基于一维堆叠池化融合卷积自编码器的HRRP目标识别方法

doi:10.12305/j.issn.1001-506X.2021.12.15

系统工程与电子技术 ›› 2021, Vol. 43 ›› Issue (12): 3533-3541.doi: 10.12305/j.issn.1001-506X.2021.12.15

基于一维堆叠池化融合卷积自编码器的HRRP目标识别方法

张国令¹, 吴崇明^2,*, 李睿¹, 来杰¹, 向前¹

1. 空军工程大学防空反导学院, 陕西西安 710051
2. 西京学院, 陕西西安 710123

收稿日期:2020-06-28 出版日期:2021-11-24 发布日期:2021-11-30
通讯作者: 吴崇明
作者简介:张国令(1995—), 男, 硕士研究生, 主要研究方向为人工智能、智能信息处理|吴崇明(1966—), 男, 副教授, 博士, 主要研究方向人工智能、智能信息处理|李睿(1992—), 男, 博士研究生, 主要研究方向为人工智能、智能信息处理|来杰(1994—), 男, 博士研究生, 主要研究方向为人工智能、网络空间安全|向前(1995—), 男, 博士研究生, 主要研究方向为人工智能、智能信息处理、网络空间安全
基金资助:
国家自然科学基金(61876189);国家自然科学基金(61273275);国家自然科学基金(61503407);国家自然科学基金(61806219);国家自然科学基金(61703426)

HRRP target recognition method based on one-dimensional stacked pooling fusion convolutional autoencoder

Guoling ZHANG¹, Chongming WU^2,*, Rui LI¹, Jie LAI¹, Qian XIANG¹

1. Air and Missile Defense College, Air Force Engineering University, Xi'an 710051, China
2. Xijing College, Xi'an 710123, China

Received:2020-06-28 Online:2021-11-24 Published:2021-11-30
Contact: Chongming WU

摘要/Abstract

摘要：

针对雷达高分辨距离像(high resolution range profile, HRRP)目标识别中特征提取及识别问题, 提出了一种基于一维堆叠池化融合卷积自编码器(one-dimensional stacked pooling fusion convolutional autoencoder, 1D SPF-CAE)的识别方法。首先构造一维池化融合卷积自编码器(one-dimensional pooling fusion convolutional auto-encoder, 1D PF-CAE), 在编码阶段, 采用最大池化和平均池化同时提取不同的编码特征并进行融合来提取HRRP的结构特征; 然后堆叠多个1D PF-CAE形成1D SPF-CAE; 最后使用标签数据对网络进行微调, 实现HRRP目标识别。并使用AdaBound算法优化网络训练来提高识别性能。基于弹道中段目标仿真数据的实验结果表明, 该方法具有较强的特征提取能力, 对于HRRP目标识别准确率高、鲁棒性强。

关键词: 雷达自动目标识别, 高分辨距离像, 卷积自编码器, 特征提取, 池化融合

Abstract:

Aiming at the problem of feature extraction and recognition in high resolution range profile (HRRP) target recognition, a recognition method based on one-dimensional stacked pooling fusion convolutional autoencoder (1D SPF-CAE) is proposed in this paper. Firstly, a one-dimensional pooling fusion convolutional autoencoder (1D PF-CAE) is constructed. In the encoding stage, the maximum pooling and average pooling are used to extract different encoding features and fuse them to extract the structural features of HRRP. Then, multiple 1D PF-CAEs are stacked to form 1D SPF-CAE. Finally, the network is fine-tuned using label data to realize HRRP target recognition. And the AdaBound algorithm is used to optimize network training for improving the recognition performance. The experimental results based on the simulated data of the target in the middle part of the trajectory show that the method has strong feature extraction capability, and has high accuracy and robustness for HRRP target recognition.

Key words: radar automatic target recognition, high resolution range profile, convolution autoencoder, feature extraction, pooling fusion

中图分类号:

TP183

张国令, 吴崇明, 李睿, 来杰, 向前. 基于一维堆叠池化融合卷积自编码器的HRRP目标识别方法[J]. 系统工程与电子技术, 2021, 43(12): 3533-3541.

Guoling ZHANG, Chongming WU, Rui LI, Jie LAI, Qian XIANG. HRRP target recognition method based on one-dimensional stacked pooling fusion convolutional autoencoder[J]. Systems Engineering and Electronics, 2021, 43(12): 3533-3541.

