一种Chirplet神经网络自动目标识别算法

doi:10.6040/j.issn.1672-3961.0.2019.062

摘要/Abstract

摘要：

针对飞机目标的自动识别问题,提出一种联合特征提取与分类的Chirplet神经网络方法,实现一维高分辨率距离像的识别。Chirplet神经网络将Chirplet原子变换用于多层前馈神经网络结构的输入层,替换传统的激励函数对距离像序列进行特征提取;网络的分类部分由隐层和输出层组成。在训练过程中调整神经网络权值的同时,完成对Chirplet原子时频参数的自动调整,协调优化特征参数和分类器参数,使Chirplet神经网络同时实现特征提取和目标分类。对4类飞机目标的仿真测试结果表明,相比时频变换和Gabor原子网络等方法,具有四特征参数的Chirplet神经网络方法具有较高的识别率和抗噪性能。

关键词: 自动目标识别, 高分辨率距离像, Chirplet神经网络

Abstract:

Aiming at automatic target recognition of aircrafts, a Chirplet neural network for joint feature extraction and target classification was proposed to realize recognition of one-dimensional high resolution range profiles. Based on the multilayer feedforward neural network structure, the Chirplet-atom transform was used to replace the conventional excitation function in the input layer for feature extraction, and the hidden layer and output layer constituted the classifier of the network. The network weights and the parameters of Chirplet-atom node were simultaneously adjusted and optimized to achieve joint feature extraction and target classification. The simulation results of the four types of aircrafts showed that the Chirplet neural network method with the four-feature-parameters had higher recognition rate and anti-noise performance than the time-frequency transformation and Gabor atoms network.

Key words: automatic target recognition, high resolution range profile, Chirplet neural network

中图分类号:

TP183

李怡霏,郭尊华. 一种Chirplet神经网络自动目标识别算法[J]. 山东大学学报 (工学版), 2020, 50(3): 8-14.

Yifei LI,Zunhua GUO. A Chirplet neural network for automatic target recognition[J]. Journal of Shandong University(Engineering Science), 2020, 50(3): 8-14.

