计算机科学 ›› 2021, Vol. 48 ›› Issue (7): 225-232.doi: 10.11896/jsjkx.200500091

• 计算机图形学&多媒体 • 上一篇    下一篇

基于深度学习的无人机声音识别算法

徐浩, 刘岳镭   

  1. 长安大学电子与控制工程学院 西安710016
  • 收稿日期:2020-05-20 修回日期:2020-08-23 出版日期:2021-07-15 发布日期:2021-07-02
  • 通讯作者: 刘岳镭(276945401@qq.com)

UAV Sound Recognition Algorithm Based on Deep Learning

XU Hao, LIU Yue-lei   

  1. School of Electronics and Control Engineering,Chang’ an University,Xi’ an 710016,China
  • Received:2020-05-20 Revised:2020-08-23 Online:2021-07-15 Published:2021-07-02
  • About author:XU Hao,born in 1998,undergraduate.His main research interests include deep learning and industrial automation.(2017900299@chd.edu.cn)
    LIU Yue-lei,born in 1986,Ph.D,lectu-rer.His main research interests include intelligent optimization algorithm and deep learning.

摘要: 深度学习在图像识别和声音处理方面已经展现了它优越的性能和广阔的发展前景,对于在禁飞区设立的无人机侦测系统,使用深度学习的方法判断无人机的声音信号具有一定的意义。为了获得更优的侦测效果,首先列举了目前具有代表性的特征提取和分类方法,并分析其优缺点;然后提出了一种扩大可用样本数量的数据处理方式,同时在实验中使用不同组合的深度学习网络训练样本;最后通过混淆矩阵法,针对不同信噪比模型、滤波下限、拟合程度、神经网络组合和跨型号识别的实验效果进行评价。实验结果表明,适当地降低训练样本中的无人机声强可以增大系统的识别距离;使用MFCC提取声音特征,通过全连神经网络进行分类的样本识别的半径更远,误判率更低。

关键词: 混淆矩阵, 深度学习, 声音识别, 无人机

Abstract: Deep learning has demonstrated its superior performance and broad development prospect in image recognition and sound processing.It is of certain significance for the UAV detection system established in no-fly zone to use deep learning method to judge the sound signal of UAV.In order to obtain better detection effect,the representative feature extraction and classification methods are listed at first,and their advantages and disadvantages are analyzed.Then,a method of data processing is proposed to expand the number of available samples.At the same time,different combinations of deep learning network training samples are used in the experiment.Finally,the confounding matrix method is used to evaluate the experimental results of different SNR models,filtering limits,fitting degrees,neural network combinations and cross-model recognition.The results show that reducing the sound intensity of the UAV can improve the recognition distance of the system.By using MFCC to extract the sound features,the samples classified by the fully connected neural network have a longer identification radius and a lower misjudgment rate.

Key words: Deep learning, Obfuscation matrix, Sound detection, Unmanned aerial vehicle

中图分类号: 

