一种基于模糊滤波提高SAR自动目标识别平移不变性的方法

doi:10.3969/j.issn.1001-506X.2020.11.10

系统工程与电子技术 ›› 2020, Vol. 42 ›› Issue (11): 2488-2496.doi: 10.3969/j.issn.1001-506X.2020.11.10

一种基于模糊滤波提高SAR自动目标识别平移不变性的方法

顾正强^1,^2,³(), 张严^1,^2,³(), 张冰尘^1,²()

1. 中国科学院空天信息创新研究院, 北京 100190
2. 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, 北京 100190

收稿日期:2020-01-10 出版日期:2020-11-01 发布日期:2020-11-05
作者简介:顾正强(1995-),男,硕士研究生,主要研究方向为SAR信号处理、深度学习。E-mail:guzhengqiang18@mails.ucas.ac.cn|张严(1995-),男,博士研究生,主要研究方向为SAR信号处理。E-mail:zhangyan18@mails.ucas.ac.cn|张冰尘(1973-),男,研究员,博士,主要研究方向为雷达系统与雷达信号处理、新体制雷达。E-mail:zhangbc@aircas.ac.cn
基金资助:
国家自然科学基金(61571419)

Improving translation invariance of SAR automatic target recognition based on blur filtering method

Zhengqiang GU^1,^2,³(), Yan ZHANG^1,^2,³(), Bingchen ZHANG^1,²()

1. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
2. Key Laboratory of Technology in Geospatial Information Processing and Applications System, Beijing 100190, China
3. University of Chinese Academy of Sciences, Beijing 100190, China

Received:2020-01-10 Online:2020-11-01 Published:2020-11-05

摘要/Abstract

摘要：

使用卷积神经网络去实现合成孔径雷达(synthetic aperture radar, SAR)自动目标识别(auto target recognition, ATR)成为了近年来的热点,但实际使用中存在的一个隐患问题是平移不变性的丢失,随着目标位置移动,系统输出也随之改变，从而造成错误识别。针对上述问题，提出了一种落实在模型层面的解决方法,通过对算法的改进,实现提升SAR ATR系统平移不变性,而无需数据增强。提出的模块易于移植到现有SAR ATR骨干网络中,且通过实测兼容良好,引入后不影响识别准确率,达到了与原网络近似相等甚至更高的精度。结果表明,所提出的算法不仅提升了系统的平移不变性,同时提升了系统的抗干扰能力。

关键词: 合成孔径雷达, 自动目标识别, 平移不变性, 卷积神经网络

Abstract:

Using convolutional neural network to realize synthetic aperture radar (SAR), auto target recognition (ATR) has become a hot spot in recent years.However, a hidden problem in practical use is the loss of translation invariance. As the target moves horizontally, vertically or both, the output of the system changes accordingly, which leads to misidentification. A practical solution is proposed at the model level. Through the improvement of the model algorithm, the translation invariance of the SAR ATR system is significantly improved, and there is no need for data augmentation. The proposed module is easy to be inserted into the existing SAR ATR backbone network, which is well compatible, has effect on recognition accuracy and achieves an approximate or slightly higher accuracy than the original network. Experiments demonstrate that the algorithm proposed not only improves the translation invariance of the system, but also improves the anti-interference ability of the system.

Key words: synthetic aperture radar (SAR), automatic target recognition, translation invariance, convolutional neural network

中图分类号:

TP3174

顾正强, 张严, 张冰尘. 一种基于模糊滤波提高SAR自动目标识别平移不变性的方法[J]. 系统工程与电子技术, 2020, 42(11): 2488-2496.

Zhengqiang GU, Yan ZHANG, Bingchen ZHANG. Improving translation invariance of SAR automatic target recognition based on blur filtering method[J]. Systems Engineering and Electronics, 2020, 42(11): 2488-2496.