图/表 7

图1

图2

表1

表2

表3

图3

表4

参考文献 25

1	LI H J , YANG S H . Using range profiles as feature vectors to identify aerospace objects[J]. IEEE Transactions on Antennas and Propagation, 1993, 41 (3): 261- 268. doi: 10.1109/8.233138
2	JACOBS S P , O'SULLIVAN J A . Automatic target recognition using sequences of high resolution radar range-profiles[J]. IEEE Transactions on Aerospace and Electronic Systems, 2000, 36 (2): 364- 381. doi: 10.1109/7.845214
3	CHEN J , DU L , HE H , et al. Convolutional factor analysis model with application to radar automatic target recognition[J]. Pattern Recognition, 2019, 87, 140- 156. doi: 10.1016/j.patcog.2018.10.014
4	郭尊华, 李达, 张伯彦. 雷达高距离分辨率一维像目标识别[J]. 系统工程与电子技术, 2013, 35 (1): 53- 60. doi: 10.3969/j.issn.1001-506X.2013.01.09
	GUO Zunhua , LI Da , ZHANG Boyan . Survey of radar target recognition using one-dimensional high range resolution profiles[J]. Systems Engineering & Electronics, 2013, 35 (1): 53- 60. doi: 10.3969/j.issn.1001-506X.2013.01.09
5	张贤达. 现代信号处理[M]. 2版北京: 清华大学出版社, 2002.
6	GUO Z H , LI S H . One-dimensional frequency-domain features for aircraft recognition from radar range profiles[J]. IEEE Transactions on Aerospace & Electronic Systems, 2010, 46 (4): 1880- 1892.
7	DUIN R , PE , KALSKA E . The science of pattern recognition. Achievements and perspectives[J]. Studies in Computational Intelligence, 2007, 63, 221- 259.
8	徐彬, 陈渤, 刘宏伟, 等. 基于注意循环神经网络模型的雷达高分辨率距离像目标识别[J]. 电子与信息学报, 2016, 38 (12): 2988- 2995.
	XU Bin , CHEN Bo , LIU Hongwei , et al. Attention-based recurrent neural network model for radar high-resolution range profile target recognition[J]. Journal of Electronics & Information Technology, 2016, 38 (12): 2988- 2995.
9	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
10	LUNDEN J, KOIVUNEN V. Deep learning for HRRP-based target recognition in multistatic radar systems[C]//Proceedings of 2016 IEEE Radar Conference (RadarConf). Philadelphia, USA: IEEE, 2016: 1-6.
11	殷和义, 郭尊华. 一维卷积神经网络用于雷达高分辨率距离像识别[J]. 电讯技术, 2018, 58 (10): 1121- 1126. doi: 10.3969/j.issn.1001-893x.2018.10.002
	YIN Heyi , GUO Zunhua . Radar HRRP target recognition with one-dimensional CNN[J]. Telecommunication Engineering, 2018, 58 (10): 1121- 1126. doi: 10.3969/j.issn.1001-893x.2018.10.002
12	SHAW A K , PAUL A S , WILLIAMS R . Eigen-template-based HRR-ATR with multi-look and time-recursion[J]. IEEE Transactions on Aerospace and Electronic Systems, 2013, 49 (4): 2369- 2385. doi: 10.1109/TAES.2013.6621822
13	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
14	LIU H , FENG B , CHEN B , et al. Radar high-resolution range profiles target recognition based on stable dictionary learning[J]. IET Radar, Sonar & Navigation, 2016, 10 (2): 228- 237.
15	ZHAO Q , PRINCIPE J C . Support vector machines for SAR automatic target recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2001, 37 (2): 643- 654. doi: 10.1109/7.937475
16	LIU W B , WANG Z D , LIU X H , et al. A survey of deep neural network architectures and their applications[J]. Neurocomputing, 2017, 234, 11- 26. doi: 10.1016/j.neucom.2016.12.038
17	ALEXANDRIDIS A K , ZAPRANIS A D . Wavelet neural networks: a practical guide[J]. Neural Networks, 2013, 42, 1- 27. doi: 10.1016/j.neunet.2013.01.008
18	SHI Y , ZHANG X D . A Gabor atom network for signal classification with application in radar target recognition[J]. IEEE Transactions on Signal Processing, 2001, 49 (12): 2994- 3004. doi: 10.1109/78.969508
19	ZHU F , ZHANG X D , HU Y F . Gabor filter approach to joint feature extraction and target recognition[J]. IEEE Transactions on Aerospace and Electronic systems, 2009, 45 (1): 17- 30. doi: 10.1109/TAES.2009.4805260
20	MANN S, HAYKIN S. The chirplet transform: a generalization of Gabor's logon transform[C]//Proceedings Vision Interface'91. Alberta, Canada: University of Calgary, 1991: 205-212.
21	MANN S , HAYKIN S . Adaptive "chirplet" transform: an adaptive generalization of the wavelet transform[J]. Optical Engineering, 1992, 31 (6): 1243- 1256. doi: 10.1117/12.57676
22	MANN S , HAYKIN S . The chirplet transform: physical considerations[J]. IEEE Transactions on Signal Processing, 1995, 43 (11): 2745- 2761. doi: 10.1109/78.482123
23	YANG Y , PENG Z K , DONG X J , et al. General parameterized time-frequency transform[J]. IEEE Transactions on Signal Processing, 2014, 62 (11): 2751- 2764. doi: 10.1109/TSP.2014.2314061
24	BULTAN A . A four-parameter atomic decomposition of chirplets[J]. IEEE Transactions on Signal Processing, 1999, 47 (3): 731- 745. doi: 10.1109/78.747779
25	朱明, 金炜东, 普运伟, 等. 基于Chirplet原子的雷达辐射源信号特征提取[J]. 红外与毫米波学报, 2007, 26 (4): 302- 306. doi: 10.3321/j.issn:1001-9014.2007.04.014
	ZHU Ming , JIN Weidong , PU Yunwei , et al. Feature extraction of radar emitter signals based on gaussian chirplet atoms[J]. Journal of Infrared & Millimeter Waves, 2007, 26 (4): 302- 306. doi: 10.3321/j.issn:1001-9014.2007.04.014

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

识别方法	识别率/%				训练耗时/s
识别方法	YF22	J6	F117	B2	训练耗时/s
距离像	78.3	86.7	78.7	84.7	6.70
FFT	89.5	94.0	88.1	95.8	9.89
Gabor变换	91.7	95.8	89.6	96.3	7.54
Chirplet变换	92.3	96.9	90.6	96.7	8.59
小波神经网络	94.3	96.8	92.0	96.4	0.96
Gabor原子网络	95.1	99.1	96.7	97.6	1.22
Chirplet神经网络	97.7	99.8	97.0	98.1	2.13

