基于深度卷积神经网络的大气湍流强度估算  

Atmospheric Turbulence Intensity Estimation Based on Deep Convolutional Neural Networks

作　　者：马圣杰 郝士琦 赵青松 王勇[1,2] 王磊 Ma Shengjie;Hao Shiqi;Zhao Qingsong;Wang Yong;Wang Lei(State Key Laboratory of Pulse Power Laser Technology,National University of Defense Technology,Hefei Anhui 230037 China;AnHui Province Key Laboratory of Electronic Restriction,Hefei Anhui 230037 China)

机构地区：[1]国防科技大学脉冲功率激光技术国家重点实验室,安徽合肥230037 [2]电子制约技术安徽省重点实验室,安徽合肥230037

出　　处：《中国激光》2021年第4期272-281,共10页Chinese Journal of Lasers

基　　金：国家自然科学基金(61571446,61671454)。

摘　　要：提出了一种基于深度卷积神经网络估算大气湍流折射率结构常数C_(n)^(2)的方法。将湍流影响下的高斯光束光斑图像作为神经网络的输入,利用深度卷积神经网络提取图像的特征信息,得到C_(n)^(2)大小,并采用平均绝对误差、平均相对误差、均方根方差和相关系数四个统计量来衡量模型的估算效果。结果表明,该模型能够根据湍流影响下的高斯光束光斑图像对C_(n)^(2)进行估算,当迭代500次时,相关系数为99.84%,各项误差均在2%左右。该模型在大气湍流特性分析及大气湍流强度估算等领域有一定应用价值。Objective Atmospheric turbulence causes a random fluctuation in the refractive index.When a laser propagates in atmospheric turbulence,the light intensity fluctuation phenomenon during beam propagation occurs,seriously influencing laser propagation.Because different atmospheric turbulence intensities have different effects on laser propagation,it is significantly important to estimate the atmospheric turbulence intensity.In general,the refractive index structural constant C_(n)^(2) of the atmospheric turbulence is used to measure the turbulence intensity.The value of C_(n)^(2) is directly proportional to the impact of turbulence on laser propagation.Traditional estimation methods include instrument measurement and model estimation.The instrument measurement allows building an experimental platform to directly measure C_(n)^(2),in contrast,the model estimation allows obtaining C_(n)^(2) by measuring other atmospheric parameters and establishing a model.In recent years,deep learning has allowed achieving good results in the field of image processing,which can extract the feature information of an image layer by layer.This study proposes a method to estimate the refractive index structural constant C_(n)^(2) of atmospheric turbulence based on deep convolutional neural networks.The neural network model is built to extract the features of the light spot images under the influence of atmospheric turbulence and the turbulence information is obtained to estimate the turbulence intensity.Results and Discussions In this study,a traditional AlexNet network model and a VGG16 deep convolutional neural network model are established.VGG16 is optimized on the basis of the traditional convolutional neural network,which increases the layer numbers of the network,reduces the size of the convolution kernel,and has more advantages on feature information extraction of images.The light spot images at different moments under the same turbulence intensity are selected as the inputs of the neural network to verify the feasibility of the a

关 键 词：大气光学 大气湍流 折射率结构常数 深度卷积神经网络 湍流强度估算 

分 类 号：O533[理学—等离子体物理]