基于门控多尺度匹配网络的小样本SAR目标识别

doi:10.12305/j.issn.1001-506X.2022.11.08

摘要/Abstract

摘要：

为了解决传统合成孔径雷达(synthetic aperture radar, SAR)目标识别方法在小样本条件下泛化能力差、识别准确率低的问题, 通过在匹配网络的基础上引入权重门控单元和多尺度特征提取模块, 提出了基于门控多尺度匹配网络的小样本SAR目标识别方法。在该方法中, 多尺度特征提取模块能够提取匹配网络不同卷积层的多尺度特征, 权重门控单元能够根据不同的识别任务赋予特征不同的权重大小, 实现根据具体任务选择最具代表性的目标特征, 从而以该特征为主导完成目标识别任务。在运动和静止目标获取与识别(the moving and stationary target acquisition and recognition, MSTAR)数据集上对提出的方法进行了验证, 实验结果表明，所提方法较其他3种小样本学习方法和两种小样本SAR目标识别方法表现出了一定的优越性, 而且所提方法经实验验证在噪声环境下表现出了一定的鲁棒性。

关键词: 合成孔径雷达, 雷达目标识别, 小样本学习, 融合目标识别, 度量学习, 元学习

Abstract:

In order to solve the poor generalization ability and low recognition accuracy problems of traditional synthetic aperture radar (SAR) target recognition methods in few-shot condition, a novel few-shot SAR target recognition method based on gated multi-scale matching network is proposed, which introduces weight gated unit and multi-scale feature extraction module into matching network. In the proposed method, the multi-scale feature extraction module is used to extract multi-scale features of different convolutional layers in matching network and the weight gated unit is used to weight different multi-scale features according to different recognition tasks. The proposed method achieves the effect of carrying out different recognition tasks mainly based on features of different layers thanks to the weight gated unit. The proposed method is evaluated on the moving and stationary target acquisition and recognition (MSTAR) dataset and achieved promising performance compared with state-of-the-art few-shot learning methods and few-shot SAR target methods. Furthermore, the proposed method shows good robustness in noisy environments.

Key words: synthetic aperture radar(SAR), radar target recognition, few-shot learning, fusion target recognition, metric learning, meta-learning

中图分类号:

TN95

刘旗, 张新禹, 刘永祥. 基于门控多尺度匹配网络的小样本SAR目标识别[J]. 系统工程与电子技术, 2022, 44(11): 3346-3356.

Qi LIU, Xinyu ZHANG, Yongxiang LIU. Few-shot SAR target recognition based on gated multi-scale matching network[J]. Systems Engineering and Electronics, 2022, 44(11): 3346-3356.

