Advanced Search
Turn off MathJax
Article Contents
DONG Pengyu, XIANG Xin, WANG Rui, LV Siting, LIANG Yuan, MAO Hu. A Lightweight Dual-Stream Convolutional Network for Feature Fusion in UAV RF Recognition[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260464
Citation: DONG Pengyu, XIANG Xin, WANG Rui, LV Siting, LIANG Yuan, MAO Hu. A Lightweight Dual-Stream Convolutional Network for Feature Fusion in UAV RF Recognition[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260464

A Lightweight Dual-Stream Convolutional Network for Feature Fusion in UAV RF Recognition

doi: 10.11999/JEIT260464 cstr: 32379.14.JEIT260464
  • Received Date: 2026-04-30
  • Accepted Date: 2026-08-10
  • Rev Recd Date: 2026-07-31
  • Available Online: 2026-08-20
  •   Objective  With the rapid proliferation of Unmanned Aerial Vehicles (UAVs) and increasing demand for airspace security, Radio Frequency (RF) fingerprint recognition has become an important approach for identifying non-cooperative UAVs. However, existing methods show limited robustness under low Signal-to-Noise Ratio (SNR) conditions and often require substantial computational resources, which restricts their deployment on resource-constrained tactical edge devices. To address these limitations, a Lightweight Dual-Stream Convolutional Network (LDSC-Net) is proposed for UAV RF recognition. LDSC-Net extracts static spectral texture features and dynamic temporal gradient features in parallel and integrates them using a lightweight feature fusion strategy.  Methods  The proposed LDSC-Net processes RF signals through two parallel streams. First, a Short-Time Fourier Transform (STFT) is applied to the input signal to generate a two-dimensional spectrogram. The spectrogram is converted to a single-channel grayscale image, normalized to the range of [–1,1], and resized to 128 × 128 pixels. The static stream extracts static spectral texture features from the STFT spectrogram using a series of lightweight convolutional blocks consisting of convolution, batch normalization, ReLU activation, and max-pooling operations. The dynamic stream first applies a first-order temporal difference along the temporal dimension of the STFT spectrogram to generate a temporal gradient map. This operation suppresses static background noise and enhances dynamic signal variations, thereby improving feature contrast under low-SNR conditions. The temporal gradient map is then processed by a convolutional structure symmetric to that of the static stream. The features from the two streams are fused by element-wise addition without introducing additional learnable parameters. The fused features are then subjected to global average pooling and passed to the classification head for UAV category recognition. Experiments are conducted on the publicly available DroneRF dataset. Ablation experiments, comparisons of different feature fusion strategies, feature visualization, and comparisons with established convolutional neural networks are performed to evaluate the effectiveness, robustness, and lightweight characteristics of LDSC-Net.  Results and Discussions  LDSC-Net achieves an accuracy of 95.65% on the test set, which is approximately 5 percentage points higher than that of the best single-stream network. The static stream and dynamic stream achieve accuracies of 90.22% and 83.15%, respectively, confirming the complementary roles of static spectral texture features and dynamic temporal gradient features. The first-order temporal difference increases the local contrast of the time-frequency representation by more than 1 dB, enhancing the discriminability of dynamic temporal gradient features under low-SNR conditions. LDSC-Net contains only 0.58 M parameters and achieves a single-sample inference time of 2.37 ms. Compared with ResNet-18, EfficientNetV1, MobileNetV2, ShuffleNetV2, and SqueezeNet, LDSC-Net maintains an accuracy of 95.65% and an F1-score of 0.96 with substantially fewer parameters. Feature visualization further shows that the static and dynamic streams capture complementary information. The element-wise addition strategy achieves performance comparable to or better than channel concatenation, attention weighting, and element-wise maximum while introducing no additional learnable parameters. Robustness evaluation under SNR conditions ranging from 0 dB to 20 dB further demonstrates the effectiveness of LDSC-Net under noisy conditions.  Conclusions  A lightweight dual-stream convolutional network is proposed for UAV RF recognition in complex environments. The method enhances recognition performance through the complementary extraction of static spectral texture features and dynamic temporal gradient features. The first-order temporal difference suppresses background interference and enhances dynamic feature contrast. The element-wise addition fusion strategy integrates the two types of features without introducing additional learnable parameters, thereby maintaining a lightweight architecture suitable for edge deployment. The proposed method provides an effective approach for UAV RF recognition under low-SNR conditions.
  • loading
  • [1]
    CRIOLLO L, MENA-ARCINIEGA C, and XING Shen. Classification, military applications, and opportunities of unmanned aerial vehicles[J]. Aviation, 2024, 28(2): 115–127. doi: 10.3846/aviation.2024.21672.
    [2]
    LYU Mingyang, ZHAO Yibo, HUANG Chao, et al. Unmanned aerial vehicles for search and rescue: A survey[J]. Remote Sensing, 2023, 15(13): 3266. doi: 10.3390/rs15133266.
    [3]
    QU Chengyi, SORBELLI F B, SINGH R, et al. Environmentally-aware and energy-efficient multi-drone coordination and networking for disaster response[J]. IEEE Transactions on Network and Service Management, 2023, 20(2): 1093–1109. doi: 10.1109/TNSM.2023.3243543.
    [4]
    CEVIZ O, SEN S, and SADIOGLU P. A survey of security in UAVs and FANETs: Issues, threats, analysis of attacks, and solutions[J]. IEEE Communications Surveys & Tutorials, 2025, 27(5): 3227–3265. doi: 10.1109/COMST.2024.3515051.
    [5]
    OMOLARA A E, ALAWIDA M, and ABIODUN O I. Drone cybersecurity issues, solutions, trend insights and future perspectives: A survey[J]. Neural Computing and Applications, 2023, 35(31): 23063–23101. doi: 10.1007/s00521-023-08857-7.
    [6]
    杨勇, 王雪松, 张斌. 基于时频检测与极化匹配的雷达无人机检测方法[J]. 电子与信息学报, 2021, 43(3): 509–515. doi: 10.11999/JEIT200768.

