DroneRFb-DIR: 用于非合作無人機(jī)個(gè)體識(shí)別的射頻信號(hào)數(shù)據(jù)集

任俊宇; 俞寧寧; 周成偉; 史治國(guó); 陳積明

doi:10.11999/JEIT240804

DroneRFb-DIR: 用于非合作無人機(jī)個(gè)體識(shí)別的射頻信號(hào)數(shù)據(jù)集

doi: 10.11999/JEIT240804 cstr: 32379.14.JEIT240804

任俊宇^{1, 2},
俞寧寧^{1, 2},
周成偉^{1, 2},
史治國(guó)^{1, 4, ,},
陳積明^{2, 3}

1.
浙江大學(xué)信息與電子工程學(xué)院杭州 310027
2.
浙江大學(xué)工業(yè)控制技術(shù)全國(guó)重點(diǎn)實(shí)驗(yàn)室杭州 310027
3.
杭州電子科技大學(xué)自動(dòng)化學(xué)院杭州 310018
4.
浙江大學(xué)金華研究院金華 321037

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(U21A20456, 62271444)，中央高?；究蒲袠I(yè)務(wù)費(fèi)(226-2023-00111, 226-2024-00004)

詳細(xì)信息

作者簡(jiǎn)介:
任俊宇：男，博士生，研究方向?yàn)榉礋o人機(jī)檢測(cè)識(shí)別、信號(hào)估計(jì)等

俞寧寧：男，博士生，研究方向?yàn)榉礋o人機(jī)檢測(cè)、電磁頻譜認(rèn)知、信號(hào)識(shí)別等

周成偉：男，博士，研究員，研究方向?yàn)殛嚵行盘?hào)處理、張量信號(hào)處理、無人機(jī)智能監(jiān)測(cè)技術(shù)等

史治國(guó)：男，博士，教授，研究方向?yàn)樾盘?hào)處理及其定位應(yīng)用、物聯(lián)網(wǎng)等

陳積明：男，博士，教授，研究方向?yàn)榫W(wǎng)絡(luò)優(yōu)化與控制、網(wǎng)絡(luò)系統(tǒng)安全、工業(yè)大數(shù)據(jù)與物聯(lián)網(wǎng)等

通訊作者:
史治國(guó)　shizg@zju.edu.cn

中圖分類號(hào): TN975
計(jì)量
- 文章訪問數(shù): 1322
- HTML全文瀏覽量: 399
- PDF下載量: 303
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2024-09-19
- 修回日期: 2025-02-21
- 網(wǎng)絡(luò)出版日期: 2025-02-26
- 刊出日期: 2025-03-01

DroneRFb-DIR: An RF Signal Dataset for Non-cooperative Drone Individual Identification

REN Junyu^{1, 2},
YU Ningning^{1, 2},
ZHOU Chengwei^{1, 2},
SHI Zhiguo^{1, 4
, ,},
CHEN Jiming^{2, 3}

1.
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
2.
State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China
3.
School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China
4.
Jinhua Institute of Zhejiang University, Jinhua 321037, China

Funds: The National Natural Science Foundation of China (U21A20456, 62271444), The Fundamental Research Funds for Central Universities (226-2023-00111, 226-2024-00004)

