| 319 | 0 | 722 |
| 下载次数 | 被引频次 | 阅读次数 |
无人机技术的广泛应用对其安全性与可靠性提出了更高要求，基于指纹特征的识别技术成为管控非法无人机的关键手段。为系统综述基于深度学习的无人机指纹识别方法研究现状，重点关注现存神经网络架构、数据集问题及其优化，以及复杂环境中的适应性提升。介绍了深度学习架构如卷积神经网络(Convolutional Neural Network, CNN)、循环神经网络(Recurrent Neural Network, RNN)等在无人机信号特征提取和分类中的应用现状、优势及其改进；研究分析了训练数据集现存问题，总结了样本总量不足和类别间样本比例失衡两方面挑战，针对这些问题的数据扩充技术进行了分析；研究总结了深度学习技术在噪声干扰、硬件缺陷、特定地形等复杂环境下提升无人机指纹识别适应性的优势与做法。清晰指出了现有架构的优势与改进方向、数据集的核心瓶颈及解决路径、复杂环境下的增强策略，为深度学习在无人机指纹识别领域的应用与发展提供了重要参考。
Abstract：The widespread application of UAV technology has imposed higher requirements on its safety and reliability. Recognition technology based on fingerprint features has become a key means for the management and control of illegal UAVs. To systematically review the research status of UAV fingerprint recognition methods based on deep learning, existing neural network architectures, problems in datasets and their optimizations, as well as the improvement of adaptability in complex environments have been focused on. Firstly, the current application status, advantages and improvements of deep learning architectures such as Convolutional Neural Network(CNN) and Recurrent Neural Network(RNN) in feature extraction and classification of UAV signals have been introduced. Secondly, the existing problems of training datasets have been studied and analyzed, the challenges of insufficient total samples and imbalanced sample proportions among categories have been summarized, and the data augmentation techniques for addressing these problems have been analyzed. Finally, the advantages and approaches of deep learning technologies in enhancing the adaptability of UAV fingerprint recognition under complex environments such as noise interference, hardware defects, and specific terrains have been summarized. The advantages and improvement directions of existing architectures, the core bottlenecks of datasets and their solution paths, as well as the enhancement strategies under complex environments have been clearly pointed out. This study can provide important references for the application and development of deep learning in UAV fingerprint recognition.
[1] EZUMA M,ERDEN F,ANJINAPPA C K,et al.Micro-UAV Detection and Classification from RF Fingerprints Using Machine Learning Techniques[C]//Proceedings of IEEE Aerospace Conference.Big Sky:IEEE,2019:1-13.
[2] JIAN T,RENDON B C,OJUBA E,et al.Deep Learning for RF Fingerprinting:A Massive Experimental Study[J].IEEE Internet of Things Magazine,2020,3(1):50-57.
[3] CU Y Q,XU G X,AN Z L,et al.Adversarial Attacks and Active Defense on Deep Learning Based Identification of GaN Power Amplifiers Under Physical Perturbation[J].AEU-International Journal of Electronics and Communications,2023,159:154478.
[4] SHORTEN C,KHOSHGOFTAAR T M.A Survey on Image Data Augmentation for Deep Learning[J].Journal of Big Data,2019,6:60.
[5] WANG Y Q,YAO Q M,KWOK J T,et al.Generalizing from a Few Examples:A Survey on Few-shot Learning[J].ACM Computing Surveys,2020,53(3):63.
[6] SANDLER M,HOWARD A,ZHU M L,et al.MobileNetV2:Inverted Residuals and Linear Bottlenecks[C]//Proceedings of 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:4510-4520.
[7] SANKHE K,BELGIOVINE M,ZHOU F,et al.ORACLE:Optimized Radio Classification Through Convolutional Neural Network[C]//Proceedings of 2019 IEEE Conference on Computer Communications.Paris:IEEE,2019:370-378.
[8] 何兵.基于信号指纹的多旋翼无人机遥控端个体识别研究[D].赣州：江西理工大学，2021.
[9] 蒋平，谢跃雷.一种民用小型无人机的射频指纹识别方法[J].电讯技术，2021,61(6):737-743.
[10] 王豪，罗俊松，王惠明，等.无人机射频指纹识别方法综述[J].无线电工程，2024,54(11):2672-2684.
[11] 耿飞跃.无人机射频指纹提取与分类识别方法研究[D].南京：东南大学，2019.
