基于结构化字典学习的判别稀疏微波成像方法

doi:10.12305/j.issn.1001-506X.2025.01.10

系统工程与电子技术 ›› 2025, Vol. 47 ›› Issue (1): 94-100.doi: 10.12305/j.issn.1001-506X.2025.01.10

基于结构化字典学习的判别稀疏微波成像方法

孟洋¹^,²^,³, 周国如¹^,²^,³, 李洁¹^,²^,³, 张冰尘¹^,²^,³^,*

1. 中国科学院空天信息创新研究院, 北京 100094
2. 中国科学院空间信息处理与应用系统技术重点实验室, 北京 100190
3. 中国科学院大学电子电气与通信工程学院, 北京 100049

收稿日期:2023-12-27 出版日期:2025-01-21 发布日期:2025-01-25
通讯作者: 张冰尘
作者简介:孟洋(1999—), 男, 硕士研究生, 主要研究方向为SAR信号处理、字典学习
周国如(1997—), 女, 博士研究生, 主要研究方向为SAR信号处理、压缩感知、稀疏SAR成像
李洁(1996—), 女, 博士研究生, 主要研究方向为TomoSAR信号处理、深度学习
张冰尘(1973—), 男, 研究员, 博士, 主要研究方向为雷达系统、雷达信号处理、新体制雷达

Discriminative sparse microwave imaging method based on structured dictionary learning

Yang MENG¹^,²^,³, Guoru ZHOU¹^,²^,³, Jie LI¹^,²^,³, Bingchen ZHANG¹^,²^,³^,*

1. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2. Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing 100190, China
3. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2023-12-27 Online:2025-01-21 Published:2025-01-25
Contact: Bingchen ZHANG

摘要/Abstract

摘要：

基于字典学习的合成孔径雷达(synthetic aperture radar, SAR)稀疏微波成像方法面对多类别目标时, 字典中存在冗余信息导致成像准确性降低, 针对此问题提出一种基于结构化字典学习(structured dictionary learning, SDL)的判别稀疏微波成像方法。首先, 利用SDL面向多类别目标训练获得包含多个子字典的结构化字典, 每个子字典对应特定类别目标。其次, 结合结构化字典构建判别稀疏微波成像模型, 处理过程中根据不同子字典对目标的表征误差进行判别。最后, 根据判别结果选择对应类别子字典进行成像。实验结果表明, 与现有的成像方法相比, 所提算法在降采样的条件下能够更好地抑制伪影模糊, 提高成像的准确性。

关键词: 结构化字典学习, 合成孔径雷达, 稀疏微波成像, 稀疏表征

Abstract:

When dealing with multi-class targets, the sparse microwave imaging method of synthetic aperture radar (SAR) based on dictionary learning has redundant information in the dictionary, which leads to a decrease in imaging accuracy. To address this problem, a discriminative sparse microwave imaging method based on structured dictionary learning (SDL) is proposed. Firstly, using SDL to train for multi-class targets, a structured dictionary containing multiple sub-dictionaries is obtained, with each sub dictionary corresponding to a specific category of targets. Secondly, a discriminative sparse microwave imaging model is constructed by combining structured dictionaries, and the representation errors of the target are distinguished based on different sub-dictionaries during the processing. Finally, based on the discrimination results, the corresponding category sub-dictionary is selected for imaging. The experimental results show that compared with existing imaging methods, the proposed algorithm can better suppress artifact blurring and improve imaging accuracy under downsampling conditions.

Key words: structured dictionary learning (SDL), synthetic aperture radar (SAR), sparse microwave imaging, sparse representation

中图分类号:

TN957.52

孟洋, 周国如, 李洁, 张冰尘. 基于结构化字典学习的判别稀疏微波成像方法[J]. 系统工程与电子技术, 2025, 47(1): 94-100.

Yang MENG, Guoru ZHOU, Jie LI, Bingchen ZHANG. Discriminative sparse microwave imaging method based on structured dictionary learning[J]. Systems Engineering and Electronics, 2025, 47(1): 94-100.