摘要

摘要: 無人機(jī)射頻檢測(cè)是實(shí)現(xiàn)非合作無人機(jī)管控的手段之一，而基于射頻信號(hào)的無人機(jī)個(gè)體識(shí)別(DIR)是無人機(jī)檢測(cè)的重要環(huán)節(jié)。鑒于當(dāng)前DIR開源數(shù)據(jù)集缺失，該文公開了一個(gè)名為DroneRFb-DIR的無人機(jī)射頻信號(hào)數(shù)據(jù)集。該數(shù)據(jù)集使用軟件無線電設(shè)備采集無人機(jī)與遙控器間通信的射頻信號(hào)，包含城市場(chǎng)景下的無人機(jī)種類共6類(每類無人機(jī)各包含3架不同個(gè)體)以及1類背景參考信號(hào)。采樣信號(hào)存儲(chǔ)為最原始的I/Q數(shù)據(jù)，每類數(shù)據(jù)包含不少于40個(gè)片段，每個(gè)片段包含不少于4 M個(gè)采樣點(diǎn)。信號(hào)采集范圍為2.4～2.48 GHz，包含無人機(jī)飛控信號(hào)、圖傳信號(hào)以及周圍干擾設(shè)備的信號(hào)。該數(shù)據(jù)集包含詳細(xì)的個(gè)體編號(hào)和視距或非視距場(chǎng)景標(biāo)注，并已劃分訓(xùn)練集與測(cè)試集，以便于用戶進(jìn)行識(shí)別算法驗(yàn)證和性能對(duì)比分析。與此同時(shí)，該文提供了一種基于快速頻率估計(jì)和時(shí)域相關(guān)分析的無人機(jī)個(gè)體識(shí)別方法，并在該數(shù)據(jù)集上驗(yàn)證了所提方法的有效性。
- 無人機(jī)個(gè)體識(shí)別 /
- 頻譜感知 /
- 非合作無人機(jī) /
- 射頻檢測(cè)數(shù)據(jù)集
Abstract: RF-based drone detection is an essential method for managing non-cooperative drones, with Drone Individual Recognition (DIR) via RF signals being a key component in the detection process. Given the current scarcity of DIR datasets, this paper proposes an open-source DroneRFb-DIR dataset for RF-based DIR. The dataset is constructed by capturing RF signals exchanged between drones and their remote controllers using a Software-Defined Radio (SDR). It includes signals from six types of drones, each with three different individuals, as well as background signals from urban environments. The captured signals are stored in raw I/Q format, and each drone type consists of over 40 signal segments, with each segment containing more than 4 million sample points. The RF sampling range spans from 2.4 GHz to 2.48 GHz, covering Flight Control Signals (FCS), Video Transmission Signals (VTS), and interference from surrounding devices. The dataset is annotated with entity identifiers (e.g., drone type and individual) and environmental labels (line-of-sight vs. non-line-of-sight). A DIR method based on fast frequency estimation and time-domain correlation analysis is also proposed and validated using this dataset. Objective: Drones are increasingly used in sectors such as geospatial mapping, aerial photography, traffic monitoring, and disaster relief, playing a significant role in modern industries and daily life. However, the rise in unauthorized drone operations presents serious threats to national security, public safety, and privacy, especially in urban areas. While existing methods emphasize general drone detection and classification, they struggle to distinguish individual drones of the same type, which is crucial for distinguishing friend from foe, analyzing swarm dynamics, and implementing effective countermeasures. This study addresses this gap by introducing the DroneRFb-DIR dataset, a large-scale, open-source RF signal dataset for non-cooperative DIR. Additionally, a novel method based on fast frequency estimation and time-domain correlation analysis is proposed to achieve accurate drone identification in urban environments. Methods: The DroneRFb-DIR dataset is developed using SDR device to capture RF signals in an urban environment with interference from devices like Wi-Fi and Bluetooth. It includes signals from six drone types, each with three individual units, as well as background reference signals. The dataset is collected at an 80 MHz sampling rate in the 2.4～2.48 GHz band and stored in raw I/Q format for detailed analysis. Each signal is annotated with identifiers (e.g., drone type and individual) and scene labels (line-of-sight and non-line-of-sight). For algorithm validation, the dataset is partitioned into training and testing sets. The proposed method consists of three key stages: (1) Signal Detection: A dynamic bandpass or band-stop filter isolates drone control signals from background noise and interference. (2) Frequency Localization: Adaptive filtering and frequency estimation to identify the spectral location of drone signals. (3) Identity Feature Extraction: Correlation analysis extracts identity features from control signal segments to differentiate individual drones, focusing on unique frequency modulation patterns. Results and Discussions: The dataset comprises 4,690 signal segments, each containing with over 4 million sample points. Experiments demonstrated the effectiveness of the proposed method (Table 3), showing high rejection rates of background signals and accurate identification of specific drone types. However, performance varied across drone types due to factors such as signal quality, environmental interference, and control signal characteristics. For instance, drones with low-SNR signals or less distinct frequency modulation patterns posed greater challenges for identification. Despite these difficulties, the method achieved competitive accuracy in identifying individual drones, even in non-line-of-sight conditions. These findings underscore the importance of advanced filtering and feature extraction for robust DIR in complex urban environments. Conclusions: This study addresses the critical need for DIR technologies by introducing the DroneRFb-DIR dataset and a novel identification method. Featuring six drone types, 18 individual drones, and one background signal class, the dataset is the first large-scale open-source resource for non-cooperative DIR in urban scenarios (Table 2). The proposed method effectively separates drone signals from interference and accurately identifies individual drones. Future work will focus on expanding the dataset with more diverse drone types, additional environmental scenarios (e.g., multipath interference and dynamic drone states), and machine learning models for improved recognition. Optimization of non-learning methods will also be explored to enhance feature extraction and identification rates, especially for drones with weaker signal characteristics.
- Drone individual Recognition (DIR) /
- Spectrum sensing /
- Non-cooperative drone /
- RF detection dataset