图/表 11

图1

图2

图3

图4

图5

表1

图6

表2

表3

图7

表4

参考文献 40

1	BARTON D K , LEONOV S A . Radar technology encyclopedia[M]. New York: Artech house, 1998.
2	胡利平. 合成孔径雷达图像目标识别技术研究[D]. 西安: 西安电子科技大学, 2009.
	HU L P. Study on SAR images target recognition[D]. Xi'an: Xidian University, 2009.
3	庞礴. 多通道SAR成像理论与方法研究[D]. 长沙: 国防科学技术大学, 2014.
	PANG B. Study on the imaging theory and method of multi-channel SAR[D]. Changsha: National University of Defense and Technology, 2014.
4	LI Y Y , PENG C , CHEN Y Q , et al. A deep learning method for change detection in synthetic aperture radar images[J]. IEEE Trans.on Geoscience and Remote Sensing, 2019, 57 (8): 5751- 5763. doi: 10.1109/TGRS.2019.2901945
5	RAN L , LIU Z , LI T , et al. Extension of map-drift algorithm for highly squinted SAR autofocus[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10 (9): 4032- 4044. doi: 10.1109/JSTARS.2017.2702621
6	SHI L J, KARVONEN J, CHENG B, et al. Sea ice thickness retrieval from SAR imagery over Bohai sea[C]//Proc. of the IEEE Geoscience and Remote Sensing Symposium, 2014: 4864-4867.
7	陈冬, 句彦伟. 基于改进型YOLOv3的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2021, 43 (4): 937- 943.
	CHEN D , JU Y W . Ship detection in SAR image based on improved YOLOv3[J]. Systems Engineering and Electronics, 2021, 43 (4): 937- 943.
8	胡利平, 李胜, 殷红成. 基于差准则的二维非参数特征分析的SAR目标识别[J]. 系统工程与电子技术, 2015, 37 (10): 2250- 2254. doi: 10.3969/j.issn.1001506X.2015.10.09
	HU L P , LI S , YIN H C . 2-dimensional nonparametric feature analysis based on difference criterion and SAR target recognition[J]. Systems Engineering and Electronics, 2015, 37 (10): 2250- 2254. doi: 10.3969/j.issn.1001506X.2015.10.09
9	ZHANG J S , XING M D , XIE Y Y . FEC: a feature fusion framework for SAR target recognition based on electromagnetic scattering features and deep CNN features[J]. IEEE Trans.on Geoscience and Remote Sensing, 2020, 59 (3): 2174- 2187.
10	CHEN L , JIANG X , LI Z , et al. Feature-enhanced speckle reduction via low-rank and space-angle continuity for circular SAR target recognition[J]. IEEE Trans.on Geoscience and Remote Sensing, 2020, 58 (11): 7734- 7752. doi: 10.1109/TGRS.2020.2983420
11	OH J , YOUM G Y , KIM M . SPAM-net: a CNN-based SAR target recognition network with pose angle marginalization learning[J]. IEEE Trans.on Circuits and Systems for Video Technology, 2020, 31 (2): 701- 714.
12	GUO Y C , DU L , WEI D , et al. Robust sar automatic target recognition via adversarial learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 14, 716- 729.
13	YANG R , HU Z T , LIU Y M , et al. A novel polarimetric SAR classification method integrating pixel-based and patch-based classification[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 17 (3): 431- 435.
14	BAI X R , XUE R H , WANG L , et al. Sequence SAR image classification based on bidirectional convolution-recurrent network[J]. IEEE Trans.on Geoscience and Remote Sensing, 2019, 57 (11): 9223- 9235. doi: 10.1109/TGRS.2019.2925636
15	ZHU H L , LIN N , LEUNG H , et al. Target classification from SAR imagery based on the pixel grayscale decline by graph convolutional neural network[J]. IEEE Sensors Letters, 2020, 4 (6): 1002204.
16	CHEN L , JIANG X , LI Z , et al. Feature-enhanced speckle reduction via low-rank and space-angle continuity for circular SAR target recognition[J]. IEEE Trans.on Geoscience and Remote Sensing, 2020, 58 (11): 7734- 7752. doi: 10.1109/TGRS.2020.2983420
17	ZHAO Q , PRINCIPE J C . Support vector machines for SAR automatic target recognition[J]. IEEE Trans.on Aerospace and Electronic Systems, 2001, 37 (2): 643- 654. doi: 10.1109/7.937475
18	HUANG X Y , QIAO H , ZHANG B . SAR target configuration recognition using tensor global and local discriminant embedding[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 13 (2): 222- 226.
19	EL-DARYMLI K , MCGUIRE P , GILL E W , et al. Holism-based features for target classification in focused and complex-valued synthetic aperture radar imagery[J]. IEEE Trans.on Aerospace and Electronic Systems, 2016, 52 (2): 786- 808. doi: 10.1109/TAES.2015.140757
