一种用于锥体目标微动分类的深度学习模型

doi:10.19665/j.issn1001-2400.2020.03.015

摘要/Abstract

摘要：

针对传统的空间锥体目标微动分类需人工构造、提取特征而缺乏通用性、智能性及在强噪声条件下分类性能差等问题,提出一种卷积神经网络和双向长短期记忆网络相结合的网络新模型。该网络将残差网络、Inception网络及双向长短期记忆网络融合成一体化网络,通过增加网络的深度和宽度来挖掘更高维度的抽象特征以提升网络的分类准确率,而双向长短期记忆网络的推理能力能提高网络的容错性,时序分类的优势,以及残差网络跳跃式的旁路支线结构还能减少参数冗余,加快网络训练速度。仿真结果表明,该网络模型不仅能实现更快速的智能分类,同时比ResNet-18、GoogLeNet模型的精度分别提高5%、4%,验证了该模型的有效性和泛化能力。

关键词: 空间锥体目标, 微动分类, 时频分析, 深度学习

Abstract:

To overcome the shortcomings of traditional micro-motion classification of spatial cone targets, such as manual construction, feature extraction, and lack of generality, intelligence and poor classification performance under strong noise, a new network model combining a convolutional neural network and a bidirectional long short-term memory network is proposed. The network combines the residual network, inception network and bidirectional long short-term memory network into an integrated network. By increasing the depth and width of the network to mine the abstract features of higher dimensions, the classification accuracy of the network can be improved. The reasoning ability of the bidirectional long short-term memory network can improve the fault tolerance of the network, and the advantages of time series classification and the jumping bypass branch structure of the residual network can also reduce parameter redundancy and speed up network training. Simulation results show that the network model not only achieves faster intelligent classification, but also improves the accuracy of ResNet-18 and GoogLeNet models by 5% and 4% respectively, thus verifying the validity and generalization ability of the model.

Key words: spatial cone target, micro-motion classification, time-frequency analysis, deep learning

中图分类号:

TN957

李江,冯存前,王义哲,许旭光. 一种用于锥体目标微动分类的深度学习模型[J]. 西安电子科技大学学报, 2020, 47(3): 105-112.

LI Jiang,FENG Cunqian,WANG Yizhe,XU Xuguang. Deep learning model for micro-motion classification of cone targets[J]. Journal of Xidian University, 2020, 47(3): 105-112.

