基于深度学习的弹道目标智能分类

doi:10.3969/j.issn.1001-506X.2020.06.04

摘要/Abstract

摘要：

针对弹道目标微动分类前需平动补偿及典型雷达散射截面积(radar cross-section, RCS)序列分类需构造人工特征的问题,提出利用弹道目标微动特性和RCS相结合的弹道目标智能分类算法。首先,建立弹道目标运动模型并分析得到方位角和俯仰角,从而获取RCS序列,在此基础上利用小波变换得到时频图并构建数据集;然后,通过卷积神经网络(convolutional neural network, CNN)提取时频图像特征序列并与RCS序列融合成高维特征;最后,利用具有容错能力的双向长短期记忆网络充分学习序列之间的相关性以实现目标分类。仿真结果表明,该算法比卷积神经网络和支持向量机的分类精度分别提高5%和2%以上,分类速度比卷积神经网络和双向长短期记忆网络分别提高1.5倍和2.5倍,实现了更高精度的快速智能分类。

关键词: 深度学习, 弹道目标, 智能分类, 雷达散射截面积, 小波变换

Abstract:

Aiming at the problems of translational compensation before micro-motion classification of ballistic targets and the need to construct artificial features for typical radar cross-section(RCS) sequence classification, an intelligent classification method of ballistic targets based on micro-motion characteristics of ballistic targets and RCS is proposed. Firstly, the ballistic targets motion model is established and the azimuth and elevation angles are analyzed to obtain the RCS sequence. On this basis, the time-frequency diagram is obtained by using wavelet transform to construct the data set. Then, the time-frequency diagram feature sequence is extracted by convolutional neural network(CNN) and fused with the RCS sequence to form high-dimensional features. Finally, the bidirectional long short-term memory network with fault tolerance is used to fully learn the correlation between sequences to achieve target classification. The simulation results show that the classification accuracy of the proposed algorithm is 5% and 2% higher than that of CNN and support vector machines, and the classification speed is 1.5 and 2.5 times faster than that of CNN and bidirectional long short-term memory networks, respectively. The algorithm achieves faster intelligent classification with higher accuracy.

Key words: deep learning, ballistic target, intelligent classification, radar cross-section(RCS), wavelet transform

中图分类号:

TN957

李江, 冯存前, 王义哲, 贺思三. 基于深度学习的弹道目标智能分类[J]. 系统工程与电子技术, 2020, 42(6): 1226-1234.

Jiang LI, Cunqian FENG, Yizhe WANG, Sisan HE. Intelligent classification of ballistic targets based on deep learning[J]. Systems Engineering and Electronics, 2020, 42(6): 1226-1234.

