基于深度CNN模型的SAR图像有源干扰类型识别方法

陈思伟 崔兴超 李铭典 陶臣嵩 李郝亮

陈思伟, 崔兴超, 李铭典, 等. 基于深度CNN模型的SAR图像有源干扰类型识别方法[J]. 雷达学报, 2022, 11(5): 897–908. doi: 10.12000/JR22143
引用本文: 陈思伟, 崔兴超, 李铭典, 等. 基于深度CNN模型的SAR图像有源干扰类型识别方法[J]. 雷达学报, 2022, 11(5): 897–908. doi: 10.12000/JR22143
CHEN Siwei, CUI Xingchao, LI Mingdian, et al. SAR image active jamming type recognition based on deep CNN model[J]. Journal of Radars, 2022, 11(5): 897–908. doi: 10.12000/JR22143
Citation: CHEN Siwei, CUI Xingchao, LI Mingdian, et al. SAR image active jamming type recognition based on deep CNN model[J]. Journal of Radars, 2022, 11(5): 897–908. doi: 10.12000/JR22143

基于深度CNN模型的SAR图像有源干扰类型识别方法

doi: 10.12000/JR22143
基金项目: 国家自然科学基金(62122091, 61771480),湖南省自然科学基金(2020JJ2034)
详细信息
    作者简介:

    陈思伟,博士,教授,主要研究方向为极化雷达成像与目标识别、机器学习、电子对抗等

    崔兴超,博士生,主要研究方向为极化雷达成像与目标识别

    李铭典,博士生,主要研究方向为极化雷达成像与目标识别

    陶臣嵩,博士生,主要研究方向为电子对抗、机器学习

    李郝亮,博士生,主要研究方向为极化雷达成像与目标识别

    通讯作者:

    陈思伟 chenswnudt@163.com

  • 责任主编:毕大平 Corresponding Editor: BI Daping
  • 中图分类号: TN958

SAR Image Active Jamming Type Recognition Based on Deep CNN Model

Funds: The National Natural Science Foundation of China (62122091, 61771480), The Natural Science Foundation of Hunan Province (2020JJ2034)
More Information
  • 摘要: 合成孔径雷达(SAR)能够全天时全天候获取感兴趣区域的高分辨率雷达图像,在诸多领域获得了成功应用。在电子对抗博弈环境下,SAR图像解译与情报生成也面临复杂电磁干扰的严重影响。当前,国内外学者提出了许多SAR抗干扰技术方法。然而,作为抗干扰的前提,SAR图像干扰类型识别这一关键技术却鲜有报道。该文针对SAR图像典型有源干扰类型识别开展研究。首先,选取5种典型有源干扰样式,并根据干扰参数,细分为9种干扰类型,作为干扰识别对象。其次,开展干扰信号回波仿真,通过与MiniSAR实测数据进行回波域叠加和成像处理,构建了典型有源干扰类型样本集。在此基础上,提出了一种结合注意力机制的深度卷积神经网络(CNN)模型,并开展了对比实验验证。实验表明,对不同场景和不同干扰参数情形,相比于传统深度CNN模型,该文方法取得了更高的识别精度和更稳健的性能。

     

  • 图  1  干扰数据构建流程图

    Figure  1.  Flowchart of jamming data construction

    图  2  MiniSAR数据切片

    Figure  2.  Image chips of MiniSAR data

    图  3  包含9种干扰类型和9种干扰机位置的车辆目标SAR图像切片((a) 噪声压制干扰,(b) 固定移频干扰,(c) 随机移频干扰,(d) 步进移频干扰,(e) 分段移频干扰,(f) 距离向间歇采样转发干扰,(g) 方位向间歇采样转发干扰,(h) 微动调制干扰,(i) 延迟多抽头干扰)

    Figure  3.  SAR image chips with vehicle targets containing 9 jamming types and 9 jammer positions((a) Noise suppression jamming, (b) Fixed shift-frequency jamming, (c) Random shift-frequency jamming, (d) Stepped shift-frequency jamming, (e) Blocked shift-frequency jamming, (f) Intermittent sampling repeater jamming in range, (g) Intermittent sampling repeater jamming in azimuth, (h) Micro-motion modulation jamming, (i) Delayed multi-taps jamming)

