A Novel SAR Super-Resolution Method via Signal Extrapolation and Hierarchical Learning

WANG Yan; WANG Xiao; GAO Yuyang; DONG Ganggang

doi:10.12263/DZXB.20250767

您当前的位置：

首页 >

文章列表页 >

A Novel SAR Super-Resolution Method via Signal Extrapolation and Hierarchical Learning

PAPERS | 更新时间：2026-05-28

- A Novel SAR Super-Resolution Method via Signal Extrapolation and Hierarchical Learning
- ACTA ELECTRONICA SINICA Vol. 54, Issue 2, Pages: 601-610(2026)
- 作者机构：
  
  西安电子科技大学雷达信号处理全国重点实验室，陕西西安 710071
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(61971324;62571400)
- DOI：10.12263/DZXB.20250767
  CLC： TN95;
- Received：04 September 2025，
  
  Accepted：04 February 2026，
  
  Published：25 February 2026
- 稿件说明：
移动端阅览
王焱, 王潇, 高宇洋, 等. 一种信号外推和层级学习SAR超分辨率方法[J]. 电子学报, 2026, 54(02): 601-610.

WANG Yan, WANG Xiao, GAO Yuyang, et al. A Novel SAR Super-Resolution Method via Signal Extrapolation and Hierarchical Learning[J]. Acta Electronica Sinica, 2026, 54(02): 601-610.
王焱, 王潇, 高宇洋, 等. 一种信号外推和层级学习SAR超分辨率方法[J]. 电子学报, 2026, 54(02): 601-610. DOI：10.12263/DZXB.20250767

WANG Yan, WANG Xiao, GAO Yuyang, et al. A Novel SAR Super-Resolution Method via Signal Extrapolation and Hierarchical Learning[J]. Acta Electronica Sinica, 2026, 54(02): 601-610. DOI：10.12263/DZXB.20250767

摘要

成像分辨率是合成孔径雷达（Synthetic Aperture Radar， SAR）系统最为重要的指标参数，更高分辨能力的成像结果能显著提升图像层次，使得目标轮廓、纹理及散射特性更清晰，有效抑制相干斑噪声对细节的污染，从而为下游图像解译与信息提取提供更稳健的底层物理表征。经验理论建模的方法物理意义清晰、理论推导严密，但在拟合实际数据时容易出现模型失配，且忽略历史信息。先验数据驱动的方法特征表示与数据拟合能力强，但无法考虑相干成像原理，理论可解释性差。对此，提出一种信号外推与层级融合的SAR单视复图像超分辨率新方法。首先，根据SAR成像原理进行频域补零的信号外推，完成初始对齐任务，实现理论可解释外推。其次，在此基础上设计包括双模交叉学习特征学习和精细化特征融合重建的超分辨率专属学习框架，通过卷积与Transformer的双模交叉学习机制，从初始对齐图像挖掘高层语义表征与细节电磁特征，其中卷积分支用于局部特征学习，Transformer分支用于长时窗依赖建模，并设计残差跨层特征融合完成精细重建，实现SAR单视复图超分辨率重建。最后，针对通用指标无法对SAR成像质量进行全面客观评价的问题，构建SAR超分辨率评价体系，从可视化聚焦、点目标成像、相位保真度等维度客观评价重建结果。利用实测数据开展大量实验验证，结果表明所提方法可提高峰值信噪比（Peak Signal-to-noise Ratio，PSNR）6.27 dB，同时降低峰值旁瓣比5.85 dB。

Abstract

The quality of SAR imaging was important for the downstream tasks. The classical methods were relied on the parameterized models to fit the measured data

and hence suffered from mismatch. The learning-driven methods ignored the coherent imaging mechanism and phase information. To solve these problems

a new complex-valued SAR image super-resolution method via signal extrapolation and hierarchical learning was proposed in this paper. It was composed of three phases

signal extrapolation

dual-mode cross learning

and hierarchical fusion. The spatial alignment of amplitude and phase was first achieved by the imaging operation on the zero-padded frequencies. Then

a cross learning of convolution and Transformer was employed to capture the high-level semantic information. Finally

the high-resolution SAR image was formed by feature refinement. On this basis

an evaluation system composed of the vision metrics

the imaging metrics

and the phase congruency were presented. Extensive rounds of experiments demonstrated that the proposed method improved the peak signal-to-noise ratio (PSNR) by 6.27 dB

the peak sidelobe ratio (PSLR) by 5.85 dB.

关键词

Keywords

references

杨汝良 . 高分辨率微波成像 [M ] . 北京 : 国防工业出版社 , 2013 .

Yang Ruliang . High resolution microwave imaging [M ] . Beijing : National Defense Industry Press , 2013 . (in Chinese)

董刚刚 , 匡纲要 , 刘宏伟 . 合成孔径雷达目标识别 [M ] . 北京 : 人民邮电出版社 , 2026 .

