雷达小样本目标识别方法及应用分析

doi:10.12305/j.issn.1001-506X.2021.03.11

摘要/Abstract

摘要：

针对雷达小样本目标识别问题, 结合元学习和迁移学习提出一套综合解决方案, 旨在根据实际应用场景的不同提供合适的模型学习方式和分类方式, 从而提升雷达小样本目标识别效率和准确率。同时，通过多组对比实验深入分析小样本学习算法在实际雷达目标识别场景下的模型性能变化, 得出两个可有效指导工程化应用的重要结论。元学习模型在源任务信息充足且源任务与目标任务间差异性小时性能表现良好, 否则迁移学习方法更适用; 小样本学习模型对雷达目标外在特征的关注度不同, 以识别为目的的雷达成像应重点关注模型需求的显著性特征。

关键词: 雷达目标识别, 小样本学习, 元学习, 迁移学习

Abstract:

Aiming at the problem of radar small shot target recognition, a comprehensive solution is proposed by combining meta learning and transfer learning, to provide appropriate model learning and classification methods according to different practical application scenarios, so as to improve the efficiency and accuracy of radar small shot target recognition. At the same time, through several groups of comparative experiments, the model performance changes of few shot learning algorithm in the actual radar target recognition scene are deeply analyzed, and two important conclusions that can effectively guide the engineering application are obtained. One is the performance of meta learning model is good when the source task information is sufficient and the difference between the source task and the target task is small, otherwise the transfer learning method is more suitable. The other one is the few shot learning model pay different attention to the external features of radar targets, so the recognition oriented radar imaging should focus on the salient features of the model requirements.

Key words: radar target recognition, few shot learning, meta learning, transfer learning

中图分类号:

TN911.73

晏媛, 孙俊, 孙晶明, 于俊朋. 雷达小样本目标识别方法及应用分析[J]. 系统工程与电子技术, 2021, 43(3): 684-692.

Yuan YAN, Jun SUN, Jingming SUN, Junpeng YU. Radar few shot target recognition method and application analysis[J]. Systems Engineering and Electronics, 2021, 43(3): 684-692.

图/表 12

图1

图2

图3

图4

图5

表1

图6

表2

图7

图8

图9

表3

参考文献 26

1	EL-DARYMLI K , GILL E W , MCGUIRE P , et al. Automatic target recognition in synthetic aperture radar imagery: a state-of-the-art review[J]. IEEE Access, 2016, 4, 6014- 6058. doi: 10.1109/ACCESS.2016.2611492
2	LI Y B, ZHOU C, WANG N. A survey on feature extraction of SAR images[C]//Proc.of the International Conference on Computer Application and System Modeling, 2010.
3	COMAN C, THAENS R. A deep learning SAR target classification experiment on mstar dataset[C]//Proc.of the International Radar Symposium, 2018.
4	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.
5	ZHANG D , LIU J , HENG W , et al. Transfer learning with convolutional neural networks for SAR ship recognition[J]. IOP Conference Series: Materials Science and Engineering, 2018, 322 (7): 072001.
6	HUANG Z L , PAN Z X , LEI B . Transfer learning with deep convolutional neural network for SAR target classification with limited labeled data[J]. Remote Sensing, 2017, 9 (9): 907- 928. doi: 10.3390/rs9090907
7	WANG Y Q, YAO Q. Few-shot learning: a survey.[EB/OL].[2020-06-15].https://arxiv.org/abs/1904.05046v1.
8	VANSCHOREN J. Meta-learning: a survey[EB/OL].[2020-06-15].https://arxiv.org/abs/1810.03548v1.
9	KOCH G, ZEMEL R, SALAKHUTDINOV R. Siamese neural networks for one-shot image recognition[C]//Proc.of the 32nd International Coneference on Machine Learning, 2015.
10	VINYALS O, BLUNDELL C, LILLCRAP T, et al. Matching networks for one shot learning[C]//Proc.of the Conference on Neural Information Processing Systems, 2016: 3630-3638.
11	SNELL J, SWERSKY K, ZEMEL R S. Prototypical networks for few-shot learning[C]//Proc.of the Advances in Neural Information Processing Systems, 2017: 4077-4087.
12	SUNG F, YANG Y X, ZHANG L, et al. Learning to compare: relation network for few-shot learning[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1199-1208.
13	SANTORO A, BARTUNOV S, BOTVINICK M, et al. Meta-learning with memory-augmented neural networks[C]//Proc.of the International Conference on Machine Learning, 2016: 1842-1850.
14	HOCHREITER S , SCHMIDHUBER J . Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780. doi: 10.1162/neco.1997.9.8.1735
15	FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[EB/OL].[2020-06-15].https://arxiv.org/abs/1703.03400.
16	NICHOL A, SCHULMAN J. Reptile: a scalable metalearning algorithm[EB/OL].[2020-06-15].https://arxiv.org/abs/1803.02999v1.
17	PAN S J , YANG Q . A survey on transfer learning[J]. IEEE Trans.on Knowledge and Data Engineering, 2019, 22 (10): 1345- 1359.
18	CHEN W Y, LIU C Y, KIRA Z, et al. A closer look at few-shot classification.[EB/OL].[2020-06-15].https://arxiv.org/pdf/1904.04232.pdf.
19	YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks?[C]//Proc.of the Advances in Neural Information Processing Systems, 2014: 3320-3328.
20	CHEN Y, WANG X L, LIU Z, et al. A new meta-baseline for few-shot learning[EB/OL].[2020-06-15].https://arxiv.org/abs/2003.04390.
21	SUN Q R, LIU Y Y, CHUA T S, et al. Meta-transfer learning for few-shot learning[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 403-412.
22	WANG L, BAI X R, HOU F. Few-shot SAR ATR based on conv-BiLSTM prototypical networks[C]//Proc.of the Asia-Pacific Conference on Synthetic Aperture Radar, 2019.
23	LU D, CAO L Y, LIU H W. Few-shot learning neural network for SAR target recognition[C]//Proc.of the Asia-Pacific Conference on Synthetic Aperture Radar, 2019.
24	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 International Geoscience and Remote Sensing Symposium, 2019: 1212-1215.
25	ROSTAMI M , KOLOURI S , EATON E , et al. Deep transfer learning for few-shot sar image classification[J]. Remote Sensing, 2019, 11 (11): 1374- 1393. doi: 10.3390/rs11111374
26	朱克凡, 王杰贵. 小样本条件下SCGAN+CNN低分辨雷达目标一步识别算法[J]. 系统工程与电子技术, 2020, 42 (1): 67- 75.
	ZHU K F , WANG J G . Low-resolution radar target one-step recognition algorithm based on SCGAN+CNN with a limited training data[J]. Systems Engineering and Electronics, 2020, 42 (1): 67- 75.