    图  4  结合注意力机制的有源干扰类型识别网络模型

    Figure  4.  Active jamming type recognition network model based on attention mechanism

    图  5  实验1模型训练过程损失值曲线和平均总体识别精度

    Figure  5.  Loss value in model training process and mean overall accuracy of experiment 1

    图  6  实验2平均总体识别精度

    Figure  6.  Mean overall accuracy of experiment 2

    表  1  干扰参数设置

    Table  1.   Jamming parameter configuration

    干扰类型参数设置
    噪声压制干扰JSR=5.0, 7.5, 10.0, 12.5, 15.0, 17.5, 20.0, 22.5 dB
    固定移频干扰$R = 20$
    随机移频干扰$R = 20$, $a = - 1$, $b = 1$
    步进移频干扰$R = 20$, $ {f_{{{\text{d}}_{\text{0}}}}} = 0 $
    分段移频干扰$R = 20$, $N = 3$, $ {f_1} = {f_{\text{d}}} $, $ {f_2} = 0 $,
    $ {f_3} = - {f_{\text{d}}} $
    距离向间歇采样转发干扰$R = 20$, ${D_{\rm r}} = 0.1$
    方位向间歇采样转发干扰$R = 20$, ${D_{\rm r}} = 0.1$
    微动调制干扰$R = 20$, $L = 100$
    延迟多抽头干扰$R = 20$, $N = 2$
    下载: 导出CSV

    表  2  实验1有源干扰类型识别结果(%)

    Table  2.   Active jamming type recognition results of experiment 1 (%)

    测试集方法噪声干扰固定移频随机移频分段移频步进移频距离向
    间歇采样
    方位向
    间歇采样
    延迟多抽头微动干扰OA
    JSR_7.5VGG-16100±098.41±2.46100±097.46±2.1599.68±0.63100±0100±094.29±4.3399.37±0.7898.80±0.70
    ResNet-18100±070.48±9.66100±090.79±2.5486.35±5.3792.06±5.22100±069.21±2.9491.11±3.1188.89±1.59
    Inception v490.79±9.6485.08±3.84100±093.65±6.4397.46±1.2775.56±7.8899.68±0.6387.62±4.6494.60±2.9491.60±0.56
    VGG-16+AN100±099.68±0.63100±099.05±0.78100±0100±0100±099.37±0.78100±099.79±0.13
    JSR_12.5VGG-16100±099.15±0.98100±098.31±1.9399.89±0.21100±0100±095.56±3.6199.47±0.6799.15±0.63
    ResNet-18100±075.87±8.75100±093.86±2.4590.69±3.8296.40±2.38100±073.12±4.0693.97±3.2091.55±1.32
    Inception v496.03±4.8988.89±2.39100±095.24±5.4898.10±0.8684.97±4.5099.89±0.2190.90±3.1396.51±2.4394.50±0.57
    VGG-16+AN100±099.89±0.21100±099.58±0.4099.79±0.42100±0100±099.58±0.62100±099.87±0.11
    JSR_17.5VGG-16100±099.37±0.74100±098.65±1.6099.92±0.16100±0100±096.03±3.3399.60±0.5099.29±0.55
    ResNet-18100±078.81±7.79100±095.00±2.2192.06±3.5797.30±1.78100±074.68±3.7594.92±2.9892.53±1.20
    Inception v497.02±3.6790.48±2.20100±095.79±5.1698.49±0.7787.62±4.0399.92±0.1691.75±3.1497.14±2.1195.36±0.63
    VGG-16+AN100±099.92±0.16100±099.68±0.3099.84±0.32100±0100±099.44±0.59100±099.88±0.10
    JSR_22.5VGG-16100±099.49±0.59100±098.92±1.2899.94±0.1399.24±0.25100±096.44±3.0899.68±0.4099.30±0.51
    ResNet-18100±081.33±6.96100±095.94±1.8493.52±3.0796.51±2.1099.94±0.1376.13±3.8695.81±2.5193.24±1.01
    Inception v497.62±2.9391.94±2.07100±096.32±4.4298.73±0.7289.52±3.8399.94±0.1391.87±3.2497.65±1.6995.95±0.64
    VGG-16+AN100±099.94±0.13100±099.75±0.2499.87±0.2599.49±0.52100±099.37±0.57100±099.82±0.12
    下载: 导出CSV