[12] 严丹莉.基于通信信号指纹的无人机个体识别[D].成都：电子科技大学，2020.
[13] AL-EMADI S,AL-ALI A,MOHAMMAD A,et al.Audio Based Drone Detection and Identification Using Deep Learning[C]//Proceedings of 15th IEEE International Wireless Communications and Mobile Computing Conference.Tangier:IEEE,2019:459-464.
[14] BREMNES K,MOEN R S,YEDURI R,et al.Classification of UAVs Utilizing Fixed Boundary Empirical Wavelet Sub-bands of RF Fingerprints and Deep Convolutional Neural Network[J].IEEE Sensors Journal,2022,22(21):21248-21256.
[15] ZHENG Y F,ZHANG X J,WANG S H,et al.Convolutional Neural Network and Ensemble Learning-based Unmanned Aerial Vehicles Radio Frequency Fingerprinting Identification[J].Drones,2024,8(8):391.
[16] YANG J,GU H,HU C H,et al.Deep Complex-valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting[J].Drones,2022,6(12):374.
[17] SONG L L,GAO Z Z,HUANG J,et al.A Lightweight Radio Frequency Fingerprint Extraction Scheme for Device Identification[C]//Proceedings of 2023 IEEE Wireless Communications and Networking Conference(WCNC).Glasgow:IEEE,2023:1-5.
[18] BASAK S,RAJENDRAN S,POLLIN S,et al.Spectrum Prediction for Protocol-aware RF Jamming[J].IEEE Transactions on Cognitive Communications and Networking,2024,10(2):363-373.
[19] ZHAO Y S.Research on UAV Signal Classification Algorithm Based on Deep Learning[C]//Proceedings of 3rd International Conference on Image Processing and Machine Vision.Hong Kong:ACM,2021:24-29.
[20] VIANA J,FARKHARI H,SEBASTI?O P,et al.Deep Attention Recognition for Attack Identification in 5G UAV Scenarios:Novel Architecture and End-to-End Evaluation[J].IEEE Transactions on Vehicular Technology,2024,73(1):131-146.
[21] 杨宁，胡景明，张邦宁，等.低空智联网中基于多质心OpenMax的无人机开集识别方法[J].数据采集与处理，2024,39(1):60-70.
[22] HUANG G,SUN Y,LIU Z,et al.Deep Networks with Stochastic Depth[C]// Computer Vision-ECCV 2016.Amsterdam:Springer,2016:646-661.
[23] LI Q L,WANG F S,ZHANG Y B,et al.Novel Micro-UAV Identification Approach Assisted by Combined RF Fingerprint[J].IEEE Sensors Journal,2024,24(16):26802-26813.
[24] TIRAS F E,ALTINOLUK H S.CrossRF:A Domain-invariant Deep Learning Approach for RF Fingerprinting[EB/OL].(2025-05-21)[2025-05-21].https://export.arxiv.org/abs/2505.18200.
[25] YAN X,HAN B,SU Z G,et al.SignalFormer:Hybrid Transformer for Automatic Drone Identification Based on Drone RF Signals[J].Sensors,2023,23(22):9098.
[26] HUSSAIN A M,ABUGHANAM N,PAPADIMITRATOS P.Edge AI-based Radio Frequency Fingerprinting for IoT Networks[EB/OL].(2024-12-13)[2025-03-19].https://arxiv.org/abs/2412.10553.
[27] 俞宁宁，毛盛健，周成伟，等.DroneRFa:用于侦测低空无人机的大规模无人机射频信号数据集[J].电子与信息学报，2024,46(4):1147-1156.
[28] SWINNEY C J,WOODS J C.DroneDetect Dataset:A Radio Frequency Dataset of Unmanned Aerial System (UAS) Signals for Machine Learning Detection & Classification[DS/OL].(2022-05-18) [2025-03-19].https://ieee-dataport.org/open-access/dronedetect-dataset-radio-frequency-dataset-unmanned-aerial-system-uas-signals-machine.
[29] ZHAO T Y,DOMAE B W,STEIGERWALD C,et al.Drone RF Signal Detection and Fingerprinting:UAVSig Dataset and Deep Learning Approach[C]//Proceedings of MILCOM 2024-2024 IEEE Military Communications Conference (MILCOM).Washington D.C.:IEEE,2024:431-436.