20	ROY S , MENAPACE W , OEI S , et al. Deep learning for classification and localization of COVID-19 markers in point-of-care lung ultrasound[J]. IEEE Trans.on Medical Imaging, 2020, 39 (8): 2676- 2687. doi: 10.1109/TMI.2020.2994459
21	DENG J, DONG W, SOCHER R, et al. Imagenet: a large-scale hierarchical image database[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2009: 248-255.
22	GIRSHICK R , DONAHUE J , DARRELL T , et al. Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2015, 38 (1): 142- 158.
23	TU Y H , DU J , LEE C H . Speech enhancement based on teacher-student deep learning using improved speech presence probability for noise-robust speech recognition[J]. IEEE/ACM Trans.on Audio, Speech, and Language Processing,, 2019, 27 (12): 2080- 2091. doi: 10.1109/TASLP.2019.2940662
24	ZHANG Z M , WANG H P , XU F , et al. Complex-valued convolutional neural network and its application in polarimetric SAR image classification[J]. IEEE Trans.on Geoscience and Remote Sensing, 2017, 55 (12): 7177- 7188. doi: 10.1109/TGRS.2017.2743222
25	WANG J , ZHENG T , LEI P , et al. Ground target classification in noisy SAR images using convolutional neural networks[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11 (11): 4180- 4192. doi: 10.1109/JSTARS.2018.2871556
26	WANG N , WANG Y H , LIU H W , et al. Feature-fused SAR target discrimination using multiple convolutional neural networks[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (10): 1695- 1699. doi: 10.1109/LGRS.2017.2729159
27	TANG J X, ZHANG F, ZHOU Y S, et al. A fast inference networks for SAR target few-shot learning based on improved siamese networks[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2019: 1212-1215.
28	WANG L , BAI X R , GONG C , et al. Hybrid inference network for few-shot SAR automatic target recognition[J]. IEEE Trans.on Geoscience and Remote Sensing, 2021, 59 (11): 9257- 9269. doi: 10.1109/TGRS.2021.3051024
29	FU K , ZHANG T F , ZHANG Y , et al. Few-shot SAR target classification via metalearning[J]. IEEE Trans.on Geoscience and Remote Sensing, 2022, 60, 2000314.
30	ROSTAMI M, KOLOURI S, EATON E, et al. SAR image classification using few-shot cross-domain transfer learning[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.
31	WANG C C , GU H , SU W M . SAR image classification using contrastive learning and pseudo-labels with limited data[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19, 4012505.
32	FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proc. of the International Conference on Machine Learning, 2017: 1126-1135.
33	RAVI S, LAROCHELLE H. Optimization as a model for few-shot learning[C]//Proc. of the International Conference of Learning Representation, 2016.
34	VINYALS O , BLUNDELL C , LILLICRAP T , et al. Matching networks for one shot learning[J]. Advances in Neural Information Processing Systems, 2016, 29, 3630- 3638.
35	高飞, 赵洁琼, 林翀, 等. 基于距离度量学习的SAR图像识别方法[J]. 北京理工大学学报, 2021, 41 (3): 334- 340.
	GAO F , ZHAO J Q , LIN C , et al. A SAR image recognition method based on distance metric learning[J]. Transactions of Beijing Institute of Technology, 2021, 41 (3): 334- 340.
36	应自炉, 宣晨, 翟懿奎, 等. 面向小样本SAR图像识别的自注意力多尺度特征融合网络[J]. 信号处理, 2020, 36 (11): 1846- 1858.
	YING Z L , XUAN C , ZHAI Y K , et al. Self-attention multiscale feature fusion network for small sample SAR image recognition[J]. Journal of Signal Processing, 2020, 36 (11): 1846- 1858.
37	LIN Z , JI K F , KANG M , et al. Deep convolutional highway unit network for SAR target classification with limited labeled training data[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (7): 1091- 1095. doi: 10.1109/LGRS.2017.2698213
38	汪航, 陈晓, 田晟兆, 等. 基于小样本学习的SAR图像识别[J]. 计算机科学, 2020, 47 (5): 124- 128.
	WANG H , CHEN X , TIAN S Z , et al. SAR image recognition based on few-shot learning[J]. Computer Science, 2020, 47 (5): 124- 128.
39	LIU T R , LUO W H , MA L , et al. Coupled network for robust pedestrian detection with gated multi-layer feature extraction and deformable occlusion handling[J]. IEEE Trans.on Image Processing, 2020, 30, 754- 766.
40	HU J , SHEN L , ALBANIE S , et al. Squeeze-and-excitation networks[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2020, 42 (8): 2011- 2023.