    表  3  实验2有源干扰类型识别结果(%)

    Table  3.   Active jamming type recognition results of experiment 2 (%)

    测试集方法噪声
    干扰
    固定
    移频
    随机
    移频
    分段
    移频
    步进
    移频
    距离向
    间歇采样
    方位向
    间歇采样
    延迟
    多抽头
    微动
    干扰
    OA
    Para_20VGG-16100±099.37±0.74100±098.49±1.3899.60±0.2599.84±0.19100±096.67±2.9599.68±0.3099.29±0.48
    ResNet-1899.86±0.2877.94±7.19100±093.89±2.4791.11±3.3094.37±2.51100±072.86±3.3193.65±2.5091.52±1.27
    Inception v494.03±3.1189.92±2.87100±094.76±5.0598.10±1.1684.44±5.1299.44±0.5991.67±3.6596.98±1.4194.37±0.77
    VGG-16+AN100±099.92±0.16100±099.52±0.3099.92±0.16100±0100±099.37±0.78100±099.86±0.09
    Para_22VGG-16100±098.89±0.95100±093.10±5.6499.84±0.1999.76±0.32100±087.30±5.4282.38±7.4495.70±1.41
    ResNet-1899.94±0.1272.86±6.9399.76±0.4886.67±5.8589.37±3.8292.14±3.9799.76±0.3262.46±8.9765.00±5.4785.33±2.26
    Inception v494.15±3.1891.75±4.37100±073.50±16.3595.71±1.2183.49±5.1199.29±0.5391.90±4.6872.22±8.2689.12±1.43
    VGG-16+AN100±099.44±0.69100±096.59±4.3499.60±0.3599.84±0.19100±095.16±6.3193.81±2.8598.27±1.14
    Para_24VGG-16100±099.37±0.48100±094.29±4.17100±099.84±0.32100±091.19±4.068.73±4.4688.16±0.53
    ResNet-1899.98±0.0472.54±7.9699.84±0.3288.57±5.8489.37±4.8594.05±3.47100±060.95±5.3015.16±2.6180.05±2.31
    Inception v494.21±3.3892.46±2.81100±076.11±9.4396.35±2.6783.41±5.0698.49±0.8591.11±8.158.89±6.8082.34±0.64
    VGG-16+AN100±099.68±0.30100.0±099.29±1.24100±099.60±0.50100±092.70±8.586.51±4.9388.64±1.36
    Para_26VGG-16100±099.37±0.89100±095.71±4.7499.44±0.7899.68±0.39100±069.60±16.784.76±6.0685.40±2.01
    ResNet-1899.88±0.2466.59±8.4499.84±0.3288.02±4.0185.56±8.1689.44±4.07100±044.21±6.5312.62±3.2876.24±2.34
    Inception v494.17±3.6091.67±3.98100±064.60±17.0693.49±3.2884.44±4.4999.84±0.3273.80±13.377.78±4.6778.88±0.95
    VGG-16+AN100±099.84±0.32100±092.5±12.7799.05±1.1798.33±2.39100±073.40±23.681.19±1.2084.94±3.68
    Para_28VGG-16100±099.92±0.16100±085.5±16.1498.73±1.3898.73±1.16100±033.20±19.3817.50±13.8381.53±3.88
    ResNet-1899.88±0.2471.1±10.0099.76±0.3281.03±5.1584.05±7.8184.44±6.63100±038.41±3.3030.08±4.9176.54±1.47
    Inception v494.07±3.6792.46±3.21100±049.1±22.0593.73±4.3981.59±5.3599.60±0.4352.90±17.5526.90±11.5076.72±2.78
    VGG-16+AN100±0100±099.84±0.3282.7±19.3297.22±3.1397.14±2.71100±042.50±26.5629.60±11.5483.25±5.08
    Para_30VGG-16100±099.21±0.75100±073.3±26.0396.75±4.3694.76±6.0499.92±0.1620.30±16.4831.20±17.8879.51±5.44
    ResNet-1899.82±0.3659.50±12.5699.84±0.3275.32±7.8373.70±13.2376.35±6.4399.68±0.6337.54±5.8636.35±5.6073.13±2.42
    Inception v493.91±3.3589.84±3.76100±045.60±20.6088.41±8.6278.57±6.0499.13±0.3039.50±16.9637.90±10.9074.77±2.82
    VGG-16+AN100±099.84±0.1999.84±0.3279.7±19.9194.92±4.7793.25±6.0399.92±0.1634.30±26.1646.67±7.6583.17±4.71
    下载: 导出CSV
  • [1] CUMMING I G and WONG F H. Digital Processing of Synthetic Aperture Radar Data[M]. Boston: Artech House, 2005.
    [2] Bu-Chin Wang. Digital Signal Processing Techniques and Applications in Radar Image Processing[M]. Hoboken: John Wiley & Sons, 2008.
    [3] 王雪松, 陈思伟. 合成孔径雷达极化成像解译识别技术的进展与展望[J]. 雷达学报, 2020, 9(2): 259–276. doi: 10.12000/JR19109

