现代防御技术 ›› 2025, Vol. 53 ›› Issue (2): 129-140.DOI: 10.3969/j.issn.1009-086x.2025.02.014
收稿日期:
2024-03-16
修回日期:
2024-07-05
出版日期:
2025-04-28
发布日期:
2025-04-30
作者简介:
李家宽(1999-),男,河北邯郸人。硕士生,研究方向为雷达目标识别。
Jiakuan LI, Bo FENG, Lunhao SHEN, Chunmao YE, Jizhou YU
Received:
2024-03-16
Revised:
2024-07-05
Online:
2025-04-28
Published:
2025-04-30
摘要:
高分辨逆合成孔径雷达(ISAR)图像在目标识别中发挥着重要作用,但是获取目标高分辨的ISAR图像需要长时间的雷达照射,无法满足雷达资源调度需求。对此提出了一种入射视线角引导雷达图像特征融合的识别方法,选取驻留时间内的两端时间资源用于成像,满足雷达其余功能在时间上的调整与分配。考虑到不同机型图像调制现象的差异以及同一机型在不同入射视线角下的调制差异,设计混合注意力残差模块和角度引导注意力模块使网络有针对性地关注图像的关键区域并将目标特征与目标姿态进行关联。通过特征融合模块进行图像特征的整合以实现融合识别,最终通过3类飞机实测数据证明,该方法能在满足雷达资源调度需求的前提下获得较高的识别精度。
中图分类号:
李家宽, 冯博, 申伦豪, 叶春茂, 余继周. 入射视线角引导雷达图像特征融合的气动目标识别方法[J]. 现代防御技术, 2025, 53(2): 129-140.
Jiakuan LI, Bo FENG, Lunhao SHEN, Chunmao YE, Jizhou YU. Aerodynamic Target Recognition Method Based on Incidence Angle-Guided Radar Image Feature Fusion[J]. Modern Defense Technology, 2025, 53(2): 129-140.
目标类别 | 训练集 | 测试集 |
---|---|---|
“安26” | 12.1°~165.7° | 22.3°~89.1°,132.2°~167.2° |
“奖状” | 14.6°~165.3° | 31.1°~138.2° |
“雅克42” | 114.3°~174.3° | 161.3°~177.8° |
表1 数据集覆盖角度范围
Table 1 Dataset composition
目标类别 | 训练集 | 测试集 |
---|---|---|
“安26” | 12.1°~165.7° | 22.3°~89.1°,132.2°~167.2° |
“奖状” | 14.6°~165.3° | 31.1°~138.2° |
“雅克42” | 114.3°~174.3° | 161.3°~177.8° |
目标 类别 | 数据集1 | 数据集3 | 数据集5 | |||
---|---|---|---|---|---|---|
训练集 | 测试集 | 训练集 | 测试集 | 训练集 | 测试集 | |
“安26” | 4 830 | 4 528 | 4 782 | 4 484 | 4 686 | 4 394 |
“奖状” | 4 830 | 4 830 | 4 782 | 4 782 | 4 686 | 4 686 |
“雅克42” | 4 830 | 2 722 | 4 782 | 2 704 | 4 686 | 2 656 |
表2 数据集组成
Table 2 Composition of the dataset
目标 类别 | 数据集1 | 数据集3 | 数据集5 | |||
---|---|---|---|---|---|---|
训练集 | 测试集 | 训练集 | 测试集 | 训练集 | 测试集 | |
“安26” | 4 830 | 4 528 | 4 782 | 4 484 | 4 686 | 4 394 |
“奖状” | 4 830 | 4 830 | 4 782 | 4 782 | 4 686 | 4 686 |
“雅克42” | 4 830 | 2 722 | 4 782 | 2 704 | 4 686 | 2 656 |
融合时间 | 识别准确率 | 平均 识别率 | ||
---|---|---|---|---|
“安26” | “奖状” | “雅克42” | ||
前端融合 | 87.89 | 98.36 | 99.89 | 95.38 |
中期融合 | 90.83 | 98.55 | 99.41 | 96.26 |
后端融合 | 91.05 | 97.51 | 99.70 | 96.06 |
表3 不同阶段融合对比
Table 3 Comparison of fusion at different stages %
融合时间 | 识别准确率 | 平均 识别率 | ||
---|---|---|---|---|
“安26” | “奖状” | “雅克42” | ||
前端融合 | 87.89 | 98.36 | 99.89 | 95.38 |
中期融合 | 90.83 | 98.55 | 99.41 | 96.26 |
后端融合 | 91.05 | 97.51 | 99.70 | 96.06 |
输入形式 | 识别准确率 | 平均 识别率 | ||
---|---|---|---|---|
“安26” | “奖状” | “雅克42” | ||
未添加 | 90.83 | 98.55 | 99.41 | 96.26 |
角度中值 | 98.72 | 96.49 | 99.93 | 98.38 |
角度序列+角度中值 | 98.43 | 98.90 | 99.46 | 98.93 |
表4 不同角度编码输入形式对比
Table 4 Comparison of different angle coding input forms %
输入形式 | 识别准确率 | 平均 识别率 | ||
---|---|---|---|---|
“安26” | “奖状” | “雅克42” | ||
未添加 | 90.83 | 98.55 | 99.41 | 96.26 |
角度中值 | 98.72 | 96.49 | 99.93 | 98.38 |
角度序列+角度中值 | 98.43 | 98.90 | 99.46 | 98.93 |
实验选取数据集 | 3类飞机识别率 | 平均 识别率 | ||
