FU Wenqiao,XU Zixin,WANG Zhihong,et al.Research on Classification and Recognition of UAV Image Transmission Signals based on EfficientNet[J].Journal of Chengdu University of Information Technology,2026,41(01):32-38.[doi:10.16836/j.cnki.jcuit.2026.01.005]
基于EfficientNet的无人机图传信号分类识别研究
- Title:
- Research on Classification and Recognition of UAV Image Transmission Signals based on EfficientNet
- 文章编号:
- 2096-1618(2026)01-0032-07
- Keywords:
- UAV; mapping signals; signal detection; deep learning
- 分类号:
- TP391.41
- 文献标志码:
- A
- 摘要:
- 针对无人机迅速发展带来的非法侦查、空域侵0犯、无人机碰撞等潜在安全问题,提出一种基于软件定义无线电和深度学习的无人机图传信号检测与识别方法。通过搭建以USRP B210和飞腾派为核心的硬件平台,成功采集多种无人机图传信号及Wi-Fi信号,并对采集到的信号进行时频图转换,构建高质量的数据集。采用EfficientNet模型进行训练,并在训练集和验证集上实现了显著的性能提升。最终,在大疆Mavic系列、Mini 4 Pro等6种无人机上使用构建的无人机图传信号数据集进行实验,识别和分类准确率达96%以上,表明该方法在民用无人机信号监测领域的高应用前景。
- Abstract:
- Aiming at the potential security problems such as illegal detection,airspace infringement and UAV collision brought by the rapid development of UAVs, and in order to solve the problem of UAV “black flight” of UAVs, this paper proposes a method to detect and recognise UAV mapping signals based on software-defined radio and deep learning. By building a hardware platform with USRP B210 and Feitengpai as the core, a variety of UAV Image Transmission signals and Wi-Fi signals are successfully collected, and the collected signals are converted into time-frequency diagrams to construct a high-quality data set. The EfficientNet model was used for training, and significant performance improvements were realized on the training and validation sets. Finally, experiments were conducted on six types of UAVs, including DJI Mavic series and Mini 4 Pro, using the UAV Image Transmission signal dataset constructed in this paper, and the recognition and classification accuracy reached more than 96%, demonstrating the high application prospect of this method in the field of civil UAV signal monitoring.
参考文献/References:
[1] Gupta L,Jain R,Vaszkun G.Survey of important issues in UAV communication networks[J].IEEE communications surveys & tutorials,2015,18(2):1123-1152.
[2] 曲健.警惕无人机带来的新型威胁[J].保密工作,2019(3):60-62.
[3] Schilling F,Schiano F,Floreano D.Vision-based drone flocking in outdoor environments[J].IEEE Robotics and Automation Letters,2021,6(2):2954-2961.
[4] 邵盼愉.基于视觉的无人机入侵检测与跟踪系统设计与实现[D].杭州:浙江大学,2018.
[5] Shi Z,Chang X,Yang C,et al.An acoustic-based surveillance system for amateur drones detection and localization[J].IEEE transactions on vehicular technology,2020,69(3):2731-2739.
[6] 黄强.低空无人机被动声探测定位方法研究[D].成都:电子科技大学,2018.
[7] Choi B,Oh D,Kim S,et al.Long-range drone detection of 24 g FMCW radar with e-plane sectoral horn array[J].Sensors,2018,18(12):4171.
[8] 马越,缪晨,张若愚,等.“低慢小”无人机雷达探测研究与展望[J].国防科技,2023,44(5):60-66.
[9] Chiper F L,Martian A,Vladeanu C,et al.Drone detection and defense systems:Survey and a software-defined radio-based solution[J].Sensors,2022,22(4):1453.
[10] 蒋平,谢跃雷.基于飞控信号频谱特征的无人机检测与识别系统设计[J].电子器件,2020,43(4):7.
[11] Bi L,Xu Z X,Yang L.Low-cost UAV detection via WiFi traffic analysis and machine learning[J].Scientific Reports,2023,13(1):20892.
[12] Yu T,Imada S,Araki K,et al.Multi-UAV full-duplex communication systems for joint video transmission and flight control[C].2021 IEEE 11th Annual Computing and Communication Workshop and Conference(CCWC).IEEE,2021:1423-1428.
