采用CNN-SSD的雷达HRRP小样本目标识别方法

doi:10.19665/j.issn1001-2400.2021.02.002

Abstract

Abstract:

The development of radar high resolution range profile(HRRP)non-cooperative targets recognition technology is mainly limited by two aspects:(1) Due to the low observation frequency of non-cooperative targets,the number of labeled HRRPs is insufficient,making non-cooperative HRRP based target recognition a typical few-shot recognition problem,which is still a hot and difficult issue without definite conclusion in the academia.(2) The existing HRRP based target recognition methods are mostly based on the hypothesis of complete dataset,making them mismatch with non-cooperative target recognition in few-shot setting.In this paper,we put aside the complete hypothesis and propose an HRRP based few-shot target recognition method with CNN-SSD.The proposed method first uses a complete training HRRP containing 45 classes of cooperative targets to learn an initial category-independent feature extractor,on the basis of which we further utilize the model sequential self-distillation mechanism to obtain a more generalized feature extractor.Finally,the generalization ability of the extracted features is evaluated on unseen non-cooperative targets during training.Experimental results on self-simulated HRRP dataset reveal that the proposed method can achieve an average recognition rates of 61.26%,84.69% and 92.52% respectively when only 1,5 and 10 annotated HRRPs of non-cooperative targets are available.

Key words: radar target recognition, few shot learning, feature extraction, high resolution range profile, convolutional neural networks, sequential self-distillation, radar target recognition, few shot learning, feature extraction, high resolution range profile, convolutional neural networks, sequential self-distillation

CLC Number:

TP183

GUO Zekun,TIAN Long,HAN Ning,WANG Penghui,LIU Hongwei,CHEN Bo. Radar HRRP based few-shot target recognition with CNN-SSD[J].Journal of Xidian University, 2021, 48(2): 7-14.

Figures/Tables 6

References 13

[1]	徐丹蕾, 杜兰, 王鹏辉, 等. 采用多任务稀疏学习的雷达HRRP小样本目标识别[J]. 西安电子科技大学学报, 2016,43(2):23-28.
	XU Danlei, DU Lan, WANG Penghui, et al. Radar HRRP Target Recognition by Utilizing Multitask Sparse Learning with A Small Training Data Size[J]. Journal of Xidian University, 2016,43(2):23-28.
[2]	和华. 雷达高分辨距离像噪声稳健和小样本稳健识别方法研究[D]. 西安: 西安电子科技大学, 2016.
[3]	何松华, 张润民, 欧建平, 等. 基于卷积神经网络的高分辨率雷达目标识别[J]. 湖南大学学报, 2019,46(8 ): 141-148.
	HE Songhua, ZHANG Runmin, OU Jianping, et al. High Resolution Radar Target Recognition Based on Convolution Neural Network[J]. Journal of Hunan University, 2019,46(8):141-148.
[4]	杨予昊, 孙晶明, 虞盛康. 基于卷积神经网络迁移学习的飞机目标识别[J]. 现代雷达, 2019,41(12):35-39.
	YANG Yuhao, SUN Jingming, YU Shengkang. Aircraft Target Recognition Based on Convolutional Neural Network with Transfer Learning[J]. Modern Radar, 2019,41(12):35-39.
[5]	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.
[6]	TIAN L, CHEN B, PENG Y, et al. Meta Network for Radar HRRP Noncooperative Target Recognition with Missing Aspects[C]// Proceedings of the 2020 IEEE International Geoscience and Remote Sensing Symposium. Piscataway:IEEE, 2020: 2053-2056.
[7]	DU L, LIU H, BAO Z, et al. Radar HRRP Target Recognition Based on Higher Order Spectra[J]. IEEE Transactions on Signal Processing, 2005,53(7):2359-2368.
[8]	DU L, LIU H, BAO Z. Radar HRRP Statistical Recognition:Parametric Model and Model Selection[J]. IEEE Transactions on Signal Processing, 2008,56(5):1931-1944.
[9]	LEE K, MAJI S, RAVICHANDRAN A, et al. Meta-Learning with Differentiable Convex Optimization[C]//Proceedings of the 2019 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington:IEEE Computer Society, 2019: 10649-10657.
[10]	LAN Goodfellow, YOSHUA Bengio, AARON Courville. Deep Learning[M]. 北京: 人民邮电出版社, 2017:111-117.
[11]	HINTON G, VINYALS O, DEAN J. Distilling the Knowledge in a Neural Network[C/OL].[2020-11-26]. https://arxiv.org/pdf/1503.02531.pdf
[12]	FURLANELLO T, LIPTON Z C, TSCHANNEN M, et al. Born Again Neural Networks[C]//Proceedings of the 2018 35th International Conference on Machine Learning. Lille:IMLS, 2018: 2615-2624.
[13]	WAN J, CHEN B, XU B, et al. Convolutional Neural Networks for Radar HRRP Target Recognition and Rejection[J/OL].[2020-12-01]. https://doi.org/10.1186/s13634-019-0603-y.