图/表 17

图1

图2

图3

图4

图5

图6

表1

图7

图8

图9

表2

表3

图10

表4

图11

图12

图13

参考文献 30

1	SAMSON V . American missile defense[M]. California: Praeger Security International, 2010: 44- 78.
2	STEPHEN B J . Technical and institutional factors in the emergence of project management[J]. International Journal of Project Management, 2013, 31 (5): 670- 681. doi: 10.1016/j.ijproman.2013.01.006
3	SHENG J. Target identity recognition method based on RCS distribution and spatial location[C]//Proc. of the 7th International Conference on Identification, Information and Knowledge in the Internet of Things, 2018: 632-637.
4	WANG T , BI W J , ZHAO Y L , et al. Radar target recognition algorithm based on RCS observation sequence—set-valued identification method[J]. Journal of Systems Science & Complexity, 2016, 29 (3): 573- 588.
5	束长勇, 张生俊, 黄沛霖, 等. 基于微多普勒的空间锥体目标微动分类[J]. 北京航空航天大学学报, 2017, 43 (7): 1387- 1394.
	SHU C Y , ZHANG S J , HUANG P L , et al. Micro-motion classification of spatial cone target based on micro-doppler[J]. Journal of Beijing University of Aeronautics and Astronautics, 2017, 43 (7): 1387- 1394.
6	WANG Y Z, FENG C Q, ZHANG Y S.Classification of space targets with micro-motion based on deep CNN[C]//Proc.of the 2nd International Conference on Electronic Information and Communication Technology, 2019: 557-561.
7	许小剑, 黄培康. 利用RCS幅度信息进行雷达目标识别[J]. 系统工程与电子技术, 1992, 14 (6): 1- 9. doi: 10.3321/j.issn:1001-506X.1992.06.001
	XU X J , HUANG P K . Radar target reeognition using RCS magnitude signatures[J]. Systems Engineering and Electronics, 1992, 14 (6): 1- 9. doi: 10.3321/j.issn:1001-506X.1992.06.001
8	张俊, 胡生亮, 杨庆, 等. 浮空式角反射体RCS统计特征及识别模型研究[J]. 系统工程与电子技术, 2019, 41 (4): 780- 786.
	ZHANG J , HU S L , YANG Q , et al. RCS statistical features and recognition model of air-floating corner reflector[J]. Systems Engineering and Electronics, 2019, 41 (4): 780- 786.
9	LIU W B , YUAN J W , ZHANG G , et al. HRRP target recognition based on kernel joint discriminant analysis[J]. Journal of Systems Engineering and Electronics, 2019, 30 (4): 703- 708.
10	DU C , CHEN B , XU B , et al. Factorized discriminative conditional variational auto-encoder for radar HRRP target recognition[J]. Signal Processing, 2019, 158 (5): 176- 189.
11	XIANG L , LI S D , YANG J , et al. A fast decoupled ISAR high-resolution imaging method using structural sparse information under low SNR[J]. Journal of Systems Engineering and Electronics, 2019, 30 (3): 492- 503.
12	BAI X R , ZHOU X N , ZHANG F , et al. Robust pol-ISAR target recognition based on ST-MC-DCNN[J]. IEEE Trans.on Geoscience and Remote Sensing, 2019, 57 (12): 9912- 9927. doi: 10.1109/TGRS.2019.2930112
13	WANG Y Z, FENG C Q, ZHANG Y S, et al. Space precession target classification based on radar high-resolution range profiles[EB/OL].[2019-10-12]. https://doi.org/10.1155/2019/8151620.
14	DONG Y B , ZHANG H , WANG C , et al. Fine-grained ship classification based on deep residual learning for high-resolution SAR images[J]. Remote Sensing Letters, 2019, 10 (11): 1095- 1104. doi: 10.1080/2150704X.2019.1650982
15	PAN M , JIANG J , KONG Q , et al. Radar HRRP target recognition based on t-SNE segmentation and discriminant deep belief network[J]. Geoscience and Remote Science Letter, 2017, 14 (9): 1609- 1613. doi: 10.1109/LGRS.2017.2726098
16	KIM Y , TOOMAJIAN B . Hand gesture recognition using micro-Doppler signatures with convolutional neural network[J]. IEEE Access, 2016, 4, 7125- 7130. doi: 10.1109/ACCESS.2016.2617282
17	WANG J , ZHU H , LEI P , et al. CNN based classification of rigid targets in space using radar micro-Doppler signatures[J]. Chinese Journal of Electronics, 2019, 28 (4): 856- 862. doi: 10.1049/cje.2018.08.003
18	FETTER S , SESSLER A , CORNWALL J , et al. Countermeasures: a technical evaluation of the operational effectiveness of the planned US national missile defense system[J]. Journal of Bacteriology, 2000, 188 (2): 450- 500.
19	GU F F , FU M H , LIANG B S , et al. Translational motion compensation and micro-Doppler feature extraction of space spinning targets[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (10): 1550- 1554.
20	陈行勇, 黎湘, 郭桂蓉, 等. 微进动弹道导弹目标雷达特征提取[J]. 电子与信息学报, 2006, 28 (4): 643- 646.
	CHEN H Y , LI X , GUO G R , et al. Radar feature extraetion of miero-preeession ballistie missile warhead[J]. Journal of Electronics & Information Technology, 2006, 28 (4): 643- 646.
21	CHEN V C . The micro-Doppler effect in radar[M]. Fitchburg: Artech House, 2011: 51- 61.
22	BASSEN R M . Radar systems analysis and design using matlab[M]. 3rd ed, Florida: CRC Press, 2013: 494- 511.
23	CORNIA M , BARALDI L , SERRA G , et al. Predicting human eye fixations via an LSTM-based saliency attentive model[J]. IEEE Trans.on Image Processing, 2018, 27 (10): 5142- 5154. doi: 10.1109/TIP.2018.2851672
24	HOCHREITER S , SCHMIDHUBER J . Long short-term me-mory[J]. Neural Computation, 1997, 9 (8): 1735- 1780. doi: 10.1162/neco.1997.9.8.1735
25	BENGIO Y , SIMARD S , FRASCONI P . Learning long-term dependencies with gradient descent is difficult[J]. IEEE Trans.on Neural Networks, 1994, 5 (2): 157- 66. doi: 10.1109/72.279181
26	LU Z , JIANG X D , KOT A . Deep coupled ResNet for low-resolution face recognition[J]. IEEE Signal Processing Letters, 2018, 25 (4): 526- 530. doi: 10.1109/LSP.2018.2810121
27	AFRIDIA M J , ROSS A , SHAPIRO E M . On automated source selection for transfer learning in convolutional neural networks[J]. Pattern Recognition, 2018, 73 (1): 65- 75.
28	SHIN H C , ROTH H R , GAO M C , et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning[J]. IEEE Trans.on Medical Imaging, 2016, 35 (5): 1285- 1298. doi: 10.1109/TMI.2016.2528162
29	ALICKOVIC E , SUBASI A . Ensemble SVM method for automatic sleep stage classification[J]. IEEE Trans.on Instrumentation and Measurement, 2018, 67 (6): 1258- 1265. doi: 10.1109/TIM.2018.2799059
30	MUGHAL M O , KIM S W . Signal classification and jamming detection in wide-band radios using naïve bayes classifier[J]. IEEE Communications Letters, 2018, 22 (7): 1398- 1401. doi: 10.1109/LCOMM.2018.2830769

