逆合成孔径成像雷达隐身目标零样本识别

doi:10.12305/j.issn.1001-506X.2023.10.15

系统工程与电子技术 ›› 2023, Vol. 45 ›› Issue (10): 3116-3121.doi: 10.12305/j.issn.1001-506X.2023.10.15

• 传感器与信号处理 • 上一篇

逆合成孔径成像雷达隐身目标零样本识别

周春花¹^,²^,³^,*, 魏维伟¹^,²^,³, 张学成⁴, 郑鑫⁵, 程冕之¹

1. 上海无线电设备研究所, 上海 201109
2. 上海目标识别与环境感知工程技术研究中心, 上海 201109
3. 中国航天科技集团交通感知雷达技术研发中心, 上海 201109
4. 陆军装备部驻上海地区第三军事代表室, 上海 200031
5. 上海航天技术研究院, 上海 201109

收稿日期:2021-10-26 出版日期:2023-09-25 发布日期:2023-10-11
通讯作者: 周春花
作者简介:周春花(1980—), 女, 研究员, 硕士, 主要研究方向为雷达成像、杂波抑制、动目标检测与跟踪
魏维伟(1977—), 男, 研究员, 硕士, 主要研究方向为雷达探测与识别
张学成(1976—), 男, 高级工程师, 博士, 主要研究方向为系统总体技术
郑鑫(1980—), 男, 高级工程师, 硕士, 主要研究方向为飞行器总体和雷达信号处理
程冕之(1980—), 男, 高级工程师, 主要研究方向为项目管理研究
基金资助:
上海市自然科学基金(19ZR1454000)

Zero-shot identification for stealth target by inverse synthetic aperture imaging radar

Chunhua ZHOU¹^,²^,³^,*, Weiwei WEI¹^,²^,³, Xuecheng ZHANG⁴, Xin ZHENG⁵, Mianzhi CHENG¹

1. Shanghai Radio Equipment Research Institute, Shanghai 201109, China
2. Shanghai Engineering Research Center of Target Identification and Environment Perception, Shanghai 201109, China
3. Traffic Perception Radar Technology Research & Development Center of China Aerospace Science and Technology Corporation, Shanghai 201109, China
4. The 3rd Military Representative Office of the Ministry of Army Equipment, Shanghai 200031, China
5. Shanghai Academy of Spaceflight Technology, Shanghai 201109, China

Received:2021-10-26 Online:2023-09-25 Published:2023-10-11
Contact: Chunhua ZHOU

摘要/Abstract

摘要：

针对现有算法不具备识别出未在训练过程中出现的新类别目标的能力问题，提出了针对逆合成孔径成像雷达(inverse synthetic aperture imaging radar，ISAR)隐身目标零样本学习识别方法。首先，基于飞行类动态目标三维网络化物理模型，使用FEKO电磁场仿真软件进行编程，实现ISAR可见的源目标图像数据生成；然后，在此基础上形成不同飞机类目标细节属性的文本语义特征表达。所提出的新类型算法网络模型采用两个变分自编码器，分别进行了图像和语义的特征生成，从而让网络学习到模态不变的特征表达。使用可见类别数据训练网络，并获得能够凭借语义信息生成图像特征的模型。训练识别采用该学习模型不可见的未知新类别目标, 从不可见未知的新类别文本语义生成不可见未知的新目标图像特征信息，支撑了不可见未知的新目标识别, 统计未知的新类别识别正确率为75%。

关键词: 逆合成孔径成像雷达, 零样本学习, 隐身目标

Abstract:

For the zero-shot learning and recognition problem of stealth targets for inverse synthetic aperture imaging radar (ISAR), the existed algorithms cannot recognize the new category of targets that have not appeared in the training process. A target learning and recognition method with zero-shot learning (ZSL) is proposed for solving the problem above. Firstly, based on three dimensional grid physical model of the aircraft-class dynamic target, the FEKO electromagnetic field simulation software programming is used to realize the ISAR-visible source target image data generation. Secondly, on this basis, the text semantic feature expression of detail attributes for different aircraft-class targets is formed. In the novel-type proposed algorithm's network model, two variation autoencoders are used to generate image and semantic features respectively, so that the network can learn the modal's invariant feature expression. The network is trained with visible category data to obtain the model that can generate image features based on semantic information. The training recognition process adopts the targets of the new category which are unknown and invisible for the proposed learning model. The unknown and invisible image feature information of the new target is generated from the invisible and unknown text semantic of the new category, which supports the recognition for the new targets which are unknown and invisible. The accuracy rate of the recognition for the new category targets is up to 75% according to the relevant statistic result, which means an important military and strategic significance.

Key words: inverse synthetic aperture imaging radar (ISAR), zero-shot learning (ZSL), stealth target

中图分类号:

TN957.52

周春花, 魏维伟, 张学成, 郑鑫, 程冕之. 逆合成孔径成像雷达隐身目标零样本识别[J]. 系统工程与电子技术, 2023, 45(10): 3116-3121.

Chunhua ZHOU, Weiwei WEI, Xuecheng ZHANG, Xin ZHENG, Mianzhi CHENG. Zero-shot identification for stealth target by inverse synthetic aperture imaging radar[J]. Systems Engineering and Electronics, 2023, 45(10): 3116-3121.