图/表 13

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

图10

图11

图12

参考文献 23

1	ZHU X X , TUIA D , MOU L C , et al. Deep learning in remote sensing: a comprehensive review and list of resources[J]. IEEE Geoscience and Remote Sensing Magazine, 2017, 5 (4): 8- 36. doi: 10.1109/MGRS.2017.2762307
2	杨龙, 苏娟, 李响. 基于深度卷积神经网络的SAR舰船目标识别[J]. 系统工程与电子技术, 2019, 41 (9): 1990- 1997.
	YANG L , SU J , LI X . Ship detection in SAR images based on deep convolutional neural network[J]. Systems Engineering and Electronics, 2019, 41 (9): 1990- 1997.
3	PEI J F , HUANG Y L , HUO W B . SAR automatic target recognition based on multiview deep learning framework[J]. IEEE Trans.on Geoscience and Remote Sensing, 2018, 56 (4): 2196- 2210. doi: 10.1109/TGRS.2017.2776357
4	刘赢, 田润澜, 王晓峰. 基于深层卷积神经网络和双谱特征的雷达信号识别方法[J]. 系统工程与电子技术, 2019, 41 (9): 1998- 2005.
	LIU Y , TIAN R L , WANG X F . Radar signal recognition method based on deep convolutional neural network andbispectrumfeature[J]. Systems Engineering and Electronics, 2019, 41 (9): 1998- 2005.
5	ZHANG H , NASRABADI N M , ZHANG Y , et al. Multi-view automatic target recognition using joint sparse representation[J]. IEEE Trans. on Aerospace and Electronic Systems, 2012, 48 (3): 2481- 2497.
6	IKEUCHI K, WHEELER M D, YAMAZAKIT, et al. Model based SAR ATR system[M]. 3rd ed. Algorithms for Synthetic Aperture Radar Imagery, 1996.
7	CHEN S Z, WANG H P. SAR target recognition based on deep learning[C]//Proc.of the International Conference on Data Science and Advanced Analytics, 2014: 541-547.
8	CHEN S Z , WANG H P , XU F , et al. Target classification using the deep convolutional neural networks for SAR images[J]. IEEE Trans.on Geoscience and Remote Sensing, 2016, 54 (8): 4806- 4817. doi: 10.1109/TGRS.2016.2551720
9	MALMGREN-HANSEN D. Training convolutional neural networks for translational invariance on SAR ATR[C]//Proc.of the European Conference on Synthetic Aperture Radar, 2016.
10	FURUKAWA H . Deep learning for target classification from SAR imagery: data augmentation and translation invariance[J]. IEICE Technical Report, 2017, 117 (182): 13- 17.
11	DING J , CHEN B , LIU H W . Convolutional neural network with data augmentation for SAR target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13 (3): 364- 368.
12	CUI Z Y, WANG S F, DANG S H, et al. A translational invariant SAR-ATR method based on convolutional neural network[C]//Proc.of the IEEE International Geoscience and Remote Sensing Symposium, 2018: 677-680.
13	HU J, SHEN L, SUN G. Squeeze and excitation networks[C]//Proc.of the Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
14	LI Y, WANG J B, XU Y L, et al. DeepSAR-Net: deep convolutional neural networks for SAR target recognition[C]//Proc.of the IEEE International Conference on Big Data Analysis, 2017: 740-743.
15	KAUDERER-ABRAMS E. Quantifying translation-invariance in convolutional neural networks[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2018.
16	SIMONCELLI E P , FREEMAN W T , ADELSON E H , et al. Shiftable multiscale transforms[J]. IEEE Trans.on Information Theory, 1992, 38 (2): 587- 607.
17	AZULAY A, WEISS Y. Why do deep convolutional networks generalize so poorly to small image transformations[C]//Proc.of the International Conference on Learning Representations, 2019.
18	LOWE D G . Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60, 91- 110. doi: 10.1023/B:VISI.0000029664.99615.94
19	SCHERE D , MULLER A , BEHNKE S . Evaluation of pooling operations in convolutional architectures for object recognition[M]. Springer: Artificial Neural Networks-ICANN, 2010: 92- 101.
20	ZHANG H. Making convolutional networks shift-invariant again[C]//Proc.of the International Conference on Machine Learning, 2019.
21	ALOM M Z , TAHA T M , YAKOPCIC C , et al. A state-of-the-art survey on deep learning theory and architectures[J]. Electronics, 2019, 8 (3): 292- 359. doi: 10.3390/electronics8030292
22	GLOROT X , BENGIO Y . Understanding the difficulty of training deep feedforward neural networks[J]. Journal of Machine Learning Research-Proceedings Track, 2010, 9, 249- 256.
23	KINGMA D, BA J. Adam: a method for stochastic optimization[C]//Proc.of the International Conference on Learning Representations, 2014.

最大容忍值T	算法
最大容忍值T	原始网络	池化模糊	数据增强	并用	全模糊1	全模糊2
D7	1	4	5	7	6	8
BTR60	5	6	6	10	19	19
ZIL131	4	4	8	14	13	13
T62	5	5	5	5	8	9
BRDM-2	7	5	3	5	8	19

[1]	宋爽, 张悦, 张琳娜, 岑翼刚, 李浥东. 基于深度学习的轻量化目标检测算法[J]. 系统工程与电子技术, 2022, 44(9): 2716-2725.
[2]	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.
[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]	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.
[5]	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.
[6]	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.
[7]	韦娟, 杨皇卫, 宁方立. 基于NMF与CNN联合优化的声学场景分类[J]. 系统工程与电子技术, 2022, 44(5): 1433-1438.
[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]	方伟, 王玉, 闫文君, 林冲. 基于神经网络的符号化飞行动作识别[J]. 系统工程与电子技术, 2022, 44(3): 737-745.
[13]	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.
[14]	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.
[15]	刘恒燕, 张立民, 闫文君, 钟兆根, 凌青, 梁晓军. 基于WBP-CNN算法的LDPC译码[J]. 系统工程与电子技术, 2022, 44(3): 1030-1035.

一种基于模糊滤波提高SAR自动目标识别平移不变性的方法

Improving translation invariance of SAR automatic target recognition based on blur filtering method

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 23

相关文章 15

编辑推荐

Metrics

本文评价