---|---|---|---|---|
“安26” | “奖状” | “雅克42” | ||
数据集1 | 86.68 | 98.49 | 100 | 95.06 |
数据集2 | 98.43 | 98.90 | 99.46 | 98.93 |
数据集3 | 90.97 | 97.66 | 100 | 96.21 |
数据集4 | 98.29 | 99.43 | 99.82 | 99.18 |
数据集5 | 75.13 | 89.98 | 85.23 | 83.45 |
数据集6 | 98.91 | 99.69 | 100 | 99.53 |
表5 不同数据集下的识别性能对比
Table 5 Comparison of recognition performance for different network models %
实验选取数据集 | 3类飞机识别率 | 平均 识别率 | ||
---|---|---|---|---|
“安26” | “奖状” | “雅克42” | ||
数据集1 | 86.68 | 98.49 | 100 | 95.06 |
数据集2 | 98.43 | 98.90 | 99.46 | 98.93 |
数据集3 | 90.97 | 97.66 | 100 | 96.21 |
数据集4 | 98.29 | 99.43 | 99.82 | 99.18 |
数据集5 | 75.13 | 89.98 | 85.23 | 83.45 |
数据集6 | 98.91 | 99.69 | 100 | 99.53 |
1 | LIU Chunsheng, WANG Zhongmei. Efficient Complex ISAR Object Recognition Using Adaptive Deep Relation Learning[J]. IET Computer Vision, 2020, 14(5): 185-191. |
2 | SHENG Bowen, CHEN Chengzeng, WANG Ruohui, et al. An ISAR Image Classification Method Based on MLP-Mixer Framework[C]∥2022 4th International Academic Exchange Conference on Science and Technology Innovation (IAECST). Piscataway: IEEE, 2022: 1003-1007. |
3 | AVADHANI A, CHAUDHARI S, GACHERIA P, et al. Inverse Synthetic-Aperture Radar(ISAR) Images Recognition Using Deep Learning[C]∥2020 Advanced Computing and Communication Technologies for High Performance Applications (ACCTHPA). Piscataway: IEEE, 2020: 293-298. |
4 | DUAN Jia, MA Yan, ZHANG Lei, et al. Abnormal Dynamic Recognition of Space Targets from ISAR Image Sequences with SSAE-LSTM Network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-16. |
5 | LI Gaopeng, SUN Zhao, ZHANG Yun. ISAR Target Recognition Using Pix2pix Network Derived from cGAN[C]∥2019 International Radar Conference (RADAR). Piscataway: IEEE, 2019: 1-4. |
6 | ZHOU Xuening, BAI Xueru. Robust ISAR Target Recognition Based on IC-STNs[C]∥2019 6th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR). Piscataway: IEEE, 2019: 1-5. |
7 | BAI Xueru, ZHOU Xuening, ZHANG Feng, et al. Robust Pol-ISAR Target Recognition Based on ST-MC-DCNN[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(12): 9912-9927. |
8 | ZHOU Xuening, BAI Xueru, WANG Li, et al. Robust ISAR Target Recognition Based on ADRISAR-Net[J]. IEEE Transactions on Aerospace and Electronic Systems, 2022, 58(6): 5494-5505. |
9 | YANG Yi, GAO Xunzhang, SHEN Qinmu. Learning Embedding Adaptation for ISAR Image Recognition with Few Samples[C]∥2021 2nd Information Communication Technologies Conference (ICTC). Piscataway: IEEE, 2021: 86-89. |
10 | 杨敏佳, 白雪茹, 刘士豪, 等. 基于高斯原型网络的小样本逆合成孔径雷达目标识别[J]. 电子与信息学报, 2022, 44(10): 3566-3573. |
YANG Minjia, BAI Xueru, LIU Shihao, et al. Small-Data Inverse Synthetic Aperture Radar Object Recognition Based on Gaussian Prototypical Network[J]. Journal of Electronics & Information Technology, 2022, 44(10): 3566-3573. | |
