基于迁移学习的SAR目标超分辨重建

doi:10.7527/S1000-6893.2014.0348

电子与控制

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于迁移学习的SAR目标超分辨重建

徐舟¹, 曲长文², 何令琪³

1. 电子工程学院雷达对抗系, 合肥 230000;
2. 海军航空工程学院电子信息工程系, 烟台 264001;
3. 北京大学软件与微电子学院, 北京 100871

收稿日期:2014-07-07 修回日期:2014-08-11 出版日期:2015-06-15 发布日期:2014-12-26
通讯作者: 曲长文 Tel.: 0535-6635080 E-mail: qcwwby@sohu.com E-mail:qcwwby@sohu.com
作者简介:徐舟男, 助教。主要研究方向: SAR信号处理、SAR图像超分辨技术。 E-mail: zhouzhou900521@126.com;曲长文男, 教授, 博士生导师。主要研究方向: SAR信号处理、SAR系统设计、无源定位技术。 Tel: 0535-6635080 E-mail: qcwwby@sohu.com
基金资助:
国家自然科学基金 (61102166); 山东省优秀中青年科学家科研奖励基金 (BS2013DX003)

SAR target super-resolution based on transfer learning

XU Zhou¹, QU Changwen², HE Lingqi³

1. Department of Radar Countermeasure, Electronic Engineering Institute, Heifei 230000, China;
2. Department of Electronic and Information Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China;
3. School of Software and Microelectronics, Peking University, Beijing 100871, China

Received:2014-07-07 Revised:2014-08-11 Online:2015-06-15 Published:2014-12-26
Supported by:
National Natural Science Foundation of China (61102166); Science Foundation for the Excellent Youth Scientist of ShanDong Province (BS2013DX003)

摘要/Abstract

摘要：

针对合成孔径雷达(SAR)目标超分辨重建问题,提出了一种基于迁移学习的超分辨方法。在光学图像梯度域中联合训练超完备字典与稀疏编码映射,利用半耦合字典联系SAR图像与光学图像,寻找SAR图像在半耦合字典下的稀疏编码,并在高分辨率字典下完成重建。结合SAR图像的先验信息,使用正则化方法对SAR目标进行特征增强。所提方法在TerraSAR-X数据和MSTAR数据上进行了仿真实验,重建结果表明,相比目前的插值方法和稀疏表示方法,所提方法空间分辨率可提高0.5~1.5个像素。正则化增强结果表明,引入稀疏先验的正则化增强能够进一步提高空间分辨率并抑制杂波比,最后分析了正则化参数的选取对图像质量的影响。

关键词: 合成孔径雷达, 超分辨, 迁移学习, 半耦合字典, 稀疏表示

Abstract:

Based on transfer learning, a method for synthetic aperture radar(SAR) target super-resolution reconstruction is proposed in this paper. A semi-coupled dictionary is jointly trained in the gradient domain of optical image. By utilizing the relationship revealed by semi-coupled dictionary, the sparse codes of SAR image are obtained. Then the image is reconstructed in the high resolution dictionary. Based on some prior knowledge of SAR image, the regularization method is also used in order to enhance the target feature. Several simulation experiments are conducted based on TerraSAR-X and MSTAR data, and the reconstructed results show that the spatial resolution obtained by the proposed method is 0.5-1.5 pixels higher compared to the current interpolation method as well as the sparse representation method. Regularization enhancement results show that it can further improve the spatial resolution and suppress clutters by introducing the sparse prior. Finally, the influences on the spatial resolution and target structure of the reconstruction image caused by regularization parameter are analyzed qualitatively.

Key words: synthetic aperture radar, super-resolution, transfer learning, semi-coupled dictionary, sparse representation

中图分类号:

徐舟, 曲长文, 何令琪. 基于迁移学习的SAR目标超分辨重建[J]. 航空学报, 2015, 36(6): 1940-1952.

XU Zhou, QU Changwen, HE Lingqi. SAR target super-resolution based on transfer learning[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2015, 36(6): 1940-1952.