识别方法	识别率/%				训练耗时/s
识别方法	YF22	J6	F117	B2	训练耗时/s
距离像	76.3	82.4	73.8	82.3	8.90
FFT	80.9	89.8	80.5	95.7	12.41
Gabor变换	82.3	88.3	81.6	96.0	9.39
Chirplet变换	82.5	92.6	83.2	95.5	12.86
小波神经网络	83.2	90.7	80.8	94.5	10.57
Gabor原子网络	85.3	93.8	85.2	96.7	23.38
Chirplet神经网络	87.2	95.3	86.5	96.8	29.50

识别方法	识别率/%				训练耗时/s
识别方法	YF22	J6	F117	B2	训练耗时/s
距离像	72.8	80.9	71.0	80.2	13.00
FFT	74.8	83.0	74.2	96.6	21.22
Gabor变换	77.6	86.7	77.5	96.3	14.91
Chirplet变换	78.0	92.0	79.8	96.8	20.07
小波神经网络	79.3	89.8	81.9	94.8	32.34
Gabor原子网络	83.1	91.8	82.5	95.7	137.69
Chirplet神经网络	83.9	92.1	84.7	96.0	156.22

识别方法	识别率/%
识别方法	YF22	J6	F117	B2
距离像	44.9	48.6	49.5	46.0
FFT	55.1	53.4	51.3	69.8
Gabor变换	51.6	52.2	48.0	67.4
Chirplet变换	59.8	51.4	54.1	73.4
小波神经网络	65.7	76.5	71.4	74.7
Gabor原子网络	72.8	74.5	70.1	76.8
Chirplet神经网络	75.5	77.3	74.2	75.1

[1]	刘子一,崔超然,孟凡安,林培光. 基于批归一化统计量的无源多领域自适应方法[J]. 山东大学学报 (工学版), 2023, 53(2): 102-108.
[2]	梁蒙蒙,周涛,夏勇,张飞飞,杨健. 基于PSO-ConvK卷积神经网络的肺部肿瘤图像识别[J]. 山东大学学报 (工学版), 2018, 48(5): 77-84.
[3]	刘帆,陈泽华,柴晶. 一种基于深度神经网络模型的多聚焦图像融合方法[J]. 山东大学学报(工学版), 2016, 46(3): 7-13.
[4]	李翔1,朱全银1,王尊2. 基于可变基函数和GentleAdaBoost的小波神经网络研究[J]. 山东大学学报(工学版), 2013, 43(5): 31-38.
[5]	尹建川1,2, 邹早建1,3, 徐锋1. 一种基于Akaike信息准则的极限学习机[J]. 山东大学学报(工学版), 2011, 41(6): 7-11.
[6]	梅红,王勇,赵荣齐 . 基于蚁群神经网络算法的机器人逆解[J]. 山东大学学报(工学版), 2008, 38(5): 72-76 .
[7]	赵宁宁,唐雪嵩,赵鸣博. 基于卷积神经网络的深度线段分类算法[J]. 山东大学学报 (工学版), 2020, 50(4): 22-27.
[8]	刘帅,王磊,丁旭涛. 基于Bi-LSTM的脑电情绪识别[J]. 山东大学学报 (工学版), 2020, 50(4): 35-39.
[9]	张沁洋,李旭,姚春龙,李长吾. 结合句法依存信息的方面级情感分类[J]. 山东大学学报 (工学版), 2021, 51(2): 83-89.
[10]	丁飞,江铭炎. 基于改进狮群算法和BP神经网络模型的房价预测[J]. 山东大学学报 (工学版), 2021, 51(4): 8-16.
[11]	于畅,伍星,邓秋菊. 基于深度学习的多视角螺钉缺失智能检测算法[J]. 山东大学学报 (工学版), 2023, 53(4): 104-112.
[12]	韦修喜,陶道,黄华娟. 改进果蝇算法优化BP神经网络预测汽油辛烷值[J]. 山东大学学报 (工学版), 2023, 53(5): 20-28.
[13]	王碧瑶,韩毅,崔航滨,刘毅超,任铭然,高维勇,陈姝廷,刘嘉巍,崔洋. 基于图像的道路语义分割检测方法[J]. 山东大学学报 (工学版), 2023, 53(5): 37-47.
[14]	孙园,曾惠权,欧阳苏建,高佳倩,王绮楠,林智勇. 基于粒子群算法的模糊大脑情感学习非线性系统辨识[J]. 山东大学学报 (工学版), 2024, 54(1): 25-32.
[15]	顾玉磊,马晖,王愚勤,胡卉,刘富鑫. 基于BP-Adaboost与TOPSIS的航空装备供应商评价[J]. 山东大学学报 (工学版), 2024, 54(1): 63-73.