图/表 5

图1

图2

表1

图3

表2

参考文献 30

1	MOREIRA A , PRATS-IRAOLA P , YOUNIS M , et al. A tutorial on synthetic aperture radar[J]. IEEE Geoscience and Remote Sensing Magazine, 2013, 1 (1): 6- 43. doi: 10.1109/MGRS.2013.2248301
2	ZHANG B C , HONG W , WU Y R . Sparse microwave imaging: principles and applications[J]. SCIENCE CHINA Information Sciences, 2012, 55 (8): 1722- 1754. doi: 10.1007/s11432-012-4633-4
3	吴一戎, 洪文, 张冰尘. 稀疏微波成像导论[M]. 北京: 科学出版社, 2018.
	WU Y R , HONG W , ZHANG B C . Introduction to sparse microwave imaging[M]. Beijing: Science Press, 2018.
4	XU G , ZHANG B J , YU H W , et al. Sparse synthetic aperture radar imaging from compressed sensing and machine learning: theories, applications, and trends[J]. IEEE Geoscience and Remote Sensing Magazine, 2022, 10 (4): 32- 69. doi: 10.1109/MGRS.2022.3218801
5	DONOHO D L . Compressed sensing[J]. IEEE Trans.on Information Theory, 2006, 52 (4): 1289- 1306. doi: 10.1109/TIT.2006.871582
6	沈笑云, 廖仙华, 孙卫天, 等. 可变先验贝叶斯学习稀疏SAR成像[J]. 系统工程与电子技术, 2021, 43 (7): 1781- 1790. doi: 10.12305/j.issn.1001-506X.2021.07.07
	SHEN X Y , LIAO X H , SUN W T , et al. Sparse SAR imaging based on varying prior Bayes learning[J]. Systems Engineering and Electronics, 2021, 43 (7): 1781- 1790. doi: 10.12305/j.issn.1001-506X.2021.07.07
7	SAMADI S , CETIN M , MASNADI-SHIRAZI M A . Sparse representation-based synthetic aperture radar imaging[J]. IET Radar, Sonar & Navigation, 2011, 5 (2): 182- 193.
8	HU C Y , WANG L , ZHU D Y , et al. Inverse synthetic aperture radar sparse imaging exploiting the group dictionary learning[J]. Remote Sensing, 2021, 13 (14): 2812. doi: 10.3390/rs13142812
9	NASH C, MENICK J, DIELEMAN S, et al. Generating images with sparse representations[EB/OL]. [2023-11-27]. https://arxiv.org/abs/2103.03841.
10	NANAVATI S P , PANIGRAHI P K . Wavelet transform[J]. Resonance, 2004, 9 (3): 50- 64. doi: 10.1007/BF02834988
11	SAMADI S , CETIN M , MASNADI-SHIRAZI M A . Multiple feature-enhanced SAR imaging using sparsity in combined dictionaries[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 10 (4): 821- 825.
12	SAMADI S, CETIN M, MASNADI-SHIRAZI M A. Multiple feature-enhanced synthetic aperture radar imaging[C]//Proc. of the Comference on Algorithms for Synthetic Aperture Radar Imagery XVI, 2009.
13	熊世超, 倪嘉成, 张群, 等. 基于混合稀疏表示的二维压缩感知SAR成像[J]. 北京航空航天大学学报, 2022, 48 (11): 2314- 2324.
	XIONG S C , NI J C , ZHANG Q , et al. 2-D compressed sensing SAR imaging based on mixed sparse representation[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48 (11): 2314- 2324.
14	AKHAVAN S , BAGHESTANI F , KAZEMI P , et al. Dictio-nary learning for sparse representation of signals with hidden Markov model dependency[J]. Digital Signal Processing, 2022, 123, 103420. doi: 10.1016/j.dsp.2022.103420
15	NG S M , YAZID H , MUSTAFA N . Performance analysis on dictionary learning and sparse representation algorithms[J]. Multimedia Tools and Applications, 2022, 81 (12): 16455- 16476. doi: 10.1007/s11042-022-12375-4