图/表 13

图1

图2

图3

图4

表1

图5

图6

表2

图7

表3

图8

图9

图10

参考文献 24

1	LIAO K , SI J X , ZHU F Q , et al. Radar HRRP target recognition based on concatenated deep neural networks[J]. IEEE Access, 2018, 6, 29211- 29218. doi: 10.1109/ACCESS.2018.2842687
2	LI L , LIU Z , LI T . Radar high resolution range profile recognition via multi-SV method[J]. Journal of Systems Engineering and Electronics, 2017, 28 (5): 879- 889. doi: 10.21629/JSEE.2017.05.07
3	LIU J , FANG N , XIE Y J , et al. Scale-space theory-based mutil-scale feature for aircraft classification using HRRP[J]. Electronics Letters, 2016, 52 (6): 475- 477. doi: 10.1049/el.2015.3583
4	李龙, 刘峥. 基于核主分量相关判别分析特征提取方法的目标HRRP识别[J]. 电子与信息学报, 2018, 40 (1): 173- 180.
	LI L , LIU Z . Kernel principal component correlation and discrimination analysis feature extraction method for target HRRP recognition[J]. Journal of Electronics & Information Technology, 2018, 40 (1): 173- 180.
5	ZHOU D Y . Radar target HRRP recognition based on reconstructive and discriminative dictionary learning[J]. Signal Processing, 2016, 126, 52- 64. doi: 10.1016/j.sigpro.2015.12.006
6	GUO Y , XIAO H T , KAN Y Z , et al. Learning using privileged information for HRRP-based radar target recognition[J]. IET Signal Processing, 2018, 12 (2): 188- 197. doi: 10.1049/iet-spr.2016.0625
7	PAN M , JIANG J , KONG Q P , 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
8	杨予昊, 孙晶明, 虞盛康, 等. 基于卷积神经网络的高分辨距离像目标识别[J]. 现代雷达, 2017, 39 (12): 28- 32.
	YANG Y H , SUN J M , YU S K , et al. High resolution range profile target recognition based on convolutional neural network[J]. Modern Radar, 2017, 39 (12): 28- 32.
9	FENG B , CHEN B , LIU H W . Radar HRRP target recognition with deep networks[J]. Pattern Recognition, 2017, 61, 379- 393. doi: 10.1016/j.patcog.2016.08.012
10	ZHAO F X , LIU Y X , HUO K , et al. Radar HRRP target recognition based on stacked autoencoder and extreme learning machine[J]. Sensors, 2018, 18 (1): 173- 187.
11	CHEN M , SHI X B , ZHANG Y , et al. Deep features learning for medical image analysis with convolutional autoencoder neural network[J]. IEEE Trans.on Big Data, 2017, doi: 10.1109/TBDATA.2017.2717439
12	HUANG H , HU X T , ZHAO Y , et al. Modeling task fMRI data via deep convolutional autoencoder[J]. IEEE Trans.on Medical Imaging, 2017, 37 (7): 1551- 1561.
13	LUO W , LI J , YANG J , et al. Convolutional sparse autoencoders for image classification[J]. IEEE Trans.on Neural Networks, 2018, 29 (7): 3289- 3294.
14	DU B , XIONG W , WU J , et al. Stacked convolutional denoising auto-encoders for feature representation[J]. IEEE Trans.on Cybernetics, 2017, 47 (4): 1017- 1027. doi: 10.1109/TCYB.2016.2536638
15	LUO L, XIONG Y, LIU Y, et al. Adaptive gradient methods with dynamic bound of learning rate[EB/OL]. [2020-07-24]. https://arxiv.org/abs/1902.09843?context=cs.LG.
16	HOU B R , YAN R Q . Convolutional auto-encoder model for finger-vein verification[J]. IEEE Trans.on Instrumentation & Measurement, 2020, 69 (5): 2067- 2074.
17	严国萍, 陈禹, 李雨冲, 等. 基于一维堆叠卷积自编码器的分布式应变裂缝检测[J]. 计算机系统应用, 2020, 29 (1): 144- 150.
	YAN G P , CHEN Y , LI Y C , et al. Distributed strain crack detection based on one-dimensional stacked convolutional autoencoder[J]. Computer Systems & Applications, 2020, 29 (1): 144- 150.
18	张海利, 王普, 高学金, 等. 基于批次图像化的卷积自编码故障监测方法[J]. 控制与决策, 2021, 36 (6): 1361- 1367.
	ZHANG H L , WANG P , GAO X J , et al. Fault detection of batch image-based convolutional autoencoder[J]. Control and Decision, 2021, 36 (6): 1361- 1367.
19	罗畅, 王洁, 王鹏飞, 等. 卷积自编码器中粗粒度池化特征提取研究[J]. 电子学报, 2017, 45 (10): 2390- 2401. doi: 10.3969/j.issn.0372-2112.2017.10.012
	LUO C , WANG J , WANG P F , et al. Coarse-grained pooled features learning in convolutional autoencoders[J]. Acta Electronica Sinica, 2017, 45 (10): 2390- 2401. doi: 10.3969/j.issn.0372-2112.2017.10.012
20	WAHLBECK K , TUUNAINEN A , AHOKAS A , et al. Dropout rates in randomised antipsychotic drug triais[J]. Psychopharmacology, 2001, 155 (3): 230- 233. doi: 10.1007/s002130100711
21	BENGIO Y , LAMBLIN P , DAN P , et al. Greedy layer-wise training of deep networks[J]. Proceedings of the Advances in Neural Information Processing Systems, 2006, 19, 153- 160.
22	VINCENT P , LAROCHELLE H , LAJOIE I , et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11 (12): 3371- 3408.
23	LE Q V, NGIAM I, COATES A, et al. On optimization methods for deep learning[C]//Proc. of the 28th International Conference on Machine Learning, 2011.
24	张国令, 王晓丹, 李睿, 等. 基于栈式降噪稀疏自编码器的极限学习机[J]. 计算机工程, 2020, 46 (9): 61- 67.
	ZHANG G L , WANG X D , LI R , et al. Stacked denoising sparse autoencoder based extreme learning machine[J]. Computer Engineering, 2020, 46 (9): 61- 67.