图/表 11

图1

图2

表1

图3

图4

图5

表2

图6

表3

图7

表4

参考文献 24

[1]	CHEN V C. Analysis of Radar Micro-Doppler Signature with Time-frequency Transform [C]//Proceedings of the 2000 10th IEEE Workshop on Statistical Signal and Array Processing. Piscataway: IEEE, 2000: 463-466.
[2]	CHEN V C, LI F, HO S S, et al. Analysis of Micro-Doppler Signatures[J]. IEE Proceedings: Radar, Sonar and Navigation, 2003,150(4):271-276. doi: 10.1049/ip-rsn:20030743
[3]	WANG Y Z, ZHANG Y S, HE S S, et al. Precession Parameters Estimation of Space Rotationally Symmetric Targets Based on HRRP Sequences[J]. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2018,E101A(9):1580-1584.
[4]	韩勋, 杜兰, 刘宏伟, 等. 基于时频分布的空间锥体目标微动形式分类[J]. 系统工程与电子技术, 2013,35(4):684-691. doi: 10.3969/j.issn.1001-506X.2013.04.02
	HAN Xun, DU Lan, LIU Hongwei, et al. Classfifcation of Micro Motion form of Space Cone Shaped Objects Based on Time-frequency Distribution[J]. Systems Engineering and Electronics, 2013,35(4):684-691. doi: 10.3969/j.issn.1001-506X.2013.04.02
[5]	关永胜, 左群声, 刘宏伟, 等. 空间锥体目标微动特性分析与识别方法[J]. 西安电子科技大学学报, 2011,38(2):105-111.
	GUAN Yongsheng, ZUO Qunsheng, LIU Hongwei, et al. Micro-motion Characteristic Analysis and Recognition of Cone-shaped Targets[J]. Journal of Xidian University, 2011,38(2):105-111.
[6]	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 Changyong, ZHANG Shengjun, HUANG Peilin, 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.
[7]	刘树东, 王晓敏, 张艳. 一种对称残差CNN的图像超分辨率重建方法[J]. 西安电子科技大学学报, 2019,46(5):15-23.
	LIU Shudong, WANG Xiaomin, ZHANG Yan. Symmetric Residual Convolution Neural Networks for the Image Super-resolution Reconstruction[J]. Journal of Xidian University, 2019,46(5):15-23.
[8]	YUEK, YANG L, LI R R, et al. TreeUNet: Adaptive Tree Convolutional Neural Networks for Subdecimeter Aerial Image Segmentation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019,156(10):1-13. doi: 10.1016/j.isprsjprs.2019.07.007
[9]	王世平, 毕笃彦, 刘坤, 等. 一种多映射卷积神经网络的超分辨率重建算法[J]. 西安电子科技大学学报, 2018,45(4):155-160.
	WANG Shiping, BI Duyuan, LIU Kun, et al. Multi Mapping Convolution Neural Network for the Image Super-resolution Algorithm[J]. Journal of Xidian University, 2018,45(4):155-160.
[10]	YANG Y, HOU C P, LANG Y, et al. Person Identification Using Micro-Doppler Signatures of Human Motions and UWB Radar[J]. IEEE Microwave and Wireless Components Letters, 2019,29(5):366-368. doi: 10.1109/LMWC.7260
[11]	CAO P B, XIA W J, YE M, et al. Radar-ID: Human Identification Based on Radar Micro-Doppler Signatures Using Deep Convolutional Neural Networks[J]. IET Radar, Sonar and Navigation, 2018,12(7):729-734. doi: 10.1049/iet-rsn.2017.0511
[12]	SKARIA S, AI-HOURANI A, LECH M, et al. Hand-gesture Recognition Using Two-antenna Doppler Radar with Deep Convolutional Neural Networks[J]. IEEE Sensors Journal, 2019,19(8):3041-3048. doi: 10.1109/JSEN.2019.2892073
[13]	PAN M, JIANG J, KONG Q, et al. Radar HRRP Target Recognition Based on t-SNE Segmentation and Discriminant Deep Belief Network[J]. IEEE Geoscience and Remote Sensing Letters, 2017,14(9):1609-1613. doi: 10.1109/LGRS.2017.2726098
[14]	苏宁远, 陈小龙, 关键, 等. 基于卷积神经网络的海上微动目标检测与分类方法[J]. 雷达学报, 2018,7(5):565-574.
	SU Ningyuan, CHEN Xiaolong, GUAN Jian, et al. Detection and Classification of Maritime Target with Micro-motion Based on CNNs[J]. Journal of Radars, 2018,7(5):565-574.
[15]	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
[16]	WEN Z G, LIU D, LIU X Q, et al. Deep Learning Based Smart Radar Vision System for Object Recognition[J]. Journal of Ambient Intelligence and Humanized Computing, 2019,10(3):829-839. doi: 10.1007/s12652-018-0853-9
[17]	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. doi: 10.21629/JSEE.2019.04.08
[18]	徐彬, 陈渤, 刘家麒, 等. 采用双向LSTM模型的雷达HRRP目标识别[J]. 西安电子科技大学学报, 2019,46(2):29-34.
	XU Bin, CHEN Bo, LIU Jiaqi, et al. Radar HRRP Target Recognition by the Bidirectional LSTM Model[J]. Journal of Xidian University, 2019,46(2):29-34.
[19]	WANG Y Z, FENG C Q, ZHANG Y S, et al. Classification of Space Targets with Micro-Motion Based on Deep CNN [C]//Proceedings of the 2019 IEEE 2nd International Conference on Electronic Information and Communication Technology. Piscataway: IEEE, 2019: 557-561.
[20]	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
[21]	AINUJAIM I, OH D, PARK I, et al. Classification of Micro-Doppler Signatures Measured by Doppler Radar Through Transfer Learning [C]//Proceedings of the 2019 13th European Conference on Antennas and Propagation. Piscataway: IEEE, 2019: 8740208.
[22]	HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition [C]//Proceedings of the 2016 IEEE Computer Society Conference on Compute Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 770-778.
[23]	SZEGEDY C, LIU W, JIA Y Q, et al. Going Deeper with Convolutions [C]//Proceedings of the 2015 IEEE Computer Society Conference on Compute Vision and Pattern Recognition. Washington: IEEE Computer Society, 2015: 1-9.
[24]	BENGIO Y, SIMARD P, FRASCONI P. Learning Long-Term Dependencies with Gradient Descent is Difficult[J]. IEEE Transactions on Neural Networks, 1994,5(2):157-166. doi: 10.1109/TNN.72

微动参数	自旋	进动	章动
α/(°)	105:5:150	105:5:150	105:5:150
θ₀/(°)	16:2:20	16:2:20	16:2:20
φ₀/(°)	18:18:360	0	0
f_φ/Hz		0.82:0.02:1.2	0.84:0.04:1.2
θ₁/(°)			10
f_θ/Hz			1.0:0.5:1.5

方法	识别率/%
方法	自旋	进动	章动	平均
文献[4]	21.2	17.4	90.8	43.1
文献[6]	100.0	44.3	48.5	64.3
文中方法	99.7	100.0	100.0	99.9

网络算法	AlexNet	CNN+BiLSTM	ResNet-18	GoogLeNet	文中网络
识别率/%	76.44	79.11	90.11	91.48	96.85
训练时间/s	347	277	241	821	87
训练周期/轮	15	141	8	17	20

网络算法	AlexNet	SqueezeNet	ResNet-18	GoogLeNet	文中网络
识别率/%	99.09	98.00	99.11	99.04	98.28
训练时间/min	57.08	72.70	92.70	109.37	7.43