Unmanned Aerial Vehicles Detection and Recognition Method Based on Mel Frequency Cepstral Coefficients

NIE Wei; ZHANG Zhongyang; YANG Xiaolong; ZHOU Mu

doi:10.11999/JEIT241111

Volume 47 Issue 4

Apr. 2025

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2025 > 47(4): 1076-1084

NIE Wei, ZHANG Zhongyang, YANG Xiaolong, ZHOU Mu. 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

Citation:

NIE Wei, ZHANG Zhongyang, YANG Xiaolong, ZHOU Mu. 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

Citation:

PDF( 2648 KB)

Unmanned Aerial Vehicles Detection and Recognition Method Based on Mel Frequency Cepstral Coefficients

doi: 10.11999/JEIT241111 cstr: 32379.14.JEIT241111

School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

Funds: The National Natural Science Foundation of China (62101085), The Science and Technology Research Program of Chongqing Municipal Education Commission (KJQN202400647), The Science and Technology Project of Ministry of Public Security (2024JSZ16), Chongqing Technology Innovation and Application Development Special Key Project (CSTB2024TIAD-KPX0104)

Received Date: 2024-12-17
Rev Recd Date: 2025-03-14

Available Online: 2025-03-25

Publish Date: 2025-04-01

Abstract

Abstract

Objective The widespread adoption of Unmanned Aerial Vehicles (UAVs) across civilian and military domains has introduced significant privacy and security challenges. Robust UAV identification and localization technologies are essential to address these concerns. While Radio Frequency Fingerprint Identification (RFFI) techniques based on deep learning show promise, their practical deployment is hindered by excessive model complexity, prolonged training periods, and limited generalization capabilities. This research presents a novel UAV identification and localization methodology utilizing Mel-Frequency Cepstral Coefficients (MFCC) and Gated Recurrent Unit (GRU) architecture that achieves superior accuracy with enhanced computational efficiency. Methods The proposed framework comprises several key components: (1) UAV video transmission signal acquisition via USRP N210 software-defined radio platform; (2) MFCC feature extraction to characterize distinctive radio frequency fingerprints; (3) GRU-based classification for UAV identification; and (4) Regularized Orthogonal Matching Pursuit (ROMP) algorithm implementation for three-dimensional localization parameter estimation. Comprehensive experimental evaluation assessed classification accuracy, computational complexity, training efficiency, and localization precision. Results and Discussions Experimental validation demonstrates that the proposed methodology achieves 98% UAV identification accuracy. The implemented GRU architecture contains only 1.6 k parameters and requires merely 9 seconds for training completion, representing significant reductions in model complexity and computational overhead (Table 2). For localization tasks, the system achieves three-dimensional positioning error below 1 meter. Robustness assessment through classification tests on 10 identical wireless modules from the same manufacturer at varying distances (1 m, 2 m, 3 m, and 5 m) yielded identification accuracies of 100%, 98%, 98%, and 99%, respectively (Table 3). These results confirm the method’s exceptional performance in both identification and localization applications. Conclusions This research introduces an efficient and accurate UAV identification and localization methodology based on MFCC features and GRU architecture. The approach substantially reduces model complexity and training requirements while maintaining high identification accuracy and precise localization capabilities. Experimental validation confirms its feasibility and robustness for practical deployment. Future research directions include algorithm optimization for real-time processing and extension to diverse UAV platforms and operational environments.

FullText(HTML)

References(18)