[13] Gafsi M,Ajili S,Hajjaji M A,et al.High securing cryptography system for digital image transmission[J].Proceedings of the 8th International Conference on Sciences of Electronics,Technologies of Information and Telecommunications(SETIT'18),Springer International Publishing,2020,1:311-322.
[14] Tan M,Chen B,Pang R,et al.Mnasnet:Platform-aware neural architecture search for mobile[C].Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.2019:2820-2828.
[15] 陈雨红,杨长春,曹齐放,等.几种时频分析方法比较[J].地球物理学进展,2006,21(4):1180-1185.
[16] Durak L,Arikan O.Short-time Fourier transform:two fundamental properties and an optimal implementation[J].IEEE Transactions on Signal Processing,2003,51(5):1231-1242.
[17] Li Z,Liu F,Yang W,et al.A survey of convolutional neural networks:analysis,applications,and prospects[J].IEEE transactions on neural networks and learning systems,2021,33(12):6999-7019.
[18] Szegedy C,Ioffe S,Vanhoucke V,et al.Inception-v4,inception-resnet and the impact of residual connections on learning[C].Proceedings of the AAAI conference on artificial intelligence.2017,31(1).
[19] Milota III J.Software radios:survey,critical evaluation and future directions[J].Aerospace and Electronic Systems Magazine,IEEE,1992,8(4):25-36.
[20] DJI大疆创新.DJI Mini 4 Pro技术参数[EB/OL]. https://www.dji.com/cn/mini-4-pro/specs.
相似文献/References:
[1]周 咏,万 垚.基于无人机的监控系统设计[J].成都信息工程大学学报,2021,36(02):159.[doi:10.16836/j.cnki.jcuit.2021.02.006]
ZHOU Yong,WAN Yao.Design of Surveillance System based on UAV[J].Journal of Chengdu University of Information Technology,2021,36(01):159.[doi:10.16836/j.cnki.jcuit.2021.02.006]
[2]凌荣巧,卢会国,蒋娟萍,等.基于气象无人机观测的测风优化研究[J].成都信息工程大学学报,2023,38(03):271.[doi:10.16836/j.cnki.jcuit.2023.03.004]
LING Rongqiao,LU Huiguo,JIANG Juanping,et al.Optimization Study of Wind Measurement based on Meteorological Drone Observation[J].Journal of Chengdu University of Information Technology,2023,38(01):271.[doi:10.16836/j.cnki.jcuit.2023.03.004]
[3]王 会,王永前,李剑锋,等.基于无人机多光谱数据的三峡库区支流叶绿素a浓度估算——以小江为例[J].成都信息工程大学学报,2024,39(02):233.[doi:10.16836/j.cnki.jcuit.2024.02.015]
WANG Hui,WANG Yongqian,LI Jianfeng,et al.Estimation of Chlorophyll a Concentration in Three Gorges Reservoir Branch based on UAV Multispectral Data——A Case Study of Xiaojiang River[J].Journal of Chengdu University of Information Technology,2024,39(01):233.[doi:10.16836/j.cnki.jcuit.2024.02.015]
[4]范思睿,王维佳,王博为,等.2022年2月青藏高原东侧大型无人机人工增雪试验分析[J].成都信息工程大学学报,2025,40(02):220.[doi:10.16836/j.cnki.jcuit.2025.02.013]
FAN Sirui,WANG Weijia,WANG Bowei,et al.Analysis of Artificial Snow Enhancement Experiment of Large UAV on the East Side of Tibet Plateau in February 2022[J].Journal of Chengdu University of Information Technology,2025,40(01):220.[doi:10.16836/j.cnki.jcuit.2025.02.013]
[5]胡敬松,卢会国,史 静,等.基于改进卡尔曼滤波算法的无人机测风数据降噪处理[J].成都信息工程大学学报,2026,41(01):1.[doi:10.16836/j.cnki.jcuit.2026.01.001]
HU Jingsong,LU Huiguo,SHI Jing,et al.Noise Reduction Process of Drone Wind Measurement Data based on Improved Kalman Filter[J].Journal of Chengdu University of Information Technology,2026,41(01):1.[doi:10.16836/j.cnki.jcuit.2026.01.001]
备注/Memo
收稿日期:2024-08-03
基金项目:四川省科技计划资助项目(2020YFH0122)