11 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is All You Need[C]∥Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010. |
12 | WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional Block Attention Module[C]∥Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 3-19. |
13 | HU Jie, SHEN Li, SUN Gang. Squeeze-and-Excitation Networks[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141. |
14 | LI Xiang, WANG Wenhai, HU Xiaolin, et al. Selective Kernel Networks[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2019: 510-519. |
15 | WANG Qilong, WU Banggu, ZHU Pengfei, et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks[C]∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2020: 11531-11539. |
16 | LI Xiuhe, RAN Jinhe, WEN Yanbo, et al. MVFRnet: A Novel High-Accuracy Network for ISAR Air-Target Recognition via Multi-View Fusion[J]. Remote Sensing, 2023, 15(12): 3052. |
17 | 邹浩, 林赟, 洪文. 采用深度学习的多方位角SAR图像目标识别研究[J]. 信号处理, 2018, 34(5): 513-522. |
ZOU Hao, LIN Yun, HONG Wen. Research on Multi-Aspect SAR Images Target Recognition Using Deep Learning[J]. Journal of Signal Processing, 2018, 34(5): 513-522. | |
18 | PENA CABALLERO C, CANTU E, RODRIGUEZ J, et al. A Multiple Radar Approach for Automatic Target Recognition of Aircraft Using Inverse Synthetic Aperture Radar[C]∥2018 1st International Conference on Data Intelligence and Security (ICDIS). Piscataway: IEEE, 2018: 24-31. |
19 | WANG Jing, HUO Chaoying, WANG Fang, et al. Analysis of Space Target Fusion Reconstruction Based on Optical Image and ISAR Image[C]∥Eighth Symposium on Novel Photoelectronic Detection Technology and Applications. Bellingham: SPIE, 2022: 1216927. |
20 | HAN Chunlei, LU Yao, YANG Di, et al. Multi-Source Collaborative Target Classification Based on ISAR and Infrared Image[C]∥2021 6th International Conference on Image, Vision and Computing (ICIVC). Piscataway: IEEE, 2021: 149-153. |
21 | LIU Yishu, LIU Yingbin, DING Liwang. Scene Classification Based on Two-Stage Deep Feature Fusion[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(2): 183-186. |
22 | LIN Wenhao, GAO Xunzhang, SHEN Qinmu. A Novel Recognition Method of ISAR Image Fusion Based on Botnet and Embracenet[C]∥2021 IEEE 6th International Conference on Signal and Image Processing (ICSIP). Piscataway: IEEE, 2021: 841-845. |
23 | LIU Jingjing, ZHANG Shaoting, WANG Shu, et al. Multispectral Deep Neural Networks for Pedestrian Detection[J/OL]. (2016-11-08) [2024-03-15]. . |
24 | 郭峰. 基于ISAR的舰船目标识别[D]. 北京: 中国电子科技集团公司电子科学研究院, 2019. |
GUO Feng. Ship Target Recognition Based on ISAR[D]. Beijing: China Academy of Electronics and Information Technology, 2019. | |
25 | 任永梅, 杨杰, 郭志强, 等. 基于多尺度卷积神经网络的自适应熵加权决策融合船舶图像分类方法[J]. 电子与信息学报, 2021, 43(5): 1424-1431. |