[30] AL-SA’D M F,AL-ALI A,MOHAMED A,et al.RF-based Drone Detection and Identification Using Deep Learning Approaches:An Initiative Towards a Large Open Source Drone Database[J].Future Generation Computer Systems,2019,100:86-97.
[31] ALLAHHAM M S,AL-SA’D M F,AL-ALI A,et al.DroneRF Dataset:A Dataset of Drones for RF-based Detection,Classification and Identification[J].Data in Brief,2019,26:104313.
[32] LIANG H T,WANG R T,XU M,et al.Few-shot Learning UAV Recognition Methods Based on the Tri-residual Semantic Network[J].IEEE Communications Letters,2022,26(9):2072-2076.
[33] REN Z Y,REN P Y,ZHANG T T.Deep RF Device Fingerprinting by Semi-supervised Learning with Meta Pseudo Time-frequency Labels[C]//2022 IEEE Wireless Communications and Networking Conference (WCNC).Austin:IEEE:2369-2374.
[34] HUANG K J,YANG J A,LIU H,et al.Deep Learning of Radio Frequency Fingerprints from Limited Samples by Masked Autoencoding[EB-OL].(2022-06-21)[2025-03-19].https://ieeexplore.ieee.org/abstract/document/9802743.
[35] ZHANG H T,ZHAO L,JIANG Y.Triplet Network and Unsupervised-clustering-based Zero-shot Radio Frequency Fingerprint Identification with Extremely Small Sample Size[J].IEEE Internet of Things Journal,2023,11(8):14416-14434.
[36] 杨思狄，王亚玲.面向不均衡数据集的过抽样数学模型构建[J].计算机仿真，2021,38(5):472-476.
[37] 崔鑫，徐华，宿晨.面向不均衡数据集的过抽样算法[J].计算机应用，2020,40(6):1662-1667.
[38] 韩慧，王路，温明，等.不均衡数据集学习中基于初分类的过抽样算法[J].计算机应用，2006(8):1894-1897.
[39] SOLTANI N,REUS-MUNS G,SALEHI B,et al.RF Fingerprinting Unmanned Aerial Vehicles with Non-standard Transmitter Waveforms[J].IEEE Transactions on Vehicular Technology,2020,69(12):15518-15531.
[40] GU H Q,SU L S,ZHANG W F,et al.Attention Is Needed for RF Fingerprinting[J].IEEE Access,2023,11:87316-87329.
[41] ZHANG W F,ZHAO W H,TAN X H,et al.Adaptive RF Fingerprints Fusion via Dual Attention Convolutions[J].IEEE Internet of Things Journal,2022,9(24):25181-25195.
[42] CAI Z X,WANG Y,JIANG Q,et al.Toward Intelligent Lightweight and Efficient UAV Identification with RF Fingerprinting[J].IEEE Internet of Things Journal,2024,11(15):26329-26339.
[43] LI B T,LIU D,YANG J,et al.An RF Fingerprint Data Enhancement Method Based on WGAN[C]//Proceedings of International Conference in Communications,Signal Processing,and Systems.Changbaishan:Springer,2023:539-547.
[44] ASENSIO C,RUIZ M,RECUERO M.Real-time Aircraft Noise Likeness Detector[J].Applied Acoustics,2010,71(6):539-545.
[45] EZUMA M,ERDEN F,ANJINAPPA C K,et al.Detection and Classification of UAVs Using RF Fingerprints in the Presence of Wi-Fi and Bluetooth Interference[J].IEEE Open Journal of the Communications Society,2020,1:60-76.
[46] JAGANNATH A,JAGANNATH J,KUMAR P S P V.A Comprehensive Survey on Radio Frequency (RF) Fingerprinting:Traditional Approaches,Deep Learning,and Open Challenges[J].Computer Networks,2022,219:109455.
[47] TIAN Y,WEN H,ZHOU J X,et al.Optimized Radio Frequency Footprint Identification Based on UAV Telemetry Radios[J].Sensors,2024,24(16):5099.
基本信息:
中图分类号:V19;TP18;TP391.41
引用信息:
[1]李铭典,李乐文,申安泽,等.基于深度学习的无人机指纹识别[J].无线电工程,2025,55(09):1835-1846.
基金信息:
陕西省重点研发计划(2024CY2-GJHX-23)~~
2025-09-05
2025-09-05