用户名: 密码: 验证码:
基于卷积神经网络的大气中光路气流扰动实验研究
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Atmospheric Optical Path Airflow Disturbance Analysis Method Based on Convolutional Neural Network
  • 作者:刘一琛 ; 吴侃 ; 邱高峰 ; 陈建平
  • 英文作者:Liu Yichen;Wu Kan;Qiu Gaofeng;Chen Jianping;State Key Laboratory of Advanced Optical Communication Systems and Networks,Shanghai Jiao Tong University;
  • 关键词:大气光学 ; 空间光学 ; 气流扰动 ; 卷积神经网络 ; 深度学习
  • 英文关键词:atmospheric optics;;free space optics;;air flow disturbance;;convolution neural network;;deep learning
  • 中文刊名:光学学报
  • 英文刊名:Acta Optica Sinica
  • 机构:上海交通大学区域光纤通信网与新型光通信系统国家重点实验室;
  • 出版日期:2019-04-16 17:45
  • 出版单位:光学学报
  • 年:2019
  • 期:08
  • 基金:国家自然科学基金(61505105,61875122)
  • 语种:中文;
  • 页:16-26
  • 页数:11
  • CN:31-1252/O4
  • ISSN:0253-2239
  • 分类号:TP183
摘要
提出了一种基于激光光斑畸变和卷积神经网络(CNN)的光路气流扰动研究方案。利用CNN对激光光束在空间传播中受到气流扰动后的光斑畸变进行学习,得到光束传播路径上的气流扰动情况。实验表明,训练得到的评估参数与由风速仪测得的光路中的气流扰动(风速)具有强相关性。本方案提供了一种短距离、快速、低成本的气流扰动分析手段。
        A method to investigate optical path turbulence based on laser spot distortion and a convolutional neural network(CNN) is proposed. Utilizing the CNN, we evaluated the spot distortion of laser beams resulting from airflow disturbance in space propagation. As a result, details of turbulence on the beam propagation path can be obtained. Experimental results demonstrate a high correlation between the evaluation parameter and the turbulent intensity(wind speed) measured by an anemoscope. The proposed method provides a turbulence analysis with short distance, high speed, and low cost.
引文
[1] Bekkali A,Ben Naila C,Kazaura K,et al.Transmission analysis of OFDM-based wireless services over turbulent radio-on-FSO links modeled by gamma-gamma distribution[J].IEEE Photonics Journal,2010,2(3):510-520.
    [2] Gappmair W,Hranilovic S,Leitgeb E.Performance of PPM on terrestrial FSO links with turbulence and pointing errors[J].IEEE Communications Letters,2010,14(5):468-470.
    [3] Dat P T,Bekkali A,Kazaura K,et al.Studies on characterizing the transmission of RF signals over a turbulent FSO link[J].Optics Express,2009,17(10):7731-7743.
    [4] Dirkx D,Noomen R,Prochazka I,et al.Influence of atmospheric turbulence on planetary transceiver laser ranging[J].Advances in Space Research,2014,54(11):2349-2370.
    [5] Wang F,Toselli I,Li J,et al.Measuring anisotropy ellipse of atmospheric turbulence by intensity correlations of laser light[J].Optics Letters,2017,42(6):1129-1132.
    [6] Hughes A J,Pike E R.Remote measurement of wind speed by laser Doppler systems[J].Applied Optics,1973,12(3):597-601.
    [7] Jackson D A,Paul D M.Measurement of hypersonic velocities and turbulence by direct spectral analysis of Doppler shifted laser light[J].Physics Letters A,1970,32(2):77-78.
    [8] Banakh V A,Razenkov I A.Refractive turbulence strength estimation based on the laser echo signal amplification effect[J].Optics Letters,2016,41(19):4429-4432.
    [9] Tunick A.Statistical analysis of optical turbulence intensity over a 2.33 km propagation path[J].Optics Express,2007,15(7):3619-3628.
    [10] Chen Y D,Zhou B,Zhang C,et al.Effect on operating distance of laser rangefinders with deviation between axis of emitting and receiving in turbulent atmosphere[J].Proceedings of SPIE,2016,10153:101530Y.
    [11] Antar G.Visible light scattering to measure small scale turbulence[J].Review of Scientific Instruments,2000,71(1):113-117.