References

[1]	DING Siyi, GUO Xiao, PENG Ti, et al. Drone detection and tracking system based on fused acoustical and optical approaches[J]. Advanced Intelligent Systems, 2023, 5(10): 2300251. doi: 10.1002/aisy.202300251.
[2]	MAKSYMIUK R, PŁOTKA M, ABRATKIEWICZ K, et al. 5G network-based passive radar for drone detection[C]. Proceedings of 2023 24th International Radar Symposium (IRS), Berlin, Germany, 2023: 1–10. doi: 10.23919/IRS57608.2023.10172437.
[3]	ZHANG Junqing, WOODS R, SANDELL M, et al. Radio frequency fingerprint identification for narrowband systems, modelling and classification[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 3974–3987. doi: 10.1109/TIFS.2021.3088008.
[4]	HE Jiashuo, HUANG Sai, YANG Zheng, et al. Channel-agnostic radio frequency fingerprint identification using spectral quotient constellation errors[J]. IEEE Transactions on Wireless Communications, 2024, 23(1): 158–170. doi: 10.1109/TWC.2023.3276519.
[5]	LI Dingzhao, QI Jie, HONG Shaohua, et al. A class-incremental approach with self-training and prototype augmentation for specific emitter identification[J]. IEEE Transactions on Information Forensics and Security, 2024, 19: 1714–1727. doi: 10.1109/TIFS.2023.3343193.
[6]	GU Xiaolin, WU Wenjia, ZHOU Yusen, et al. TEA-RFFI: Temperature adjusted radio frequency fingerprint-based smartphone identification[J]. Computer Networks, 2024, 238: 110115. doi: 10.1016/j.comnet.2023.110115.
[7]	张晔. 基于深度学习的射频指纹识别系统设计与实现[D]. [硕士论文], 中国科学院大学(中国科学院国家空间科学中心), 2021. doi: 10.27562/d.cnki.gkyyz.2021.000024. ZHANG Ye. Design and implementation of radio frequency fingerprint identification system based on deep learning[D]. [Master dissertation], University of Chinese of Academy of Science (National Space Science Center, Chinese Academy of Sciences), 2021. doi: 10.27562/d.cnki.gkyyz.2021.000024.
[8]	王检, 张邦宁, 魏国峰, 等. 基于Welch功率谱和卷积神经网络的通信辐射源个体识别[J]. 电讯技术, 2021, 61(10): 1197–1204. doi: 10.3969/j.issn.1001-893x.2021.10.001. WANG Jian, ZHANG Bangning, WEI Guofeng, et al. Communication transmitter individual identification based on Welch power spectrum and convolution neural network[J]. Telecommunication Engineering, 2021, 61(10): 1197–1204. doi: 10.3969/j.issn.1001-893x.2021.10.001.
[9]	YANG K, KANG J, JANG J, et al. Multimodal sparse representation-based classification scheme for RF fingerprinting[J]. IEEE Communications Letters, 2019, 23(5): 867–870. doi: 10.1109/LCOMM.2019.2905205.
[10]	LIN Yun, TU Ya, DOU Zheng, et al. Contour Stella image and deep learning for signal recognition in the physical layer[J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 7(1): 34–46. doi: 10.1109/TCCN.2020.3024610.
[11]	凌逆战. 梅尔倒谱系数(MFCC)的原理讲解及python实现[EB/OL]. https://www.cnblogs.com/LXP-Never/p/10918590.html, 2024. LING Nizhan. Explanation of the principle and python implementation of the Mel Frequency Cepstral Coefficients (MFCC)[EB/OL]. https://www.cnblogs.com/LXP-Never/p/10918590.html, 2024.
[12]	张亚楠. 语音信号处理基础(十一)——梅尔倒谱系数的提取[EB/OL]. https://blog.csdn.net/qq_40644291/article/details/104417894, 2024. ZHANG Yanan. Fundamentals of speech signal processing (XI) - extraction of Mel frequency cepstral coefficients[EB/OL]. https://blog.csdn.net/qq_40644291/article/details/104417894, 2024.
[13]	何正祥, 彭平安, 廖智勤. 基于梅尔倒谱系数的矿山复杂微震信号自动识别分类方法[J]. 中国安全生产科学技术, 2018, 14(12): 41–47. doi: 10.11731/j.issn.1673-193x.2018.12.006. HE Zhengxiang, PENG Pingan, and LIAO Zhiqin. An automatic identification and classification method of complex microseismic signals in mines based on Mel-frequency cepstral coefficients[J]. Journal of Safety Science and Technology, 2018, 14(12): 41–47. doi: 10.11731/j.issn.1673-193x.2018.12.006.
[14]	CHO K, VAN MERRIENBOER B, BAHDANAU D, et al. On the properties of neural machine translation: Encoder-Decoder approaches[C]. SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, Qatar, 2014: 103–111. doi: 10.3115/v1/W14-4012.
[15]	生瓜蛋子. 深度探索: 机器学习门控循环单元(GRU)算法原理及其应用[EB/OL]. https://blog.csdn.net/qq_51320133/article/details/137629302, 2024. Raw Melon Eggs. Deep exploration: Principles of the machine learning gated recurrent unit (GRU) algorithm and its applications[EB/OL]. https://blog.csdn.net/qq_51320133/article/details/137629302, 2024.
[16]	COLAH. Understanding LSTM networks[EB/OL]. http://colah.github.io/posts/2015-08-Understanding-LSTMs/, 2015.
[17]	NEEDELL D and VERSHYNIN R. Greedy signal recovery and un-certainty principles[C]. The Conference on Computational Imaging, San Jose, USA, 2008: 68140J. doi: 10.1117/12.776996.
[18]	NEEDELL D and VERSHYNIN R. Uniform uncertainty principle and signal recovery via regularized orthogonal matching pursuit[J]. Foundations of Computational Mathematics, 2009, 9(3): 317–334. doi: 10.1007/s10208-008-9031-3.