    LU Jing, ZHOU Shenghua, PENG Xiaojun, et al. Distributed radar multiframe detection with local censored observations[J]. IEEE Transactions on Aerospace and Electronic Systems, 2024, 60(6): 9006–9028. doi: 10.1109/TAES.2024.3438103.
    [10]
    CAO Xiaomao, YI Jianxin, GONG Ziping, et al. Automatic target recognition based on RCS and angular diversity for multistatic passive radar[J]. IEEE Transactions on Aerospace and Electronic Systems, 2022, 58(5): 4226–4240. doi: 10.1109/TAES.2022.3159295.
    [11]
    PU Weiming, LIANG Zhennan, WU Jianxin, et al. Joint generalized inner product method for main lobe jamming suppression in distributed array radar[J]. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59(5): 6940–6953. doi: 10.1109/TAES.2023.3280892.
    [12]
    PU Weiming, ZHENG Ziming, TIAN Dezhi, et al. Velocity estimation of DRFM jamming source based on Doppler differences in distributed array radar[C]. The IET International Radar Conference, Chongqing, China, 2023: 387–392. doi: 10.1049/icp.2024.1110.
    [13]
    LINGADEVARU P, PARDHASARADHI B, and SRIHARI P. Sequential fusion based approach for estimating range gate pull-off parameter in a networked radar system: An ECCM algorithm[J]. IEEE Access, 2022, 10: 70902–70918. doi: 10.1109/ACCESS.2022.3185240.
    [14]
    BELL M R. Information theory and radar waveform design[J]. IEEE Transactions on Information Theory, 1993, 39(5): 1578–1597. doi: 10.1109/18.259642.
    [15]
    GARREN D A, OSBORN M K, ODOM A C, et al. Enhanced target detection and identification via optimised radar transmission pulse shape[J]. IEE Proceedings - Radar, Sonar and Navigation, 2001, 148(3): 130–138. doi: 10.1049/ip-rsn:20010324.
    [16]
    GARREN D A, OSBORN M K, ODOM A C, et al. Optimal transmission pulse shape for detection and identification with uncertain target aspect[C]. The IEEE Radar Conference, Atlanta, USA, 2001: 123–128. doi: 10.1109/NRC.2001.922963.
    [17]
    GARREN D A, ODOM A C, OSBORN M K, et al. Full-polarization matched-illumination for target detection and identification[J]. IEEE Transactions on Aerospace and Electronic Systems, 2002, 38(3): 824–837. doi: 10.1109/TAES.2002.1039402.
    [18]
    ROMERO R A, BAE J, and GOODMAN N A. Theory and application of SNR and mutual information matched illumination waveforms[J]. IEEE Transactions on Aerospace and Electronic Systems, 2011, 47(2): 912–927. doi: 10.1109/TAES.2011.5751234.
    [19]
    ALSHIRAH S Z, GISHKORI S, and MULGREW B. Frequency-based optimal radar waveform design for classification performance maximization using multiclass fisher analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(4): 3010–3021. doi: 10.1109/TGRS.2020.3008562.
    [20]
    DU Lan, LIU Hongwei, and BAO Zheng. Radar HRRP statistical recognition: Parametric model and model selection[J]. IEEE Transactions on Signal Processing, 2008, 56(5): 1931–1944. doi: 10.1109/TSP.2007.912283.
    [21]
    TAN Q J O, ROMERO R A, and JENN D C. Target recognition with adaptive waveforms in cognitive radar using practical target RCS responses[C]. The IEEE Radar Conference, Oklahoma City, USA, 2018: 0606–0611. doi: 10.1109/RADAR.2018.8378628.
    [22]
    WU Zhongjie, WANG Chnexu, LI Yingchun, et al. Extended target estimation and recognition based on multimodel approach and waveform diversity for cognitive radar[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5101014. doi: 10.1109/TGRS.2021.3065335.
    [23]
    GOYAL A and BENGIO Y. Inductive biases for deep learning of higher-level cognition[EB/OL]. https://doi.org/10.48550/arXiv.2011.15091, 2020.