16	ENGAN K, AASE S O, HUSOY J H. Method of optimal directions for frame design[C]//Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 1999: 2443-2446.
17	AHARON M , ELAD M , BRUCKSTEIN A . K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Trans.on Signal Processing, 2006, 54 (11): 4311- 4322. doi: 10.1109/TSP.2006.881199
18	SOGANLUI A, CETIN M. Dictionary learning for sparsity-driven SAR image reconstruction[C]// Proc. of the IEEE International Conference on Image Processing, 2014.
19	胡长雨, 汪玲, 朱栋强. 结合字典学习技术的ISAR稀疏成像方法[J]. 电子与信息学报, 2019, 41 (7): 1735- 1742.
	HU C Y , WANG L , ZHU D Q . Sparse ISAR imaging exploiting dictionary learning[J]. Journal of Electronics & Information Technology, 2019, 41 (7): 1735- 1742.
20	FARHANGKHAH N , SAMADI S , KHOSRAVI M R , et al. Overcomplete pre-learned dictionary for incomplete data SAR imaging towards pervasive aerial and satellite vision[J]. Wireless Networks, 2024, 30 (5): 3989- 4001. doi: 10.1007/s11276-021-02821-w
21	LIU Q P , CHENG Y Q , CAO K C , et al. Radar forward-looking imaging for complex targets based on sparse representation with dictionary learning[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19, 4026605.
22	YANG M , ZHANG L , FENG X C , et al. Sparse representation based fisher discrimination dictionary learning for image classification[J]. International Journal of Computer Vision, 2014, 109 (3): 209- 232. doi: 10.1007/s11263-014-0722-8
23	YÜCE G, ORTIZ-JIMÉNEZ G, BESBINAR B, et al. A structured dictionary perspective on implicit neural representations[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022.
24	DU H A , ZHANG Y G , MA L G , et al. Structured discriminant analysis dictionary learning for pattern classification[J]. Knowledge-Based Systems, 2021, 216, 106794. doi: 10.1016/j.knosys.2021.106794
25	CANDES E J , ROMBERG J K , TAO T . Stable signal recovery from incomplete and inaccurate measurements[J]. Communications on Pure and Applied Mathematics, 2006, 59 (8): 1207- 1223. doi: 10.1002/cpa.20124
26	BI H , BI G A , ZHANG B C , et al. Complex-image-based sparse SAR imaging and its equivalence[J]. IEEE Trans.on Geoscience and Remote Sensing, 2018, 56 (9): 5006- 5014. doi: 10.1109/TGRS.2018.2803802
27	TIBSHIRANI R . Regression shrinkage and selection via the Lasso[J]. Journal of the Royal Statistical Society Series B: Statistical Methodology, 1996, 58 (1): 267- 288. doi: 10.1111/j.2517-6161.1996.tb02080.x
28	DAUBECHIES I , DEFRISE M , DE-MOL C . An iterative thresholding algorithm for linear inverse problems with a sparsity constraint[J]. Communications on Pure and Applied Mathematics, 2004, 57 (11): 1413- 1457. doi: 10.1002/cpa.20042
29	CUMMING I G , WONG F H . Digital processing of synthetic aperture radar data[M]. Boston: Artech House, 2005.
30	WANG Z , BOVIK A C , SHEIKH H R , et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Trans.on Image Processing, 2004, 13 (4): 600- 612. doi: 10.1109/TIP.2003.819861

