属性散射中心 (attributed scattering center, ASC) 为合成孔径雷达 (synthetic aperture radar, SAR) 目标解译提供了关键的物理描述,但传统提取方法计算成本高昂且在复杂条件下性能受限。同时,多数深度学习方法仅限于目标分类等任务,其内部特征表示与物理散射机理的关联性较弱,且未能充分利用SAR数据的复数特性。为应对这些挑战,本文提出了一种名为实复数散射网络 (real-complex scattering network, RCS-Net) 的深度网络,旨在实现从SAR复数数据到 ASC 物理参数的端到端、高效、精确回归。RCS-Net的核心是1个专门设计的实复数U型架构,能够直接处理并有效利用幅相信息。本研究进一步提出一种由物理模型参数引导的训练策略：利用正交匹配追踪算法 (orthogonal matching pursuit, OMP) 离线生成 ASC参数作为监督信号,通过物理约束的多任务损失函数,驱动网络学习散射中心的位置、幅度和频率依赖因子等多维物理属性。在MSTAR数据集上的实验结果表明,与传统OMP方法相比,RCS-Net在推理效率上提升了近3个数量级,同时在参数估计精度和重建图像质量上均表现出优越性能,并展现了良好泛化能力。消融实验亦证实了实复数架构与物理参数引导策略的有效性。本研究为SAR图像的物理参数反演提供了一种高效的深度学习解决方案。
樊昱坤
,
许璐
,
王晨
,
田巳睿
,
张波
. 基于物理信息引导的实复数深度网络 SAR 属性散射中心提取方法*[J]. 中国科学院大学学报, 0
: 251230
.
DOI: 10.7523/j.ucas.2025.057
Attributed scattering center (ASC) provides crucial physical descriptions for the interpretation of synthetic aperture radar (SAR) targets. However, traditional extraction methods are computationally expensive and exhibit limited performance in complex scenarios. Concurrently, most deep learning approaches are confined to tasks such as target classification, with their internal feature representations showing a weak correlation to physical scattering mechanisms and failing to fully leverage the complex-valued nature of SAR data. To overcome these challenges, this paper proposes a deep network, named the real-complex scattering network (RCS-Net), to achieve end-to-end, efficient, and precise regression from SAR complex-valued data to ASC physical parameters. The core of RCS-Net is a custom-designed real-complex U-shaped architecture, which can directly process and effectively utilize both magnitude and phase information. This study further introduces a training strategy guided by physical model parameters: the orthogonal matching pursuit (OMP) algorithm is used to generate ASC parameters offline as supervisory signals. A physics-constrained multi-task loss function then drives the network to learn the multi-dimensional physical attributes of the scattering centers, including their position, amplitude, and frequency- dependent factors. Experimental results on the MSTAR dataset demonstrate that compared to the conventional OMP method, RCS-Net achieves a nearly three-orders-of-magnitude improvement in inference efficiency. It also shows superior performance in parameter estimation accuracy and the quality of reconstructed images, along with strong generalization capabilities. Ablation studies further validate the effectiveness of the real-complex architecture and the physics-guided training strategy. This research offers an efficient deep learning solution for the inversion of physical parameters from SAR images.
[1] Liao L Y, Du L, Chen J, et al.EMI-net: an end-to-end mechanism-driven interpretable network for SAR target recognition under EOCs[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: TGRS.2024. DOI: 10.1109/TGRS.2024.3362334
[2] Zhou Y, Li Y, Xie W T, et al.A convolutional neural network combined with attributed scattering centers for SAR ATR[J]. Remote Sensing, 2021, 13(24): 5121. DOI: 10.3390/rs13245121.
[3] 岳子瑜, 徐丰. 基于物理启发机器学习的属性散射中心提取方法[J]. 电子与信息学报, 2024, 46(5): 2036-2047. DOI:10.11999/JEIT231215.
[4] Yang H D, Huang Z L, Zhang Z.Interpretable attributed scattering center extracted via deep unfolding[C]//IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium. July 7-12, 2024, Athens, Greece. IEEE, 2024: 2004-2008. DOI: 10.1109/IGARSS53475.2024.10641709.
[5] 蒋文, 李王哲. 基于幅相分离的属性散射中心参数估计新方法[J]. 雷达学报,2019,8(5):606-615. DOI: 10.12000/JR18097.
[6] Tropp J A, Gilbert A C.Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007, 53(12): 4655-4666. DOI: 10.1109/TIT.2007.909108.
[7] Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition[C]//Proceedings of 27th Asilomar conference on signals, systems and computers. IEEE, 1993: 40-44. November 1-3,1993, Pacific Grove, California, United States. DOI: 10.1109/ACSSC.1993.342465.
[8] Kamilov U S, Goyal V K, Rangan S.Message-passing de-quantization with applications to compressed sensing[J]. IEEE Transactions on Signal Processing, 2012, 60(12): 6270-6281. DOI: 10.1109/TSP.2012. 2217334
[9] 李飞, 纠博, 刘宏伟, 等. 基于稀疏表示的 SAR 图像属性散射中心参数估计算法[J]. 电子与信息学报, 2014, 36(4): 931-937. DOI: 10.3724/SP.J.1146.2013.00576
[10] Blumensath T, Davies M E.Iterative thresholding for sparse approximations[J]. Journal of Fourier Analysis and Applications, 2008, 14(5): 629-654. DOI: 10.1007/s00041-008-9035-z.
[11] 计科峰. SAR图像目标特征提取与分类方法研究[D]. 长沙: 中国人民解放军国防科学技术大学, 2003.
[12] Chen S Z, Wang H P, Xu F, et al.Target classification using the deep convolutional networks for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8): 4806-4817. DOI: 10.1109/TGRS.2016.2551720.
[13] Ding J, Chen B, Liu H W, et al.Convolutional neural network with data augmentation for SAR target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(3): 364-368. DOI: 10.1109/LGRS.2015.2513754.
[14] Feng S J, Ji K F, Wang F L, et al.Electromagnetic scattering feature (ESF) module embedded network based on ASC model for robust and interpretable SAR ATR[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5235415. DOI: 10.1109/TGRS.2022.3208333.
[15] Trabelsi C, Bilaniuk O, Zhang Y, et al. Deep complex networks[EB]. arXiv:1705.09792, 2017.
[16] Potter L C, Moses R L.Attributed scattering centers for SAR ATR[J]. IEEE Transactions on Image Processing, 1997, 6(1): 79-91. DOI: 10.1109/83.552098.
[17] Gerry M J, Potter L C, Gupta I J, et al.A parametric model for synthetic aperture radar measurements[J]. IEEE Transactions on Antennas and Propagation, 1999, 47(7): 1179-1188. DOI: 10.1109/8.785750.
[18] Keydel E R, Lee S W, Moore J T.MSTAR extended operating conditions: a tutorial[C]//Algorithms for Synthetic Aperture Radar Imagery III. Orlando, FL. SPIE, 1996: 228-242. DOI: 10.1117/12.242059.