模型	5个新类别(500个任务)
模型	1个样本	时间/s		5个样本		时间/s		10个样本		时间/s
SVM	41.60%±1.23%		0.181		66.80%±0.94%		0.376		77.29%±0.86%		0.696
Logistic	42.77%±1.17%		0.499		65.18%±0.90%		0.778		72.59%±0.88%		0.868
AGC	29.21%±0.96%		0.449		32.33%±0.97%		0.653		36.16%±0.96%		0.775
CNN-FC	19.81%±1.46%		0.769		20.21%±1.50%		0.688		19.70%±1.43%		0.872
CNNSSD-SVM	61.26%±0.13%		1.042		84.69%±0.08%		1.293		92.52%±0.51%		1.623
CNNSSD-Logistic	60.85%±0.13%		1.825		86.41%±0.82%		5.336		92.69%±0.54%		6.287

模型	5个新类别(500个任务)
模型	1个样本	时间/s	5个样本	时间/s	10个样本	时间/s
CNN-Logistic	59.14%±1.60%	2.389	84.81%±0.89%	6.153	92.19%±0.60%	10.423
CNNKD-Logistic	60.21%±0.14%	2.077	85.58%±0.83%	6.059	92.34%±0.56%	8.204
CNNSSD-Logistic	60.85%±0.13%	1.825	86.41%±0.82%	5.336	92.69%±0.54%	6.287
CNN-SVM	58.01%±1.54%	1.755	82.63%±0.85%	1.979	90.61%±0.68%	2.385
CNNKD-SVM	60.63%±1.41%	1.056	83.31%±0.81%	1.368	91.67%±0.53%	1.772
CNNSSD-SVM	61.26%±0.13%	1.042	84.69%±0.08%	1.293	92.52%±0.51%	1.623

[1]	QIAN Zhihua,GAO Chenqiang,YE Sheng. Method for detection of a student’s pose in a multi-scene classroom based on meta-learning [J]. Journal of Xidian University, 2021, 48(5): 58-67.
[2]	ZHANG Yuhao,CHENG Peitao,ZHANG Shuhao,WANG Xiumei. Lightweight image super-resolution with the adaptive weight learning network [J]. Journal of Xidian University, 2021, 48(5): 15-22.
[3]	HUI Haisheng,ZHANG Xueying,WU Zelin,LI Fenglian. Method for stroke lesion segmentation using the primary-auxiliary path attention compensation network [J]. Journal of Xidian University, 2021, 48(4): 200-208.
[4]	LIU Jieyi,GONG Maoguo,ZHAN Tao,LI Hao,ZHANG Mingyang. Method for discrimination of false targets in multistation radar systems based on the deep neural network [J]. Journal of Xidian University, 2021, 48(2): 133-138.
[5]	WEI Ziyu,YANG Xi,WANG Nannan,YANG Dong,GAO Xinbo. Reciprocal bi-directional generative adversarial network for cross-modal pedestrian re-identification [J]. Journal of Xidian University, 2021, 48(2): 205-212.
[6]	XU Bin,ZHANG Yongshun,ZHANG Qin,WANG Fuping,ZHENG Guimei. Radar HRRP target recognition based on the multiplicative RNN model [J]. Journal of Xidian University, 2021, 48(2): 49-54.
[7]	HAN Zhuoxi,WANG Feng,CHEN Pei,LI Zhuolun. Fuzzy data association algorithm assisted by historical features [J]. Journal of Xidian University, 2021, 48(2): 92-98.
[8]	LI Kunlun,ZHANG Lu,XU Hongke,SONG Huansheng. Waveletdomain dilated network for fast low-dose CT image reconstruction [J]. Journal of Xidian University, 2020, 47(4): 86-93.
[9]	DANG Jisheng,YANG Jun. 3D model recognition and segmentation based on multi-feature fusion [J]. Journal of Xidian University, 2020, 47(4): 149-157.
[10]	WANG Xiaohua,YAO Pengchao,MA Liping,WANG Wenjie,ZHANG Lei. Algorithm for extraction of features of robot speech control in the factory environment [J]. Journal of Xidian University, 2020, 47(2): 16-22.
[11]	WANG Jijun,HAO Ziyu,LI Hongliang. Optimization of memory access for the convolutional neural network training [J]. Journal of Xidian University, 2020, 47(2): 98-107.
[12]	WANG Hongyan,ZHU Limin,ZHANG Panjie,LI Jinping. Method for the detection of the piston side defect based on external contour registration [J]. Journal of Xidian University, 2019, 46(5): 75-83.
[13]	GUO Rui,ZANG Bo,PENG Shuming,XING Mengdao. Extraction of features of the urban high-rise building from high resolution InSAR data [J]. Journal of Xidian University, 2019, 46(4): 137-143.
[14]	ZHU Suya,DU Jianchao,LI Yunsong,WANG Xiaopeng. Method for bridge crack detection based on the U-Net convolutional networks [J]. Journal of Xidian University, 2019, 46(4): 35-42.
[15]	YANG Jiangong,WANG Xili,LIU Shigang. Spectral-spatial classification of hyperspectral images using deep Boltzmann machines [J]. Journal of Xidian University, 2019, 46(3): 109-115.

Radar HRRP based few-shot target recognition with CNN-SSD

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 13

Related Articles 15

Metrics

Comments

Recommended 10