    [24]
    BHALLA R, LING H, MOORE J, et al. 3D scattering center representation of complex targets using the shooting and bouncing ray technique: A review[J]. IEEE Antennas and Propagation Magazine, 1998, 40(5): 30–39. doi: 10.1109/74.735963.
    [25]
    DING Baiyuan and WEN Gongjian. Target reconstruction based ON 3-D scattering center model for robust SAR ATR[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(7): 3772–3785. doi: 10.1109/TGRS.2018.2810181.
    [26]
    LEI Wei, ZHANG Yue, and CHEN Zengping. A real‐time fine echo generation method of extended false target with radially high‐speed moving[J]. IET Radar, Sonar & Navigation, 2023, 17(2): 312–325. doi: 10.1049/rsn2.12342.
    [27]
    LIANG Junli, SO H C, LI Jian, et al. Unimodular sequence design based on alternating direction method of multipliers[J]. IEEE Transactions on Signal Processing, 2016, 64(20): 5367–5381. doi: 10.1109/TSP.2016.2597123.
    [28]
    VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]. The 31st International Conference on Neural Information Processing Systems, Long Beach, USA, 2017: 6000–6010.
    [29]
    FAN Wen, LIANG Junli, CHEN Zihao, et al. Spectrally compatible aperiodic sequence set design with low cross- and auto-correlation PSL[J]. Signal Processing, 2021, 183: 107960. doi: 10.1016/j.sigpro.2020.107960.
    [30]
    GU A and DAO T. Mamba: Linear-time sequence modeling with selective state spaces[EB/OL]. https://doi.org/10.48550/arXiv.2312.00752, 2023.
    [31]
    GU A, DAO T, EEMON S, et al. HiPPO: Recurrent memory with optimal polynomial projections[EB/OL]. https://doi.org/10.48550/arXiv.2008.07669, 2020.
    [32]
    GU A, GOEL K, and RÉ C. Efficiently modeling long sequences with structured state spaces[EB/OL]. https://doi.org/10.48550/arXiv.2111.00396, 2021.
    [33]
    GU A, JOHNSON I, GOEL K, et al. Combining recurrent, convolutional, and continuous-time models with linear state-space layers[C]. The 35th International Conference on Neural Information Processing System, Vancouver, Canada, 2021: 44.
    [34]
    DAO T and GU A. Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality[EB/OL]. https://doi.org/10.48550/arXiv.2405.21060, 2024.
    [35]
    GUO Jianyuan, HAN Kai, WU Han, et al. CMT: Convolutional neural networks meet vision transformers[EB/OL]. https://doi.org/10.48550/arXiv.2107.06263, 2021.
    [36]
    DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[C]. The 9th International Conference on Learning Representations, 2021.
    [37]
    SHI Yuheng, DONG Minjing, LI Mingjia, et al. VSSD: Vision Mamba with non-causal state space duality[EB/OL]. https://doi.org/10.48550/arXiv.2407.18559, 2024.
    [38]
    HAN Dongchen, WANG Ziyi, XIA Zhuofan, et al. Demystify Mamba in vision: A linear attention perspective[EB/OL]. https://doi.org/10.48550/arXiv.2405.16605, 2024.
    [39]
    ALTAIR. Feko (2023) [Electromagnetic simulation software][CP/OL]. https://www.altair.com/feko, 2023.
    [40]
    SDMS. Civilian vehicle data dome overview[DS/OL]. https://www.sdms.afrl.af.mil/index.php?collection=cv_dome, 2025.
    [41]
    HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. The IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 770–778. doi: 10.1109/CVPR.2016.90.
    [42]
    SIMONYAN K and ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]. The 3rd International Conference on Learning Representations, San Diego, USA, 2015: 1–14.
    [43]
    KRETSCHMER F F and GERLACH K. Low sidelobe radar waveforms derived from orthogonal matrices[J]. IEEE Transactions on Aerospace and Electronic Systems, 1991, 27(1): 92–102. doi: 10.1109/7.68151.
    • Relative Articles
    • Supplements(0)
    • Cited By
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索
    Get Citation
    PDF
    XML
    Article views(68) PDF downloads(10) Cited by()
    Proportional views
    Related

    京ICP备20021838号-14   Supported by: Beijing Renhe Information Technology Co. Ltd     百度统计

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return