  • TP391
[1]DARIO F,ROBERT J.Science,Technology and the Future of Small Autonomous Drones[J].Nature,2015,521(7553):460-466.
[2]HASSANALIAN M,ABDELKEFI A.Classifications,Applications,and Design Challenges of Drones:A Review[J].Progress in Aerospace Sciences,2017,91:99-131.
[3]COLOMINA I,MOLINA P.Unmanned Aerial Systems for Photogrammetry and Remote Sensing:A Review[J].Isprs Journal of Photogrammetry and Remote Sensing,2014,92:79-97.
[4]MILAN E,ENRICO N,KAUSHIK R,et al.Help from the Sky:Leveraging UAVs for Disaster Management[J].IEEE Pervasive Computing,2017,16(1):24-32.
[5]HUTTUNEN M.Civil Unmanned Aircraft Systems and Security:The European Approach[J].Journal of Transportation Security,2019,12(3):83-101.
[6]SHI X F,YANG C Q,XIE W G,et al.Anti-drone system with multiple surveillance technologies:Architecture,implementation,and challenges[J].IEEE Communications Magazine,2018,9(1):68-74.
[7]LI Q Z,XIONG R R,WANG R P,et al.Research on real-time UAV recognition method based on SSD Algorithm[J].Ship Electronic Engineering,2019,39(5):30-35.
[8]ANDREA B,FEDERICA M,EMILIANO P,et al.Drone detection by acoustic signature identification[J].Electronic Imaging,2017,10(1):60-64.
[9]HUANG G B,ZHOU H M,DING X J,et al.Exterme Learning Machine for Regression and Multiclass Classification[J].System Man and Cybernetics,2012,42(2):513-529.
[10]KAROL J P.Environmental Sound Classification with Convolutional Neural Networks[C]//2015 IEEE 25th International Workshop on Machine Learning for Signal Processing(MLSP).2015:1-6.
[11]KHAN S A,ANIL S T,JAGANNATH H N,et al.A Unique Approach in Text Independent Speaker Recognition Using MFCC Feature Sets and Probabilistic Neural Network[C]//2015 EighthInternational Conference on Advances in Pattern Recognition(ICAPR).2015:1-6.
[12]WANG R P,FANG Y,CHEN D L,et al.Vehicle abnormalsound Recognition based on wavelet packet FBank Spectrogram and CNN[J].Journal of Congqing Uinversity of Technology(Natural Science),2020,34(7):1-9.
[13]HARSHITA G,DIVYA G.LPC and LPCC Method of Feature Extracion in Speech Recognition System[C]//2015 Internatio-nal Conference-Cloud System and Big Data Engineering.2015:498-502.
[14]MUHAMMAD Z A,ZEESHAN K,ABBAS J.Machine Lear-ning Inspired Sound-Based Amateur Drone Detection for Public Safety Applications[J].IEEE Transactions on Vehicular Technology,2019,68(3):2526-2534.
[15]SAHIDULLAH M,GOUTAM S.Design,Analysis and Experimental Evaluation of Block Based Transformation in MFCC Computation for Speaker Recognition[J].Speech Communication,2012,54(4):543-565.
[16]CHEN T,AO M Y,CHEN H Z.Study of speech recognitiontechnology based on MFCC and SVM[J].Journal of Guangxi Vocational and Technical College,2010,3(5):1-4.
[17]WASEEM R,WANG Z H.Deep Convolutional Neural Net-works for Image Classification:A Comprehensive Review[J].Neural Computation,2017,29(9):2352-2449.
[18]MATTHIAS H,MAKSYM A,JULIAN B.Why ReLU Net-works Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2019:41-50.
[19]DARCH J,MILNER B,VASEGHI S.MAP prediction of formant frequencies and voicing class from MFCC vectors in noise[J].Speech Communication,2006,6(48):1556-1572.
[20]HE K M,SUN J.Convolutional neural networks at constrained time cost[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2015:5353-5360.
[21]DENG X Y,LIU Q,DENG Y,et al.An Improved Method to Construct Basic Probability Assignment Based on the Confusion Matrix for Classification Problem[J].Information Sciences,2016,340:250-261.
[22]SIRANI M P,LIU J H.Complexity Reduction,Self/Complete Recursive,Radix-2 DCT I/IV Algorithms[J].Journal of Computational and Applied Mathematics,2020,379:1-16.
[23]GU S S,DING L,YANG Y,et al.A New Deep Learning MethodBased on AlexNet Model and SSD Model for Tennis Ball Recognition[C]//2017 IEEE 10th International Workshop on Computational Intelligence and Applications (IWCIA).2017:159-164.
[1] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[2] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[3] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[4] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[5] 蹇奇芮, 陈泽茂, 武晓康.
面向无人机通信的认证和密钥协商协议
Authentication and Key Agreement Protocol for UAV Communication
计算机科学, 2022, 49(8): 306-313. https://doi.org/10.11896/jsjkx.220200098
[6] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[7] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[8] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[9] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[10] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[11] 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫.
小样本雷达辐射源识别的深度学习方法综述
Survey of Deep Learning for Radar Emitter Identification Based on Small Sample
计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[12] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[13] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[14] 王君锋, 刘凡, 杨赛, 吕坦悦, 陈峙宇, 许峰.
基于多源迁移学习的大坝裂缝检测
Dam Crack Detection Based on Multi-source Transfer Learning
计算机科学, 2022, 49(6A): 319-324. https://doi.org/10.11896/jsjkx.210500124
[15] 楚玉春, 龚航, 王学芳, 刘培顺.
基于YOLOv4的目标检测知识蒸馏算法研究
Study on Knowledge Distillation of Target Detection Algorithm Based on YOLOv4
计算机科学, 2022, 49(6A): 337-344. https://doi.org/10.11896/jsjkx.210600204
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!