HTML全文

圖 1 數(shù)據(jù)采集場(chǎng)景

下載: 全尺寸圖片幻燈片

圖 2 DJI Mavic 3 Pro無人機(jī)信號(hào)時(shí)頻圖

下載: 全尺寸圖片幻燈片

圖 3 無人機(jī)圖傳(紅色實(shí)線框)與飛控信號(hào)(藍(lán)色實(shí)線框)特征示意

下載: 全尺寸圖片幻燈片

圖 4 寬帶信號(hào)的檢出流程

下載: 全尺寸圖片幻燈片

圖 5 DJI Mavic 3 Pro的無人機(jī)飛控信號(hào)時(shí)頻圖

下載: 全尺寸圖片幻燈片

圖 6 相鄰兩個(gè)時(shí)間窗FFT譜圖

下載: 全尺寸圖片幻燈片

圖 7 無人機(jī)飛控信號(hào)組成

下載: 全尺寸圖片幻燈片

圖 8 無人機(jī)個(gè)體飛控信號(hào)相關(guān)性曲線

下載: 全尺寸圖片幻燈片

表 1 無人機(jī)探測(cè)手段特點(diǎn)

探測(cè)手段	最大有效距離(m)	原理	缺點(diǎn)
雷達(dá)	8000	微多普勒	無人機(jī)雷達(dá)截面積小，成本高，不適合城市場(chǎng)景
音頻	200	時(shí)頻特征	覆蓋范圍小，受噪聲影響大
視覺	1500	外觀特征和運(yùn)動(dòng)特征	受遮擋、天氣環(huán)境影響大
射頻	5000	通信信道	易受城市環(huán)境下干擾信號(hào)影響

下載: 導(dǎo)出CSV

表 2 個(gè)體標(biāo)簽與型號(hào)對(duì)應(yīng)關(guān)系

個(gè)體標(biāo)簽	型號(hào)
A1, A2, A3	DJI Mavic 3 Pro
B	背景
C1, C2, C3	DJI Mini 2 SE
D1, D2, D3	DJI Mini 4 Pro
E1, E2, E3	DJI Mini 3
F1, F2, F3	DJI Air 3
G1, G2, G3	DJI Air 2S

下載: 導(dǎo)出CSV

表 3 無人機(jī)個(gè)體識(shí)別結(jié)果

種類標(biāo)簽	識(shí)別率(%)
A	63.96
B	100.00
C	60.74
D	29.63
E	68.62
F	37.50
G	67.95

下載: 導(dǎo)出CSV

參考文獻(xiàn)(18)