目标类型	姿态角/(°)
目标类型	15	17	30	45
BTR70(SN_C71)	196	233	-	-
BTR60	195	256	-	-
2S1	274	299	288	303
BRDM2	274	298	420	423
D7	274	299	-	-
T62	273	299	-	-
ZIL131	274	299	-	-
ZSU23/4	274	299	406	422
BMP2(SN_9563)	195	233	-	-
T72(SN_132)	196	232	-	-

参数	编号
参数	a	b	c	d	e	f	g	h	i	j	k
训练样本姿态角/(°)	15	15	15	15	15, 17	15, 17	15, 17	15, 17	15, 17	15, 17	15, 17
测试样本姿态角/(°)	15	17	30	45	15	17	30	45	15, 17	30, 45	15, 17, 30, 45
训练样本数量	200	200	200	200	200	200	200	200	400	400	400
测试样本数量	200	200	200	200	200	200	200	200	400	400	400
元学习识别率/%	97.3	97.9	82	75.26	96.7	97.9	80.4	71.8	94.7	63.5	55.2
迁移识别率/%	84.9	87.7	73.8	74.1	86.2	86.8	75.8	75	81.6	64.6	55.2

参数	炮管特征		履带特征
训练样本	有	无	有	无
测试样本	无	有	无	有
训练类别数	6	4	6	4
测试类别数	4	6	4	6
训练样本数量	400	400	400	400
测试样本数量	400	400	400	400
元学习识别率/%	83.2	84.6	94.3	86.4
迁移识别率/%	82.8	64.9	80.1	70.5

[1]	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.
[2]	杨立儒, 刘永祥, 杨威. 基于迁移学习的雷达杂波幅度统计模型选择[J]. 系统工程与电子技术, 2022, 44(8): 2457-2467.
[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]	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.
[6]	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.
[7]	何立, 沈亮, 李辉, 王壮, 唐文泉. 强化学习中的策略重用: 研究进展[J]. 系统工程与电子技术, 2022, 44(3): 884-899.
[8]	吴涛, 王伦文, 朱敬成. 基于迁移学习和注意力机制的伪装图像分割[J]. 系统工程与电子技术, 2022, 44(2): 376-384.
[9]	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.
[10]	李睿峰, 许爱强, 孙伟超, 王树友. 基于元学习的航空电子设备特征选择算法推荐方法[J]. 系统工程与电子技术, 2021, 43(7): 2011-2020.
[11]	陈浩, 杨俊安, 刘辉. 基于深度残差适配网络的通信辐射源个体识别[J]. 系统工程与电子技术, 2021, 43(3): 603-609.
[12]	胡利平, 董纯柱, 刘锦帆, 殷红成, 王超, 宁超. 基于SAR仿真图像的地面车辆非同源目标识别[J]. 系统工程与电子技术, 2021, 43(12): 3518-3525.
[13]	张一凡, 张双辉, 刘永祥, 荆锋. 基于注意力机制的堆叠LSTM网络雷达HRRP序列目标识别方法[J]. 系统工程与电子技术, 2021, 43(10): 2775-2781.
[14]	施赛楠, 董泽远, 杨静, 杨春娇. 基于时频图自主学习的海面小目标检测[J]. 系统工程与电子技术, 2021, 43(1): 33-41.
[15]	苏娟, 杨龙, 黄华, 金国栋. 用于SAR图像小目标舰船检测的改进SSD算法[J]. 系统工程与电子技术, 2020, 42(5): 1026-1034.