参考文献

[1] Zhou J X, Shi G Z, Hu L, et al. Radar target one dimensional high resolution imaging based on sparse and non-uniform samplings in frequency domain[J]. Acta Electronica Sinica, 2012, 40(5): 926-934 (in Chinese). 周建雄, 石志广, 胡磊, 等. 基于频域稀疏非均匀采样的雷达目标一维高分辨成像[J]. 电子学报, 2012, 40(5): 926-934.
[2] Mao X H, Zhu D Y, Zhu Z D. 2-D autofocus algorithm for ultra-high resolution airborne spotlight SAR imaging[J]. Acta Aeronautica et Astronautica Sinica, 2012, 33(7): 1289-1295 (in Chinese). 毛新华, 朱岱寅, 朱兆达. 一种超高分辨率机载聚束SAR两维自聚焦算法[J]. 航空学报, 2012, 33(7): 1289-1295.
[3] Freeman W T, Jones T R, Pasztor E C. Example based super-resolution[J]. IEEE Computer Graphics and Applications, 2002, 22(2): 56-65.
[4] Mallat S, Yu G. Super-resolution with sparse mixing estimators[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2889-2900.
[5] Peleg T, Elad M. A statistical prediction model based on sparse representations for single image super-resolution[J]. IEEE Transactions on Image Processing, 2014, 23(6): 2569-2582.
[6] Yang J, Wang Z, Lin Z, et al. Coupled dictionary training for image super-resolution[J]. IEEE Transactions on Image Processing, 2012, 21(8): 3467-3477.
[7] Yang J, Wright J, Huang T S, et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2851-2873.
[8] Zeyde R, Elad M, Protter, M. On single image scale-up using sparse-representations [C]//Proceedings of the 7th International Conference on Curves and Surfaces, Avignon, Berlin: Springer Berlin Heidelberg, 2010, 711-730.
[9] Dong W S, Zhang L, Shi G M, et al. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization[J]. IEEE Transactions on Image Processing, 2011, 20(7): 1838-1857.
[10] Wang S L, Zhang L, Liang Y, et al. Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence. Piscataway, NJ: IEEE Press, 2012, 2216-2223.
[11] Aharon M, Elad M, Bruckstein A. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Signal Processing, 2006, 54(11): 4311-4322.
[12] Beck A, Teboulle M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems[J]. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202.
[13] Efron B, Hastie T, Johnstone I, et al. Least angle regression[J]. The Annals of Statistics, 2004, 32(2): 407-499.
[14] Wang J H, Huang Z T, Zhou Y Y, et al. Robust sparse recovery based on approximate l₀ norm[J]. Acta Electronica Sinica, 2012, 40(6): 1185-1189 (in Chinese). 王军华, 黄知涛, 周一宇, 等. 基于近似l₀范数的稳健稀疏重构算法[J]. 电子学报, 2012, 40(6): 1185-1189.
[15] Fergus R, Singh B, Hertzmann A, et al. Removing camera shake from a single photograph[J]. ACM Transactions on Graphics, 2006, 25(3): 787-794.
[16] Gao G. Statistical modeling of SAR images: A survey[J]. Sensors, 2010, 10(1): 775-795.
[17] Cho S, Lee S. Fast motion deblurring[J]. ACM Transactions on Graphics 2009, 28(5): 145-152.
[18] Hansen P, Nagy J, O'leary D. Deblurring images: Matrices, spectra, and filtering[M]. Philadelphia: SIAM, 2006: 33-51.
[19] Figueiredo M, Nowak R, Wright S. Gradient projection for sparse reconstruction: application to compressed sensing and other inverse problems[J]. IEEE Journal of Selected Topics in Signal Processing, 2007, 1(4): 586-597.
[20] Cetin M. Feature-enhanced synthetic aperture radar imaging[D]. Manchester: University of Stanford, 2001:142-146.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于迁移学习的SAR目标超分辨重建

SAR target super-resolution based on transfer learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	叶铮, 朱岱寅, 吴迪. 一种基于重叠子孔径回波信息的SAR图像配准算法[J]. 航空学报, 2023, 44(8): 327254-327254.
[2]	邹昕, 李明磊, 朱岱寅, 饶炜, 韩承志, 李莹. 火星降落伞开伞过程形态参数辨识与应用[J]. 航空学报, 2023, 44(6): 227007-227007.
[3]	于功也, 蔡伟东, 胡明辉, 刘文才, 马波. 故障机理与领域自适应混合驱动的机械故障智能迁移诊断[J]. 航空学报, 2023, 44(2): 426800-426800.
[4]	罗皓文, 何绍溟, 金天宇, 刘子超. 基于迁移学习的角度约束时间最短制导算法[J]. 航空学报, 2023, 44(19): 328400-328400.
[5]	纪朋徽, 邢世其, 代大海, 庞礴, 冯德军. SAR距离卷积方位乘积调制场景欺骗干扰方法[J]. 航空学报, 2023, 44(18): 328235-328235.
[6]	王莲子, 汪玲, 朱岱寅. 结合迁移学习基于全卷积神经网络的ISAR自聚焦算法[J]. 航空学报, 2023, 44(17): 328172-328172.
[7]	王育鹏, 吕帅帅, 杨宇, 李嘉欣, 王叶子. 基于域自适应的复合材料结构损伤识别方法[J]. 航空学报, 2022, 43(6): 526752-526752.
[8]	鲍悦, 陈俊宇, 施天玥, 毛新华. 基于先验误差模型的机载高分宽幅DBF-SAR自聚焦算法[J]. 航空学报, 2021, 42(6): 324502-324502.
[9]	江波, 屈若锟, 李彦冬, 李诚龙. 基于深度学习的无人机航拍目标检测研究综述[J]. 航空学报, 2021, 42(4): 524519-524519.
[10]	牟金震, 刘宗明, 韩飞, 周彦, 李爽. 失效卫星远距离相对位姿估计与优化方法[J]. 航空学报, 2021, 42(11): 524959-524959.
[11]	卢景月, 张磊, 孟智超, 盛佳恋. 曲线轨迹下前视多通道SAR解模糊成像算法[J]. 航空学报, 2019, 40(7): 322745-322745.
[12]	史林, 韩宁, 宋祥君, 王立兵, 崔东辉. 基于虚拟慢时间的双基地ISAR成像算法[J]. 航空学报, 2019, 40(5): 322683-322683.
[13]	郭宝锋, 孙慧贤, 胡文华, 尹文龙, 陈关军. 双基地角时变下的ISAR等效旋转中心估计[J]. 航空学报, 2019, 40(3): 322432-322432.
[14]	韩宁, 李宝晨, 王立兵, 童俊, 郭宝锋. 基于稀疏分解的空间目标双基地ISAR自聚焦算法[J]. 航空学报, 2018, 39(8): 322037-322037.
[15]	朱晓秀, 胡文华, 马俊涛, 郭宝锋, 薛东方. 双基地角时变下的ISAR稀疏孔径自聚焦成像[J]. 航空学报, 2018, 39(8): 322059-322059.