仿真场景	采样率/%	匹配滤波	KSVD	本文算法
仿真场景	采样率/%	PSNR/SSIM	PSNR/SSIM	PSNR/SSIM
1	30	8.98/0.09	18.87/0.84	20.03/0.87
	50	13.39/0.65	18.92/0.91	20.31/0.91
	70	19.61/0.85	23.24/0.94	25.16/0.97
2	30	8.79/0.18	17.20/0.72	18.99/0.76
2	50	15.58/0.57	20.67/0.87	25.24/0.91
70	19.81/0.72	22.71/0.90	25.93/0.94
3	30	8.48/0.11	18.87/0.73	20.65/0.77
	50	15.99/0.57	20.07/0.86	24.17/0.88
	70	20.54/0.71	23.21/0.90	25.72/0.94
4	30	8.85/0.25	16.29/0.64	19.81/0.67
	50	15.59/0.46	20.33/0.73	23.80/0.75
	70	20.29/0.63	23.32/0.76	25.87/0.85

成像目标	采样率/%	匹配滤波	KSVD	本文算法
成像目标	采样率/%	PSNR/SSIM	PSNR/SSIM	PSNR/SSIM
BMP2	70	22.26/0.75	28.13/0.85	28.78/0.86
BMP2	50	14.61/0.51	22.68/0.68	24.88/0.72
BTR70	70	20.13/0.79	24.73/0.86	25.42/0.86
BTR70	50	14.68/0.61	21.13/0.70	22.26/0.72
T72	70	20.68/0.62	27.82/0.81	28.57/0.83
T72	50	14.43/0.46	22.15/0.64	24.98/0.73

[1]	蒋李兵, 杨庆伟, 郑舒予, 王壮. 基于拍卖理论的组网雷达多轨道目标ISAR成像资源分配算法[J]. 系统工程与电子技术, 2025, 47(1): 81-93.
[2]	陈洪猛, 李军, 刘京, 黄伟, 张英杰, 陈燕, 鲁耀兵. 基于Radon时频分析的海面舰船目标SAR-ISAR混合成像方法[J]. 系统工程与电子技术, 2025, 47(1): 109-116.
[3]	颜上取, 付耀文, 张文鹏, 杨威, 余若峰, 张法桐. 视频合成孔径雷达技术发展现状综述[J]. 系统工程与电子技术, 2024, 46(8): 2650-2666.
[4]	王进, 冷祥光, 孙忠镇, 马晓杰, 杨阳, 计科峰. 复杂运动舰船目标SAR成像空/时变散焦特性研究[J]. 系统工程与电子技术, 2024, 46(7): 2237-2255.
[5]	邢世其, 纪朋徽, 代大海, 冯德军. 方位向调制干扰对高分宽幅多通道SAR的影响[J]. 系统工程与电子技术, 2024, 46(6): 1946-1956.
[6]	曾顶, 殷君君, 杨健. 基于融合距离的极化SAR图像非局部均值滤波[J]. 系统工程与电子技术, 2024, 46(5): 1493-1502.
[7]	邵子康, 张晓玲, 张天文, 曾天娇. 基于锚框自适应和多尺度增强的SAR舰船检测[J]. 系统工程与电子技术, 2024, 46(4): 1204-1211.
[8]	张天文, 张晓玲, 邵子康, 曾天娇. 基于掩模注意型交互的SAR舰船实例分割[J]. 系统工程与电子技术, 2024, 46(3): 831-838.
[9]	方小宇, 黄丽佳. 基于全局位置信息和残差特征融合的SAR船舶检测算法[J]. 系统工程与电子技术, 2024, 46(3): 839-848.
[10]	张亚丽, 冯伟, 全英汇, 邢孟道. 基于多源遥感图像多级协同融合的舰船识别算法[J]. 系统工程与电子技术, 2024, 46(2): 407-418.
[11]	刘燊文, 崔兴超, 陈思伟. 结合空时上下文信息的视频SAR图像相干斑滤波[J]. 系统工程与电子技术, 2024, 46(2): 446-458.
[12]	龚峻扬, 付卫红, 刘乃安. SAR图像目标轮廓增强预处理模块设计[J]. 系统工程与电子技术, 2024, 46(12): 4010-4017.
[13]	赵忠凯, 孙宇晗, 高路. 对SAR的二维联合调制间歇采样转发干扰[J]. 系统工程与电子技术, 2024, 46(12): 4026-4033.
[14]	薛峰涛, 孙天宇, 杨益民, 杨健. 基于全局特征融合的SAR图像旋转舰船目标检测算法[J]. 系统工程与电子技术, 2024, 46(12): 4044-4053.
[15]	刘一飞, 禹卫东, 杨升辉, 李世强. 天基ISAR对空间轨道目标高分辨率成像问题分析[J]. 系统工程与电子技术, 2024, 46(11): 3671-3683.

基于结构化字典学习的判别稀疏微波成像方法

Discriminative sparse microwave imaging method based on structured dictionary learning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价