    WANG Xuesong and CHEN Siwei. Polarimetric synthetic aperture radar interpretation and recognition: Advances and perspectives[J]. Journal of Radars, 2020, 9(2): 259–276. doi: 10.12000/JR19109
    [4] CHEN Siwei, WANG Xuesong, XIAO Shunping, et al. Target Scattering Mechanism in Polarimetric Synthetic Aperture Radar: Interpretation and Application[M]. Singapore: Springer, 2018.
    [5] 陈静. 雷达无源干扰原理[M]. 北京: 国防工业出版社, 2009: 88–95.

    CHEN Jing. Principles of Radar Passive Jamming[M]. Beijing: National Defense Industry Press, 2009: 88–95.
    [6] 李永波, 黄成亮, 赵桥, 等. 伪装网的发展现状及趋势[J]. 材料导报, 2021, 35(S1): 576–577, 599.

    LI Yongbo, HUANG Chengliang, ZHAO Qiao, et al. The development status and trend of the camouflage mat[J]. Materials Reports, 2021, 35(S1): 576–577, 599.
    [7] 肖冰, 李军念, 陈秦, 等. 国外军用伪装网技术的现状及发展趋势[J]. 四川兵工学报, 2003, 24(5): 64–66. doi: 10.3969/j.issn.1006-0707.2003.05.022

    XIAO Bing, LI Junnian, CHEN Qin, et al. The status and developmental trend of the military camouflage net[J]. Journal of Ordnance Equipment Engineering, 2003, 24(5): 64–66. doi: 10.3969/j.issn.1006-0707.2003.05.022
    [8] 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. doi: 10.12305/j.issn.1001-506X.2022.07.01

    LI Haoliang, CHEN Siwei, and WANG Xuesong. Study on characterization of sea corner reflectors in polarimetric rotation domain[J]. Systems Engineering and Electronics, 2022, 44(7): 2065–2073. doi: 10.12305/j.issn.1001-506X.2022.07.01
    [9] 胡海, 张林, 张小东. 舰载充气式角反射体反导装备发展及运用[J]. 国防科技, 2018, 39(2): 74–77. doi: 10.13943/j.issn671-4547.2018.02.12

    HU Hai, ZHANG Lin, and ZHANG Xiaodong. A study on equipment developments and operational using of ship born gas-filled anti-missile multi-corner reflector[J]. Defense Technology Review, 2018, 39(2): 74–77. doi: 10.13943/j.issn671-4547.2018.02.12
    [10] 张志远, 张介秋, 屈绍波, 等. 雷达角反射器的研究进展及展望[J]. 飞航导弹, 2014(4): 64–70. doi: 10.16338/j.issn.1009-1319.2014.04.021

    ZHANG Zhiyuan, ZHANG Jieqiu, QU Shaobo, et al. Research progress and prospect of radar corner reflector[J]. Aerodynamic Missile Journal, 2014(4): 64–70. doi: 10.16338/j.issn.1009-1319.2014.04.021
    [11] 秋云. 充气武器, 以假乱真迷惑敌人[J]. 科学启蒙, 2011(11): 27.