参数名称	参数设置
参数名称	BiLSTM	CNN
ExecutionEnvironment	GPU	GPU
ValidationFrequency	20	20
GradientThreshold	2	2
numHiddenUnits	200	-
InitialLearnRate	0.000 1	0.000 1
MiniBatchSize	50	50
SolverName	RMSProp	Adam
-	-	-

分类方法	BiLSTM	SVM	Bayes	分类决策树
准确性/%	99.63	97.22	92.41	91.30

迭代次数	AlexNet		ResNet-18
迭代次数	训练时间/s	识别率/%	训练时间/s	识别率/%
2	56	88.70	59	91.48
5	128	92.04	139	95.18
8	198	93.89	230	94.63
10	243	93.22	275	94.81

网络模型	迭代次数	训练时间/s	仿真时间/s	识别率/%
ResNet-18	6	171	202	90.56
BiLSTM	130	345	349	97.41
本文算法	45	105	137	98.07

[1]	韩啸, 陈世文, 陈蒙, 杨锦程. 基于互易点学习的LPI信号开集识别[J]. 系统工程与电子技术, 2022, 44(9): 2752-2759.
[2]	张立民, 谭凯文, 闫文君, 张聿远. 基于多级跳线残差网络的雷达辐射源识别[J]. 系统工程与电子技术, 2022, 44(7): 2148-2156.
[3]	金国栋, 薛远亮, 谭力宁, 许剑锟. 基于孪生神经网络的目标跟踪算法进展研究[J]. 系统工程与电子技术, 2022, 44(6): 1805-1822.
[4]	赵晓枫, 徐叶斌, 吴飞, 牛家辉, 蔡伟, 张志利. 基于全局感知机制的地面红外目标检测方法[J]. 系统工程与电子技术, 2022, 44(5): 1461-1467.
[5]	李海, 白锦, 孙研, 任嘉伟. 基于修正小波变换插值-TAN的雷达降水粒子分类[J]. 系统工程与电子技术, 2022, 44(5): 1527-1535.
[6]	邹虹, 白陈阳, 何鹏, 崔亚平, 王汝言, 吴大鹏. 基于分布式深度学习的边缘服务放置策略[J]. 系统工程与电子技术, 2022, 44(5): 1728-1737.
[7]	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.
[8]	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.
[9]	姚云翔, 陈莹. 注意力机制下双模态交互融合的目标跟踪网络[J]. 系统工程与电子技术, 2022, 44(2): 410-419.
[10]	高涌荇, 王旭东, 汪玲, 朱岱寅, 郭军, 孟凡旺. 基于RCNN的双极化气象雷达天气信号检测[J]. 系统工程与电子技术, 2022, 44(11): 3380-3387.
[11]	孙照强, 王志贵, 孟飞, 李陆雨, 于中, 陈燕. 基于EKF及弹道方程的弹道目标跟踪滤波器设计[J]. 系统工程与电子技术, 2022, 44(10): 3207-3212.
[12]	周毅恒, 杨军, 夏赛强, 吕明久. 闪烁现象下旋翼目标微动参数估计方法[J]. 系统工程与电子技术, 2022, 44(1): 54-63.
[13]	付蓉, 黄天耀, 刘一民. 基于深度学习的捷变相参雷达1-Bit块稀疏重构[J]. 系统工程与电子技术, 2022, 44(1): 70-75.
[14]	张聿远, 张立民, 闫文君. 基于互相关特征图和扩张稠密卷积网络的SFBC-OFDM识别方法[J]. 系统工程与电子技术, 2021, 43(9): 2657-2664.
[15]	王彩云, 李阳雨, 李晓飞, 王佳宁, 魏文怡. 基于稀疏性深度学习的航拍图像超分辨重构[J]. 系统工程与电子技术, 2021, 43(8): 2045-2050.