[1]	SHI Xiufang, YANG Chaoqun, XIE Weige, et al. Anti-drone system with multiple surveillance technologies: Architecture, implementation, and challenges[J]. IEEE Communications Magazine, 2018, 56(4): 68–74. doi: 10.1109/MCOM.2018.1700430.
[2]	陳新穎, 盛敏, 李博, 等. 面向6G的無人機(jī)通信綜述[J]. 電子與信息學(xué)報(bào), 2022, 44(3): 781–789. doi: 10.11999/JEIT210789. CHEN Xinying, SHENG Min, LI Bo, et al. Survey on unmanned aerial vehicle communications for 6G[J]. Journal of Electronics & Information Technology, 2022, 44(3): 781–789. doi: 10.11999/JEIT210789.
[3]	KAUFMANN E, BAUERSFELD L, LOQUERCIO A, et al. Champion-level drone racing using deep reinforcement learning[J]. Nature, 2023, 620(7976): 982–987. doi: 10.1038/s41586-023-06419-4.
[4]	KUNERTOVA D. The war in Ukraine shows the game-changing effect of drones depends on the game[J]. Bulletin of the Atomic Scientists, 2023, 79(2): 95–102. doi: 10.1080/00963402.2023.2178180.
[5]	國(guó)務(wù)院, 中央軍委. 無人駕駛航空器飛行管理暫行條例[EB/OL]. https://www.gov.cn/zhengce/content/202306/content_6888799.htm, 2023. The State Council of the People’s Republic of China, The Central Military Commission of the Communist Party of China. Interim regulations on the management of unmanned aircraft flights[EB/OL]. https://www.gov.cn/zhengce/content/202306/content_6888799.htm, 2023.
[6]	聶偉, 戴琪霏, 楊小龍, 等. 基于多維信號(hào)特征的無人機(jī)探測(cè)識(shí)別方法[J]. 電子與信息學(xué)報(bào), 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.
[7]	SHI Zhiguo, CHANG Xianyu, YANG Chaoqun, et al. An acoustic-based surveillance system for amateur drones detection and localization[J]. IEEE Transactions on Vehicular Technology, 2020, 69(3): 2731–2739. doi: 10.1109/TVT.2020.2964110.
[8]	SI Zheng, LIU Chao, LIU Jianyu, et al. Application of SNNS model based on multi-dimensional attention in drone radio frequency signal classification[C].2024 IEEE International Conference on Acoustics, Speech and Signal Processing, Seoul, Republic of Korea, 2024: 231–235. doi: 10.1109/ICASSP48485.2024.10446694.
[9]	GLüGE S, NYFELER M, AGHAEBRAHIMIAN A, et al. Robust low-cost drone detection and classification using convolutional neural networks in low SNR environments[J]. IEEE Journal of Radio Frequency Identification, 2024, 8: 821–830. doi: 10.1109/JRFID.2024.3487303.
[10]	俞寧寧, 毛盛健, 周成偉, 等. DroneRFa: 用于偵測(cè)低空無人機(jī)的大規(guī)模無人機(jī)射頻信號(hào)數(shù)據(jù)集[J]. 電子與信息學(xué)報(bào), 2024, 46(4): 1147–1156. doi: 10.11999/JEIT230570. YU Ningning, MAO Shengjian, ZHOU Chengwei, et al. DroneRFa: A large-scale dataset of drone radio frequency signals for detecting low-altitude drones[J]. Journal of Electronics & Information Technology, 2024, 46(4): 1147–1156. doi: 10.11999/JEIT230570.
[11]	YU Ningning, WU Jiajun, ZHOU Chengwei, et al. Open set learning for RF-based drone recognition via signal semantics[J]. IEEE Transactions on Information Forensics and Security, 2024, 19: 9894–9909. doi: 10.1109/TIFS.2024.3463535.
[12]	彭鴻飛, 朱鑫潮, 周成偉, 等. 基于靜動(dòng)態(tài)綜合估計(jì)的無人機(jī)蜂群態(tài)勢(shì)感知技術(shù)[J]. 信號(hào)處理, 2024, 40(5): 826–838. doi: 10.16798/j.issn.1003-0530.2024.05.003. PENG Hongfei, ZHU Xinchao, ZHOU Chengwei, et al. UAV swarm situational awareness technology based on static and dynamic comprehensive estimations[J]. Journal of Signal Processing, 2024, 40(5): 826–838. doi: 10.16798/j.issn.1003-0530.2024.05.003.
[13]	ZHOU Chengwei, GU Yujie, SHI Zhiguo, et al. Structured nyquist correlation reconstruction for DOA estimation with sparse arrays[J]. IEEE Transactions on Signal Processing, 2023, 71: 1849–1862. doi: 10.1109/TSP.2023.3251110.
[14]	ZHENG Hang, ZHOU Chengwei, SHI Zhiguo, et al. Coarray tensor direction-of-arrival estimation[J]. IEEE Transactions on Signal Processing, 2023, 71: 1128–1142. doi: 10.1109/TSP.2023.3260559.
[15]	鄭航, 周成偉, 王勇, 等. EMVS互質(zhì)面陣張量波束成形[J]. 信號(hào)處理, 2024, 40(2): 250–262. doi: 10.16798/j.issn.1003-0530.2024.02.003. ZHENG Hang, ZHOU Chengwei, WANG Yong, et al. Tensor beamforming for EMVS coprime planar array[J]. Journal of Signal Processing, 2024, 40(2): 250–262. doi: 10.16798/j.issn.1003-0530.2024.02.003.
[16]	WANG Qiexiang, WANG Longhui, YU Lebin, et al. An ID-based robust identification approach toward multitype noncooperative drones[J]. IEEE Sensors Journal, 2023, 23(9): 10179–10192. doi: 10.1109/JSEN.2023.3259203.
[17]	ZHAO Zheng, S?RKK? S, SJ?LUND J, et al. Probabilistic estimation of instantaneous frequencies of chirp signals[J]. IEEE Transactions on Signal Processing, 2023, 71: 461–476. doi: 10.1109/TSP.2023.3245720.
[18]	KHODARAHMI M and MAIHAMI V. A review on Kalman filter models[J]. Archives of Computational Methods in Engineering, 2023, 30(1): 727–747. doi: 10.1007/s11831-022-09815-7.