    QIU Yun. Inflatable weapons confuse the enemy with the real[J]. Science Initiation, 2011(11): 27.
    [12] 崔铁军. 电磁超材料——从等效媒质到现场可编程系统[J]. 中国科学:信息科学, 2020, 50(10): 1427–1461. doi: 10.1360/SSI-2020-0123

    CUI Tiejun. Electromagnetic metamaterials—from effective media to field programmable systems[J]. Scientia Sinica Informationis, 2020, 50(10): 1427–1461. doi: 10.1360/SSI-2020-0123
    [13] LENG Xiangguang, JI Kefeng, and KUANG Gangyao. Radio frequency interference detection and localization in sentinel-1 images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(11): 9270–9281. doi: 10.1109/TGRS.2021.3049472
    [14] 汪日超. 星载SAR压制式干扰与抗干扰技术研究[D]. [硕士论文], 电子科技大学, 2017.

    WANG Richao. Research on spaceborne SAR compression interference and anti-jamming technology[D]. [Master dissertation], University of Electronic Science and Technology of China, 2017.
    [15] 宋杰, 张华春, 郑慧芳. 基于微动调制的梳状谱灵巧噪声压制干扰[J]. 雷达科学与技术, 2020, 18(5): 531–538, 545. doi: 10.3969/j.issn.1672-2337.2020.05.011

    SONG Jie, ZHANG Huachun, and ZHENG Huifang. Suppression jamming of comb spectrum smart noise based on micro-motion modulation[J]. Radar Science and Technology, 2020, 18(5): 531–538, 545. doi: 10.3969/j.issn.1672-2337.2020.05.011
    [16] 邓云凯, 郑远, 胡英辉. 合成孔径雷达转发式干扰分析[J]. 电子与信息学报, 2010, 32(1): 69–74. doi: 10.3724/SP.J.1146.2008.01636

    DENG Yunkai, ZHENG Yuan, and HU Yinghui. Analysis of synthetic aperture radar repeater jamming[J]. Journal of Electronics &Information Technology, 2010, 32(1): 69–74. doi: 10.3724/SP.J.1146.2008.01636
    [17] 赵博, 杨军, 孙光才, 等. 一种虚假大场景SAR快速转发式欺骗干扰方法研究[J]. 电子与信息学报, 2012, 34(4): 963–968. doi: 10.3724/SP.J.1146.2011.0050

    ZHAO Bo, YANG Jun, SUN Guangcai, et al. A method of SAR fast repeater deception jamming for large false scene[J]. Journal of Electronics &Information Technology, 2012, 34(4): 963–968. doi: 10.3724/SP.J.1146.2011.0050
    [18] 陈思伟, 代大海, 李永祯, 等. SAR二维余弦调相转发散射波干扰原理[J]. 电子学报, 2009, 37(12): 2620–2625. doi: 10.3321/j.issn:0372-2112.2009.12.003

    CHEN Siwei, DAI Dahai, LI Yongzhen, et al. The theory of 2-D cosinusoidal phase-modulated repeater scatter-wave jamming to SAR[J]. Acta Electronica Sinica, 2009, 37(12): 2620–2625. doi: 10.3321/j.issn:0372-2112.2009.12.003
    [19] 房明星, 毕大平, 沈爱国. 多通道SAR-GMTI二维余弦调相散射波干扰[J]. 上海交通大学学报, 2018, 52(3): 356–364. doi: 10.16183/j.cnki.jsjtu.2018.03.015

    FANG Mingxing, BI Daping, and SHEN Aiguo. 2-D cosinusoidal phase-modulated scatter-wave jamming to multi-channel SAR-GMTI[J]. Journal of Shanghai Jiaotong University, 2018, 52(3): 356–364. doi: 10.16183/j.cnki.jsjtu.2018.03.015
    [20] 王雪松, 肖顺平, 李永祯, 等. 合成孔径雷达微动干扰[M]. 北京: 科学出版社, 2016.