Dong Ganggang , Kuang Gangyao , Liu Hongwei . Synthetic aperture radar target recognition [M ] . Beijing : Posts & Telecom Press , 2026 .

Zhao Guowei . Jiang Jiaqing. Dong Ganggang, et al. SAR ship detection via knowledge transfer: From optical image[J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2025 , 18 : 17526 - 17538 . DOI: 10.1109/jstars.2025.3582808 http://dx.doi.org/10.1109/jstars.2025.3582808

赵国威 , 蒋嘉庆 , 董刚刚 . 跨模态渐进式知识迁移SAR目标检测技术 [J ] . 电子学报 , 2025 , 53 ( 9 ): 3147 - 3162 .

Zhao Guowei , Jiang Jiaqing , Dong Ganggang . Cross-modal SAR target detection via progressive knowledge transfer [J ] . Acta Electronica Sinica , 2025 , 53 ( 9 ): 3147 - 3162 . (in Chinese)

Brito A E , Chan S H , Cabrera S D . SAR image superresolution via 2-D adaptive extrapolation [J ] . Multidimensional Systems and Signal Processing , 2003 , 14 ( 1/2/3 ): 83 - 104 . DOI: 10.1023/a:1022221024995 http://dx.doi.org/10.1023/a:1022221024995

张平 , 杨汝良 . 合成孔径雷达空间变迹带宽外推超分辨算法 [J ] . 测绘学报 , 2010 , 39 ( 1 ): 71 - 75 .

Zhang Ping , Yang Ruliang . A new SAR superresolution algorithm based on apodization extrapolation [J ] . Acta Geodaetica et Cartographica Sinica , 2010 , 39 ( 1 ): 71 - 75 . (in Chinese)

Biondi F . Recovery of partially corrupted SAR images by super-resolution based on spectrum extrapolation [J ] . IEEE Geoscience and Remote Sensing Letters , 2017 , 14 ( 2 ): 139 - 143 . DOI: 10.1109/lgrs.2016.2615564 http://dx.doi.org/10.1109/lgrs.2016.2615564

He Chu , Liu Longzhu , Xu Lianyu , et al . Learning based compressed sensing for SAR image super-resolution [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2012 , 5 ( 4 ): 1272 - 1281 . DOI: 10.1109/jstars.2012.2189555 http://dx.doi.org/10.1109/jstars.2012.2189555

王伟伟 , 廖桂生 , 张磊 , 等 . 一种基于压缩感知的稀疏孔径SAR成像方法 [J ] . 电子学报 , 2012 , 40 ( 12 ): 2487 - 2494 .

Wang Weiwei , Liao Guisheng , Zhang Lei , et al . An imaging method based on compressive sensing for sparse aperture of SAR [J ] . Acta Electronica Sinica , 2012 , 40 ( 12 ): 2487 - 2494 . (in Chinese)

Lim B , Son S , Kim H , et al . Enhanced deep residual networks for single image super-resolution [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops . Piscataway : IEEE , 2017 : 1132 - 1140 . DOI: 10.1109/cvprw.2017.151 http://dx.doi.org/10.1109/cvprw.2017.151

Zhang Yulun , Li Kunpeng , Li Kai , et al . Image super-resolution using very deep residual channel attention networks [C ] // Computer Vision - ECCV 2018 . Cham : Springer , 2018 : 294 - 310 . DOI: 10.1007/978-3-030-01234-2_18 http://dx.doi.org/10.1007/978-3-030-01234-2_18

Ledig C , Theis L , Huszár F , et al . Photo-realistic single image super-resolution using a generative adversarial network [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 105 - 114 . DOI: 10.1109/cvpr.2017.19 http://dx.doi.org/10.1109/cvpr.2017.19

He Xuming , Zhou Zhiwang , Zhang Wenlong , et al . DiffSR: Learning radar reflectivity synthesis via diffusion model from satellite observations [C ] // ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2025 : 10888161 . DOI: 10.1109/icassp49660.2025.10888161 http://dx.doi.org/10.1109/icassp49660.2025.10888161

Shen Jingyi , Shen Hanwei . PSRFlow: Probabilistic super resolution with flow-based models for scientific data [J ] . IEEE Transactions on Visualization and Computer Graphics , 2024 , 30 ( 1 ): 986 - 996 .

王国栋 , 周荫清 , 李春升 . SAR图像超分辨与点扩展函数扰动校正算法 [J ] . 北京航空航天大学学报 , 2000 , 26 ( 6 ): 640 - 643 .