网络层	输入	核数	核/窗口	步长	输出
C1	(256×1)×1	32	3×1	1	(256×1)×32
C1	(256×1)×1	32	3×1	1	(256×1)×32
P1_max	(256×1)×32	—	2×1	2	(128×1)×32
P1_avg	(256×1)×32	—	2×1	2	(128×1)×32
P1	—	—	—	—	(128×1)×64
C2	(128×1)×64	48	3×1	1	(128×1)×48
C2	(128×1)×48	48	3×1	1	(128×1)×48
P2_max	(128×1)×48	—	2×1	2	(64×1)×48
P2_avg	(128×1)×48	—	2×1	2	(64×1)×48
P2	—	—	—	—	(64×1)×96
C3	(64×1)×96	64	3×1	1	(64×1)×64
C3	(64×1)×64	64	3×1	1	(64×1)×64
P3_max	(64×1)×64	—	2×1	2	(32×1)×64
P3_avg	(64×1)×64	—	2×1	2	(32×1)×64
P3	—	—	—	—	(32×1)×128
Flatten	(32×1)×128	—	—	—	4 096×1
全连接	4 096×1	—	—	—	400×1
Softmax	400×1	—	—	—	5×1

数据集	平均池化	最大池化	平均+最大池化
A	95.45	95.91	96.49
B	94.89	95.27	95.84
C	94.02	93.83	94.92

堆叠层数	各层卷积核数	识别准确率/%
1	32	93.86
2	32-48	95.63
3	32-48-64	96.49
4	32-48-64-80	96.57
5	32-48-64-80-96	96.01
6	32-48-64-80-96-112	95.14

[1]	马泽煊, 李进, 路艳丽, 陈晨. 融合WaveNet和BiGRU的网络入侵检测方法[J]. 系统工程与电子技术, 2022, 44(8): 2652-2660.
[2]	李郝亮, 陈思伟, 王雪松. 海面角反射器的极化旋转域特性研究[J]. 系统工程与电子技术, 2022, 44(7): 2065-2073.
[3]	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.
[4]	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.
[5]	王彩云, 姚晨, 吴钇达, 王佳宁, 李晓飞, 黄盼盼. 基于改进Dijkstra算法与时频域滤波的雷达目标识别[J]. 系统工程与电子技术, 2022, 44(10): 3090-3095.
[6]	但波, 付哲泉, 高山, 简涛. 基于卷积神经网络的海面目标全极化高分辨距离像识别技术[J]. 系统工程与电子技术, 2022, 44(1): 108-116.
[7]	朱峰, 蒋倩倩, 林川, 杨啸. 基于支持向量机的典型宽带电磁干扰源识别[J]. 系统工程与电子技术, 2021, 43(9): 2400-2406.
[8]	王力, 刘子奇. WPA-IGA-BP神经网络的模拟电路故障诊断[J]. 系统工程与电子技术, 2021, 43(4): 1133-1143.
[9]	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.
[10]	张良, 杨威, 李玮杰, 杨小琪, 刘永祥. 基于复数卷积-残差网络的雷达杂波幅度统计模型分类[J]. 系统工程与电子技术, 2021, 43(11): 3086-3097.
[11]	赵若辰, 王敬东, 林思玉, 顾东泽. 基于卷积神经网络的小型建筑物检测算法[J]. 系统工程与电子技术, 2021, 43(11): 3098-3106.
[12]	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.
[13]	卢旺, 张雅声, 徐灿, 林财永. 基于双谱-谱图特征和深度卷积神经网络的HRRP目标识别方法[J]. 系统工程与电子技术, 2020, 42(8): 1703-1709.
[14]	张天骐, 范聪聪, 喻盛琪, 赵健根. 基于JADE与特征提取的正交/非正交空时分组码盲识别[J]. 系统工程与电子技术, 2020, 42(4): 933-939.
[15]	弋佳东, 杨洁. 基于IFOA-SA-BP神经网络的雷达信号识别[J]. 系统工程与电子技术, 2020, 42(12): 2735-2741.

基于一维堆叠池化融合卷积自编码器的HRRP目标识别方法

HRRP target recognition method based on one-dimensional stacked pooling fusion convolutional autoencoder

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 24

相关文章 15

编辑推荐

Metrics

本文评价