    WANG Xuesong, XIAO Shunping, LI Yongzhen, et al. Micro-Motion Jamming of Sunthetic Aperture Radar[M]. Beijing: Science Press, 2016.
    [21] 黄岩, 赵博, 陶明亮, 等. 合成孔径雷达抗干扰技术综述[J]. 雷达学报, 2020, 9(1): 86–106. doi: 10.12000/JR19113

    HUANG Yan, ZHAO Bo, TAO Mingliang, et al. Review of synthetic aperture radar interference suppression[J]. Journal of Radars, 2020, 9(1): 86–106. doi: 10.12000/JR19113
    [22] 赵宗锋. 基于信号波形设计的SAR抗干扰技术研究[D]. [硕士论文], 国防科学技术大学, 2007.

    ZHAO Zongfeng. SAR anti-jamming based on waveform design[D]. [Master dissertation], National University of Defense Technology, 2007.
    [23] AXELSSON S R J. Noise radar using random phase and frequency modulation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(11): 2370–2384. doi: 10.1109/TGRS.2004.834589
    [24] ZHAO Bo, HUANG Lei, LI Jian, et al. Target reconstruction from deceptively jammed single-channel SAR[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(1): 152–167. doi: 10.1109/TGRS.2017.2744178
    [25] YANG Huizhang, HE Yaomin, DU Yanlei, et al. Two-dimensional spectral analysis filter for removal of LFM Radar interference in spaceborne SAR imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5219016. doi: 10.1109/TGRS.2021.3132495
    [26] YANG Huizhang, LI Kun, LI Jie, et al. BSF: Block subspace filter for removing narrowband and wideband radio interference artifacts in single-look complex SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5211916. doi: 10.1109/TGRS.2021.3096538
    [27] 周超, 刘泉华, 胡程. 间歇采样转发式干扰的时频域辨识与抑制[J]. 雷达学报, 2019, 8(1): 100–106. doi: 10.12000/JR18080

    ZHOU Chao, LIU Quanhua, and HU Cheng. Time-frequency analysis techniques for recognition and suppression of interrupted sampling repeater jamming[J]. Journal of Radars, 2019, 8(1): 100–106. doi: 10.12000/JR18080
    [28] TAO Mingliang, ZHOU Feng, and ZHANG Zijing. Wideband interference mitigation in high-resolution airborne synthetic aperture Radar data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(1): 74–87. doi: 10.1109/TGRS.2015.2450754
    [29] 陶臣嵩, 陈思伟, 肖顺平. 基于深度学习模型的SAR图像间歇采样转发干扰检测[J/OL]. 系统工程与电子技术. 待出版.

    TAO Chensong, CHEN Siwei, and XIAO Shunping. SAR image interrupted sampling repeater jamming detection based on deep learning models[J/OL]. Systems Engineering and Electronics, in press.
    [30] 黄洪旭, 黄知涛, 周一宇. 对合成孔径雷达的移频干扰研究[J]. 宇航学报, 2006, 27(3): 463–468. doi: 10.3321/j.issn:1000-1328.2006.03.027

    HUANG Hongxu, HUANG Zhitao, and ZHOU Yiyu. A study on the shift-frequency jamming to SAR[J]. Journal of Astronautics, 2006, 27(3): 463–468. doi: 10.3321/j.issn:1000-1328.2006.03.027
    [31] 黄洪旭, 黄知涛, 周一宇. 对合成孔径雷达的随机移频干扰[J]. 信号处理, 2007, 23(1): 41–45. doi: 10.3969/j.issn.1003-0530.2007.01.009

    HUANG Hongxu, HUANG Zhitao, and ZHOU Yiyu. Randomly-shift-frequency jamming style to SAR[J]. Signal Processing, 2007, 23(1): 41–45. doi: 10.3969/j.issn.1003-0530.2007.01.009
    [32] 黄洪旭, 黄知涛, 吴京, 等. 对合成孔径雷达的步进移频干扰[J]. 宇航学报, 2011, 32(4): 898–902. doi: 10.3873/j.issn.1000-1328.2011.04.028