    YANG Yong, WANG Xuesong, and ZHANG Bin. Radar detection of unmanned aerial vehicles based on time-frequency detection and polarization matching[J]. Journal of Electronics & Information Technology, 2021, 43(3): 509–515. doi: 10.11999/JEIT200768.
    [7]
    江波, 屈若锟, 李彦冬, 等. 基于深度学习的无人机航拍目标检测研究综述[J]. 航空学报, 2021, 42(4): 524519. doi: 10.7527/S1000-6893.2020.24519.

    JIANG Bo, QU Ruokun, LI Yandong, et al. Object detection in UAV imagery based on deep learning: Review[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 524519. doi: 10.7527/S1000-6893.2020.24519.
    [8]
    XIE Yuelei, JIANG Ping, GU Yi, et al. Dual-source detection and identification system based on UAV radio frequency signal[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 2006215. doi: 10.1109/TIM.2021.3103565.
    [9]
    ZHENG Haolin, GAO Ning, CAI Donghong, et al. UAV individual identification via distilled RF fingerprints-based LLM in ISAC networks[J]. IEEE Wireless Communications Letters, 2025, 14(11): 3769–3773. doi: 10.1109/LWC.2025.3603423.
    [10]
    MEDAIYESE O O, EZUMA M, LAUF A P, et al. Hierarchical learning framework for UAV detection and identification[J]. IEEE Journal of Radio Frequency Identification, 2022, 6: 176–188. doi: 10.1109/JRFID.2022.3157653.
    [11]
    唐智灵, 杨小牛, 李建东. 基于顺序统计的窄带通信辐射源指纹特征抽取方法[J]. 电子与信息学报, 2011, 33(5): 1224–1228. doi: 10.3724/SP.J.1146.2010.01058.

    TANG Zhiling, YANG Xiaoniu, and LI Jiandong. A novel method based on order statistics for extracting fingerprint of narrow band emitter[J]. Journal of Electronics & Information Technology, 2011, 33(5): 1224–1228. doi: 10.3724/SP.J.1146.2010.01058.
    [12]
    唐晓刚, 冯俊豪, 张斌权, 等. 基于射频指纹的卫星测控地面站身份识别方法[J]. 电子与信息学报, 2023, 45(7): 2554–2560. doi: 10.11999/JEIT220804.

    TANG Xiaogang, FENG Junhao, ZHANG Binquan, et al. Satellite telemetry track and command ground station identification method based on RF fingerprint[J]. Journal of Electronics & Information Technology, 2023, 45(7): 2554–2560. doi: 10.11999/JEIT220804.
    [13]
    吴一全, 童康. 基于深度学习的无人机航拍图像小目标检测研究进展[J]. 航空学报, 2025, 46(3): 30848. doi: 10.7527/S1000-6893.2024.30848.