REN Yongmei, YANG Jie, GUO Zhiqiang, et al. Self-Adaptive Entropy Weighted Decision Fusion Method for Ship Image Classification Based on Multi-Scale Convolutional Neural Network[J]. Journal of Electronics & Information Technology, 2021, 43(5): 1424-1431. | |
26 | HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep Residual Learning for Image Recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2016: 770-778. |
27 | 陈学斌, 叶春茂, 张彦, 等. 含旋转部件的ISAR目标分离式成像[J]. 信号处理, 2021, 37(2): 209-221. |
CHEN Xuebin, YE Chunmao, ZHANG Yan, et al. Separately Imaging for ISAR Target with Rotational Components[J]. Journal of Signal Processing, 2021, 37(2): 209-221. | |
28 | 赵东涛, 黄雁飞, 齐玉涛. 含旋转部件的动态目标ISAR成像及微多普勒特征提取[J]. 雷达科学与技术, 2021, 19(3): 292-297. |
ZHAO Dongtao, HUANG Yanfei, QI Yutao. ISAR Imaging of Dynamic Targets with Rotating Parts and Micro-Doppler Feature Extraction[J]. Radar Science and Technology, 2021, 19(3): 292-297. | |
29 | 高磊, 曾勇虎, 汪连栋, 等. 空中非合作目标旋转部件位置估计方法[J]. 国防科技大学学报, 2019, 41(5): 111-117. |
GAO Lei, ZENG Yonghu, WANG Liandong, et al. Position Estimation Method for Rotation Part in Non-Cooperation Aerial Target[J]. Journal of National University of Defense Technology, 2019, 41(5): 111-117. | |
30 | SUN Yuanshuang, WANG Yinghua, LIU Hongwei, et al. SAR Target Recognition with Limited Training Data Based on Angular Rotation Generative Network[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(11): 1928-1932. |
31 | 郭帅, 陈婷, 王鹏辉, 等. 基于角度引导Transformer融合网络的多站协同目标识别方法[J]. 雷达学报, 2023, 12(3): 516-528. |
GUO Shuai, CHEN Ting, WANG Penghui, et al. Multistation Cooperative Radar Target Recognition Based on an Angle-Guided Transformer Fusion Network[J]. Journal of Radars, 2023, 12(3): 516-528. |
[1] | 赵文栋, 张明智, 郭圣明. 一种面向体系作战的目标群体类型判识方法[J]. 现代防御技术, 2025, 53(2): 74-81. |
[2] | 付亦凡, 阮航, 周东平, 穆贺强. 基于改进轻量化神经网络的干扰识别方法[J]. 现代防御技术, 2025, 53(2): 91-98. |
[3] | 范宇哲, 范林刚, 张志衡, 陈成增. 基于改进Clean算法的ISAR像目标轮廓提取方法[J]. 现代防御技术, 2025, 53(2): 156-166. |
[4] | 邢汇源, 崔亚奇, 王子玲, 熊伟, 蒋丙栋. 复杂海况下的海上船舶目标检测算法[J]. 现代防御技术, 2024, 52(6): 88-96. |
[5] | 赵文栋, 张明智, 郭圣明. 知识互联视角下的作战行动判识方法[J]. 现代防御技术, 2024, 52(3): 64-72. |
[6] | 商城, 徐志明, 张杨, 张楷煜, 吴其华, 朱义奇, 艾小锋. 空中目标动态电磁散射数据仿真系统设计与实现[J]. 现代防御技术, 2024, 52(2): 163-171. |
[7] | 师俞晨. 基于遥感影像水下目标尾迹探测综述[J]. 现代防御技术, 2024, 52(1): 83-91. |
[8] | 李喆, 童逸琦, 夏文博, 应宇欣. 一种多源集中式空中目标类型综合识别方法[J]. 现代防御技术, 2023, 51(4): 53-62. |
[9] | 何明, 朱梓涵, 翟绪龙, 翟政, 郝程鹏. 基于多分支上下文融合的空对地目标检测算法[J]. 现代防御技术, 2023, 51(3): 91-98. |
[10] | 岳磊, 袁建虎, 杨柳, 吕婷婷. 一种巡逻执勤目标检测算法研究[J]. 现代防御技术, 2023, 51(1): 67-74. |
[11] | 张进, 徐国亮, 郭浩. 人工智能技术在国外舰载武器系统中的应用浅析[J]. 现代防御技术, 2023, 51(1): 42-49. |
[12] | 牛浩楠, 王文灿, 刘清波. 基于卷积神经网络的雷达辐射源识[J]. 现代防御技术, 2021, 49(3): 130-136. |
[13] | 黄祥, 徐静, 都晨, 郭昭艺, 吴涛. 一种无人机辐射源调制样式识别算法[J]. 现代防御技术, 2021, 49(3): 98-104. |
[14] | 刘标, 许腾, 刘树锋. 水下目标识别的规划融合算法[J]. 现代防御技术, 2018, 46(6): 64-67. |
[15] | 林菡, 李昌玺, 陈丽娟. MIMO-FNN模型的弹道导弹目标识别方法[J]. 现代防御技术, 2018, 46(6): 36-43. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||