图/表 8

图1

图2

表1

表2

表3

图3

表4

图4

参考文献 19

1	ALAMRI F, DUTTA A. Multi-head self-attention via vision transformer for zero-shot learning[EB/OL]. [2021-07-30]. https://arxiv.org/abs/2108.00045.
2	JANIK M, GARD N, HILSMANN A, et al. Zero in on shape: a generic 2D-3D instance similarity metric learned from synthetic data[C]//Proc. of the IEEE International Conference on Image Processing, 2021: 2638-2642.
3	MICHELE B, BOULCH A, PUY G, et al. Generative zero-shot learning for semantic segmentation of 3D point cloud[EB/OL]. [2021-08-13]. https://arxiv.org/abs/2108.06230.
4	HE T, GAO L L, SONG J K, et al. 2021. Semantic compositional learning for low-shot scene graph generation[EB/OL]. [2021-08-19]. https://arxiv.org/abs/2108.08600.
5	BIANCHI F, ATTANASIO G, PISONI R, et al. Contrastive language-image pre-training for the Italian language[EB/OL]. [2021-08-19]. https://arxiv.org/abs/2108.08688.
6	NARAYAN S, GUPTA A, KHAN S, et al. Discriminative region-based multi-label zero-shot learning[C]//Proc. of the IEEE/CVF International Conference on Computer Vision, 2021: 8731-8740.
7	GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets. Advances in neural information processing systems[EB/OL]. [2014-06-10]. https://arxiv.org/abs/1406.2661.
8	KINGMA D P, WELLING M. Auto-encoding variational Bayes [EB/OL]. [2013-12-20]. https://arxiv.org/abs/1312.6114.
9	FELIX R, REID I, CARNEIRO G. Multi-modal cycle-consis-tent generalized zero-shot learning[C]//Proc. of the European Conference on Computer Vision, 2018: 21-37.
10	ISOLA P, ZHU J Y, ZHOU T, et al. Image-to-image translation with conditional adversarial networks[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1125-1134.
11	KODIROV E, XIANG T, GONG S G. Semantic autoencoder for zero-shot learning[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
12	LAMPERT C H, NICKISCH H, HARMELING S. Learning to detect unseen object classes by between-class attribute transfer[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2009: 951-958.
13	XIAN Y Q , LAMPERT C H , SCHIELE B , et al. Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2018, 41 (9): 2251- 2265.
14	AKATA Z , PERRONNIN F , HARCHAOUI Z , et al. Labe-lembedding for image classification[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2015, 38 (7): 1425- 1438.
15	PATTERSON G, HAYS J. Sun attribute database: discovering, annotating, and recognizing scene attributes[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2012: 2751-2758.
16	ZHANG L, XIANG T, GONG S G. Learning a deep embedding model for zero-shot learning[C]//Proce. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2021-2030.
17	ZHU Y Z, ELHOSEINY M, LIU B C, et al. A generative adversarial approach for zero-shot learning from noisy texts[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1004-1013.
18	VERMA V K, ARORA G, MISHRA A, et al. Generalized zero-shot learning via synthesized examples[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4281-4289.
19	ATZMON Y, CHECHIK G. Adaptive confidence smoothing for generalized zero-shot learning[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 11671-11680.

方法	AwA1	AwA2	CUB	SUN
ALE^[14]	27.5	23.9	34.4	26.3
DEM^[16]	47.3	45.1	29.2	35.6
GAZSL^[17]	31.4	50.3	34.3	26.7
SE^[18]	61.5	62.8	46.7	34.9
COSMO^[19]	63.6	-	50.2	41.0
本文算法	67.6	68.2	55.0	41.4

属性	内容(单位)	描述
机身长度	数值/m	飞机的纵向长度
翼展	数值/m	飞机机翼总展开长度
是否有翼尖小翼	布尔值	机翼局部特征描述
尾翼	布尔值	尾翼局部特征描述
机翼面积	数值/m²	机翼展开总面积
高度	数字/m	最高点至最低点的距离差
展弦比	比率/%	翼展和翼弦长度比值
发动机数	数值/个	总引擎数目
机翼形状	选项值(后掠翼、三角翼、梯形翼、菱形翼)	飞机机翼俯视图形状
推进动力	选项值(螺旋桨, 喷气机)	飞机引擎动力来源
机翼数量	数值/个	飞机机翼总数目
起落架数	数值/个	飞机起落架总数目
主起落架轮子数	数值/个	主起落架轮子总数目
垂直稳定器数量	数值/个	垂直稳定器总数目
飞机类型	选项值(民航客机、民航货机、战斗机、轰炸机、军用运输机)	飞机设计用途分类
机翼挂架数目	数值/个	机翼部分炸弹挂载点
机腹挂架数目	数值/个	机腹部分炸弹挂载点

方法		F22	TU-160
传统方法	ALE^[14]	32.4	27.9
传统方法	DEM^[16]	41.3	35.7
生成方法	VAE	59.3	41.1
	GAN	72.4	49.9
	本文方法	86.0	63.1

[1]	潘崇煜, 黄健, 郝建国, 龚建兴, 张中杰. 融合零样本学习和小样本学习的弱监督学习方法综述[J]. 系统工程与电子技术, 2020, 42(10): 2246-2256.
[2]	王卓, 郑学合, 常晓兰. 基于瞬时测频原理的高机动隐身目标检测算法[J]. 系统工程与电子技术, 2019, 41(5): 1000-1006.
[3]	王卓, 郑学合, 常晓兰. 基于旋转降维的高速隐身目标检测算法[J]. 系统工程与电子技术, 2019, 41(1): 14-20.
[4]	王卓, 郑学合, 常晓兰. 基于加速度盲估计的隐身目标检测算法[J]. 系统工程与电子技术, 2017, 39(8): 1691-1696.

逆合成孔径成像雷达隐身目标零样本识别

Zero-shot identification for stealth target by inverse synthetic aperture imaging radar

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 19

相关文章 4

编辑推荐

Metrics

本文评价

类别	数目
1	100
2	100
3	100
4	100
5	100
6	100
7	100
8	100
9	100
10	100
11	100
12	100
13	100
14	100
15	100
16	100
17	100
18	100