方法	5类 1样本	5类 2样本	5类 5样本	5类 10样本
MAML^[32]	0.564	0.735	0.775	0.877
Meta-LSTM^[33]	0.611	0.671	0.792	0.844
Matching Net^[34]	0.597	0.600	0.701	0.778
所提方法	0.705	0.829	0.842	0.932

方法	5类 1样本	5类 2样本	5类 5样本	5类 10样本
度量学习小样本 SAR目标识别方法^[35]	0.608	0.650	0.767	0.800
小样本学习SAR 目标识别方法^[38]	0.600	0.650	0.700	0.869
所提方法	0.705	0.829	0.842	0.932

方法	5类 1样本	5类 2样本	5类 5样本	5类 10样本
采用余弦相似度	0.705	0.829	0.842	0.932
采用欧式距离	0.696	0.808	0.836	0.916

小样本条件	SNR/dB	识别准确率
5类1样本	-10	0.536
	-5	0.574
	0	0.605
	5	0.627
	10	0.650
5类2样本	-10	0.671
	-5	0.674
	0	0.692
	5	0.700
	10	0.724
5类5样本	-10	0.766
	-5	0.776
	0	0.780
	5	0.813
	10	0.826
5类10样本	-10	0.816
	-5	0.865
	0	0.870
	5	0.903
	10	0.904

[1]	苗添, 曾虹程, 王贺, 陈杰. 基于迭代阈值分割的星载SAR洪水区域快速提取[J]. 系统工程与电子技术, 2022, 44(9): 2760-2768.
[2]	郭军成, 万刚, 胡欣杰, 严发宝, 王帅. 太阳射电频谱爆发识别的元学习方法[J]. 系统工程与电子技术, 2022, 44(8): 2410-2418.
[3]	王彩云, 吴钇达, 王佳宁, 马璐, 赵焕玥. 基于改进的CNN和数据增强的SAR目标识别[J]. 系统工程与电子技术, 2022, 44(8): 2483-2487.
[4]	孙晶明, 虞盛康, 孙俊. 基于元学习的雷达小样本目标识别方法及改进[J]. 系统工程与电子技术, 2022, 44(6): 1839-1845.
[5]	傅东宁, 廖桂生, 黄岩, 张邦杰, 王幸. 基于图拉普拉斯嵌入的合成孔径雷达时变窄带干扰抑制算法[J]. 系统工程与电子技术, 2022, 44(6): 1846-1853.
[6]	盖明慧, 张苏, 孙卫天, 倪育德, 杨磊. 复数兼容全变分SAR目标结构特征增强[J]. 系统工程与电子技术, 2022, 44(6): 1862-1872.
[7]	徐安林, 张毓, 周峰. 基于Beta过程的高分辨ISAR成像[J]. 系统工程与电子技术, 2022, 44(6): 1873-1879.
[8]	纪朋徽, 代大海, 邢世其, 冯德军. 密集虚假运动目标生成方法[J]. 系统工程与电子技术, 2022, 44(5): 1502-1511.
[9]	刘丰恺, 黄大荣, 郭新荣, 冯存前. 基于吕氏分布的机动目标参数化平动补偿方法[J]. 系统工程与电子技术, 2022, 44(4): 1166-1173.
[10]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[11]	周晓玲, 张朝霞, 鲁雅, 王倩, 王琨琨. 基于改进R-FCN的SAR图像识别[J]. 系统工程与电子技术, 2022, 44(4): 1202-1209.
[12]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[13]	杨磊, 张苏, 盖明慧, 方澄. 高分辨SAR目标成像方向性结构特征增强[J]. 系统工程与电子技术, 2022, 44(3): 808-818.
[14]	王俊杰, 冯德军, 胡卫东. 基于时变材料的合成孔径雷达图像二维调制方法[J]. 系统工程与电子技术, 2022, 44(2): 455-462.
[15]	方澄, 李慧娟, 路稳, 宋玉蒙, 杨磊. 基于形态学自适应分块的高分辨SAR多特征增强算法[J]. 系统工程与电子技术, 2022, 44(2): 470-479.