Wang Guodong , Zhou Yinqing , Li Chunsheng . SAR Bayesian super-resolution algorithm with a correction of perturbed point spread function [J ] . Journal of Beijing University of Aeronautics and Astronautics , 2000 , 26 ( 6 ): 640 - 643 . (in Chinese)

王正明 , 朱炬波 , 谢美华 . SAR图像提高分辨率技术 [M ] . 2版 . 北京 : 科学出版社 , 2013 .

Wang Zhengming , Zhu Jubo , Xie Meihua . Technique of SAR image superresolution [M ] . 2nd ed . Beijing : Science Press , 2013 . (in Chinese)

Zamir S W , Arora A , Khan S , et al . Restormer: Efficient transformer for high-resolution image restoration [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 5718 - 5729 . DOI: 10.1109/cvpr52688.2022.00564 http://dx.doi.org/10.1109/cvpr52688.2022.00564

Li Ao , Zhang Le , Liu Yun , et al . Feature modulation transformer: Cross-refinement of global representation via high-frequency prior for image super-resolution [C ] // 2023 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2023 : 12480 - 12490 . DOI: 10.1109/iccv51070.2023.01150 http://dx.doi.org/10.1109/iccv51070.2023.01150

Zhang Xindong , Zeng Hui , Guo Shi , et al . Efficient long-range attention network for image super-resolution [M ] // Computer Vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 649 - 667 . DOI: 10.1007/978-3-031-19790-1_39 http://dx.doi.org/10.1007/978-3-031-19790-1_39

周登文 , 李文斌 , 李金新 , 等 . 一种轻量级的多尺度通道注意图像超分辨率重建网络 [J ] . 电子学报 , 2022 , 50 ( 10 ): 2336 - 2346 .

Zhou Dengwen , Li Wenbin , Li Jinxin , et al . Image super-resolution reconstruction based on lightweight multi-scale channel attention network [J ] . Acta Electronica Sinica , 2022 , 50 ( 10 ): 2336 - 2346 . (in Chinese)

Kim J , Oh J , Lee K M . Beyond image super-resolution for image recognition with task-driven perceptual loss [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 2651 - 2661 . DOI: 10.1109/cvpr52733.2024.00256 http://dx.doi.org/10.1109/cvpr52733.2024.00256

吕彤光 , 陆仲良 , 粟毅 , 等 . 冲激信号SAR成像的方位分辨率分析 [J ] . 电子学报 , 2000 , 28 ( 6 ): 40 - 43 .

Lü Tongguang , Lu Zhongliang , Su Yi , et al . The analysis of the azimuth resolution of impulse signal SAR [J ] . Acta Electronica Sinica , 2000 , 28 ( 6 ): 40 - 43 . (in Chinese)

Wang Zhou , Bovik A C , Sheikh H R , et al . Image quality assessment: From error visibility to structural similarity [J ] . IEEE Transactions on Image Processing , 2004 , 13 ( 4 ): 600 - 612 . DOI: 10.1109/tip.2003.819861 http://dx.doi.org/10.1109/tip.2003.819861

Zhang R , Isola P , Efros A A , et al . The unreasonable effectiveness of deep features as a perceptual metric [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 586 - 595 . DOI: 10.1109/cvpr.2018.00068 http://dx.doi.org/10.1109/cvpr.2018.00068

Kusano S , Sato M , Yokota Y . Data interpolation and resampling for a synthetic aperture radar data [C ] // 2011 IEEE International Geoscience and Remote Sensing Symposium . Piscataway : IEEE , 2011 : 652 - 655 . DOI: 10.1109/igarss.2011.6049213 http://dx.doi.org/10.1109/igarss.2011.6049213

Parker J A , Kenyon R V , Troxel D E . Comparison of interpolating methods for image resampling [J ] . IEEE Transactions on Medical Imaging , 1983 , 2 ( 1 ): 31 - 39 . DOI: 10.1109/tmi.1983.4307610 http://dx.doi.org/10.1109/tmi.1983.4307610

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Cross-Modal SAR Target Detection via Progressive Knowledge Transfer

An Extrapolation Algorithm for Band-Limited Signals Based on Alternating Projection Neural Networks

A New Rogularized Extrapolation Algorithm for Band-Limited Signal High-Frequency Reconstruction

Robust Node-Specific Distributed Generalized Sidelobe Canceler for Outdoor Multi-Source Enhancement

Attention Penalty and Adaptive Learning Scene Graph for Joint Multimodal Aspect-Based Sentiment Analysis

Related Author

ZHAO Guo-wei

JIANG Jia-qing

DONG Gang-gang

Wang Jin-gen

Lin Chun-sheng

Gong Shen-guang

齐忠涛

王晓东

Related Institution

The Naval University of Engineering

Unisoft Institute,Sub No.1,17,Zhonghuabeidajie, Shijiazhuang 050000) Wang Xiaodong

河北七一七发射台

⁰