    [12] Wang Y R,Mei H P.Experimental investigation on retro-reflective laser spot imaging and intensity fluctuations in turbulent atmosphere[J].Journal of Atmospheric and Environmental Optics,2018,13(4):241-249.王钰茹,梅海平.湍流大气折返路径成像光斑与光强起伏实验研究[J].大气与环境光学学报,2018,13(4):241-249.
    [13] Zhang S D,Sun H H.High precision method of long-ranged laser spot position measurement[J].Chinese Journal of Lasers,2012,39(7):0708003.张少迪,孙宏海.远距离激光光斑位置高精度测量方法[J].中国激光,2012,39(7):0708003.
    [14] Huang J,Zhang P,Deng K,et al.Boundary parameters of adaptive optical system in satellite to ground coherent laser communication system[J].Optics and Precision Engineering,2014,22(5):1204-1211.黄健,张鹏,邓科,等.星地相干激光通信中的自适应光学系统边界参数设计[J].光学精密工程,2014,22(5):1204-1211.
    [15] Andrews L C,Phillips R L.Laser beam propagation through random media[M].Bellingham:SPIE,2005.
    [16] Fu Q,Jiang H L,Wang X M.Study of laser transmission characteristics in atmosphere by simulation[J].Journal of Air Force Engineering University(Natural Science Edition),2011,12(2):57-61,80.付强,姜会林,王晓曼.激光在大气中传输特性的仿真研究[J].空军工程大学学报(自然科学版),2011,12(2):57-61,80.
    [17] Portes de Albuquerque M,Esquef I A,Gesualdi Mello A R,et al.Image thresholding using Tsallis entropy[J].Pattern Recognition Letters,2004,25(9):1059-1065.
    [18] Ojala T,Pietik?inen M,M?enp?? T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
    [19] Mukherjee J,Mitra S K.Image resizing in the compressed domain using subband DCT[J].IEEE Transactions on Circuits and Systems for Video Technology,2002,12(7):620-627.
    [20] Abadi M,Barham P,Chen J,et al.TensorFlow:a system for large-scale machine learning[C]// 12th USENIX Conference on Operating Systems Design and Implementation,November 2-4,2016,Savannah,GA,USA.CA,USA:USENIX Association Berkeley,2016,16:265-283.
    [21] Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[C]//25th International Conference on Neural Information Processing Systems,December 3-6,2012,Lake Tahoe,Nevada.USA:Curran Associates Inc.,2012,1:1097-1105.
    [22] Schuldt C,Laptev I,Caputo B.Recognizing human actions:a local SVM approach[C]//Proceedings of the 17th International Conference on Pattern Recognition,August 26-26,2004,Cambridge,UK.New York:IEEE,2004:32-36.
    [23] Lü J,Zhu W Y,Qing C,et al.Estimation of atmospheric optical turbulence at near surface of Chengdu with support vector machine[J].Chinese Journal of Lasers,2018,45(4):0404001.吕洁,朱文越,青春,等.支持向量机估算成都近地面大气光学湍流[J].中国激光,2018,45(4):0404001.
    [24] Wang L,Gjoreskia H,Murao K,et al.Summary of the Sussex-Huawei locomotion-transportation recognition challenge[C]//2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers,October 8-12,2018,Singapore.New York:ACM,2018:1521-1530.
    [25] Srivastava N,Hinton G,Krizhevsky A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958.
    [26] Schaffer C.Overfitting avoidance as bias[J].Machine Learning,1993,10(2):153-178.
    [27] China Meteorological Administration.Classification of wind scale[EB/OL].(2018-07-06)[2019-02-25].http://www.cma.gov.cn/2011xzt/2018zt/20100728/2010072806/201807/t20180706_472642.html.中国气象局.风力的等级划分[EB/OL].(2018-07-06)[2019-02-25].http://www.cma.gov.cn/2011xzt/2018zt/20100728/2010072806/201807/t20180706_472642.html.
    [28] Benesty J,Chen J D,Huang Y T,et al.Pearson correlation coefficient[M]//Cohen I,Huang Y T,Chen J D,et al.Noise reduction in speech processing.Berlin,Heidelberg:Springer,2009:1-4.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700