    HUANG Hongxu, HUANG Zhitao, WU Jing, et al. Stepped-shift-frequency jamming to SAR[J]. Journal of Astronautics, 2011, 32(4): 898–902. doi: 10.3873/j.issn.1000-1328.2011.04.028
    [33] 吴晓芳, 邢世其, 王雪松, 等. 对合成孔径雷达的脉间分段移频干扰[J]. 航天电子对抗, 2010, 26(1): 53–57. doi: 10.3969/j.issn.1673-2421.2010.01.016

    WU Xiaofang, XING Shiqi, WANG Xuesong, et al. Interpulse subsection-shift-frequency jamming to SAR[J]. Aerospace Electronic Warfare, 2010, 26(1): 53–57. doi: 10.3969/j.issn.1673-2421.2010.01.016
    [34] 王雪松, 刘建成, 张文明, 等. 间歇采样转发干扰的数学原理[J]. 中国科学E辑:信息科学, 2006, 36(8): 891–901. doi: 10.3969/j.issn.1674-7259.2006.08.007

    WANG Xuesong, LIU Jiancheng, ZHANG Wenming, et al. The mathematic principle of intermittent sampling repeater jamming[J]. Scientia Sinica Informationis, 2006, 36(8): 891–901. doi: 10.3969/j.issn.1674-7259.2006.08.007
    [35] 吴晓芳, 柏仲干, 代大海, 等. 对SAR的方位向间歇采样转发干扰[J]. 信号处理, 2010, 26(1): 1–6. doi: 10.3969/j.issn.1003-0530.2010.01.001

    WU Xiaofang, BAI Zhonggan, DAI Dahai, et al. Azimuth intermittent sampling repeater jamming to SAR[J]. Signal Processing, 2010, 26(1): 1–6. doi: 10.3969/j.issn.1003-0530.2010.01.001
    [36] 陈思伟, 王雪松, 刘阳, 等. 合成孔径雷达二维余弦调相转发干扰研究[J]. 电子与信息学报, 2009, 31(8): 1862–1866. doi: 10.3724/SP.J.1146.2008.01218

    CHEN Siwei, WANG Xuesong, LIU Yang, et al. The 2-D cosinusoidal phase modulation repeater jamming of SAR[J]. Journal of Electronics &Information Technology, 2009, 31(8): 1862–1866. doi: 10.3724/SP.J.1146.2008.01218
    [37] SIMONYAN K and ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv: 1409.1556, 2014.
    [38] CHEN Siwei and TAO Chensong. PolSAR image classification using polarimetric-feature-driven deep convolutional neural network[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(4): 627–631. doi: 10.1109/LGRS.2018.2799877
    [39] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278–2324. doi: 10.1109/5.726791
    [40] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 770–778.
    [41] SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning[C]. The 31st AAAI Conference on Artificial Intelligence, San Francisco, USA, 2017: 4278–4284.
    [42] RUEGG M, MEIER E, and NUESCH D. Vibration and rotation in millimeter-wave SAR[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(2): 293–304. doi: 10.1109/TGRS.2006.887025
    [43] CHEN, V C, LI Fayin, HO S S, et al. Micro-doppler effect in radar: Phenomenon, model, and simulation study[J]. IEEE Transactions on Aerospace and Electronic Systems, 2006, 42(1): 2–21. doi: 10.1109/TAES.2006.1603402
    [44] CAO Yue, XU Jiarui, LIN Stephen, et al. GCNet: Non-local networks meet squeeze-excitation networks and beyond[C]. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea (South), 2019: 1971–1980.
  • 加载中
图(6) / 表(3)
计量
  • 文章访问数:  1758
  • HTML全文浏览量:  948
  • PDF下载量:  299
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-07-09
  • 修回日期:  2022-09-19
  • 网络出版日期:  2022-09-30
  • 刊出日期:  2022-10-28

目录

    /

    返回文章
    返回