    WU Yiquan and TONG Kang. Research advances on deep learning-based small object detection in UAV aerial images[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(3): 30848. doi: 10.7527/S1000-6893.2024.30848.
    [14]
    蒋伊琳, 尹子茹, 宋宇. 基于卷积神经网络的低截获概率雷达信号检测算法[J]. 电子与信息学报, 2022, 44(2): 718–725. doi: 10.11999/JEIT210132.

    JIANG Yilin, YIN Ziru, and SONG Yu. Low probability of intercept radar signal detection algorithm based on convolutional neural networks[J]. Journal of Electronics & Information Technology, 2022, 44(2): 718–725. doi: 10.11999/JEIT210132.
    [15]
    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. doi: 10.1016/j.future.2019.05.007.
    [16]
    赵慎, 李广选, 周鲜成, 等. 多无人机射频信号CNN| Triplet-DNN异构网络特征提取与机型识别[J]. 电子与信息学报, 2026, 48(3): 1230–1240. doi: 10.11999/JEIT250757.

    ZHAO Shen, LI Guangxuan, ZHOU Xiancheng, et al. Multi-UAV RF signals CNN| Triplet-DNN heterogeneous network feature extraction and type recognition[J]. Journal of Electronics & Information Technology, 2026, 48(3): 1230–1240. doi: 10.11999/JEIT250757.
    [17]
    聂伟, 戴琪霏, 杨小龙, 等. 基于多维信号特征的无人机探测识别方法[J]. 电子与信息学报, 2024, 46(3): 1089–1099. doi: 10.11999/JEIT230302.

    NIE Wei, DAI Qifei, YANG Xiaolong, et al. Unmanned aerial vehicle detection and recognition method based on multi-dimensional signal feature[J]. Journal of Electronics & Information Technology, 2024, 46(3): 1089–1099. doi: 10.11999/JEIT230302.
    [18]
    聂伟, 张中洋, 杨小龙, 等. 基于梅尔倒谱系数的无人机探测与识别方法[J]. 电子与信息学报, 2025, 47(4): 1076–1084. doi: 10.11999/JEIT241111.

    NIE Wei, ZHANG Zhongyang, YANG Xiaolong, et al. Unmanned aerial vehicles detection and recognition method based on Mel Frequency Cepstral Coefficients[J]. Journal of Electronics & Information Technology, 2025, 47(4): 1076–1084. doi: 10.11999/JEIT241111.
    [19]
    田旭东, 白雪茹, 周峰. 基于稀疏自编码器的空间微动目标融合识别方法[J]. 电子与信息学报, 2023, 45(12): 4336–4344. doi: 10.11999/JEIT221163.

    TIAN Xudong, BAI Xueru, and ZHOU Feng. Fusion recognition of space targets with micro-motion based on a sparse auto-encoder[J]. Journal of Electronics & Information Technology, 2023, 45(12): 4336–4344. doi: 10.11999/JEIT221163.
    [20]
    YENDURI S, GUDAVALLI M, and C G. Optimal transport-based fusion of two-stream convolutional networks for action recognition[J]. Applied Intelligence, 2025, 55(7): 641. doi: 10.1007/s10489-025-06518-x.
    [21]
    HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. The 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016: 770–778. doi: 10.1109/CVPR.2016.90.
    [22]
    TAN Mingxing and LE Q V. EfficientNet: Rethinking model scaling for convolutional neural networks[C]. The 36th International Conference on Machine Learning (ICML), Long Beach, USA, 2019: 6105–6114.
    [23]
    HOWARD A G, ZHU Menglong, CHEN Bo, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv: 1704.04861, 2017. doi: 10.48550/arXiv.1704.04861.
    [24]
    MA Ningning, ZHANG Xiangyu, ZHENG Haitao, et al. ShuffleNet V2: Practical guidelines for efficient CNN architecture design[C]. The 15th European Conference on Computer Vision–ECCV 2018, Munich, Germany, 2018: 122–138. doi: 10.1007/978-3-030-01264-9_8.
    [25]
    IANDOLA F N, HAN Song, MOSKEWICZ M W, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size[C]. The 5th International Conference on Learning Representations, Toulon, France, 2017.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(8)  / Tables(3)

    Article Metrics

    Article views (862) PDF downloads(82) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return