• <tr id="yyy80"></tr>
  • <sup id="yyy80"></sup>
  • <tfoot id="yyy80"><noscript id="yyy80"></noscript></tfoot>
  • 99热精品在线国产_美女午夜性视频免费_国产精品国产高清国产av_av欧美777_自拍偷自拍亚洲精品老妇_亚洲熟女精品中文字幕_www日本黄色视频网_国产精品野战在线观看 ?

    Algorithm Development of Cloud Removal from Solar Images Based on Pix2Pix Network

    2022-08-24 03:30:10XianWuWeiSongXukunZhangGanghuaLinHaiminWangandYuanyongDeng
    Computers Materials&Continua 2022年5期

    Xian Wu,Wei Song,2,3,*,Xukun Zhang,Ganghua Lin,Haimin Wang and Yuanyong Deng

    1School of Information Engineering,Minzu University of China,Beijing,100081,China

    2Key Laboratory of Solar Activity,Chinese Academy of Sciences(KLSA,CAS),Beijing,100101,China

    3National Language Resource Monitoring and Research Center of Minority Languages,Minzu University of China,Beijing,100081,China

    4National Astronomical Observatories,Chinese Academy of Sciences(NAOC,CAS),Beijing,100101,China

    5Center for Solar-Terrestrial Research,New Jersey Institute of Technology,University Heights,Newark,07102-1982,USA

    6Institute for Space Weather Sciences,New Jersey Institute of Technology,University Heights,Newark,07102-1982,USA

    7Big Bear Solar Observatory,New Jersey Institute of Technology,40386,North Shore Lane,Big Bear City,92314-9672,USA

    Abstract: Sky clouds affect solar observations significantly.Their shadows obscure the details of solar features in observed images.Cloud-covered solar images are difficult to be used for further research without pre-processing.In this paper, the solar image cloud removing problem is converted to an image-to-image translation problem, with a used algorithm of the Pixel to Pixel Network (Pix2Pix), which generates a cloudless solar image without relying on the physical scattering model.Pix2Pix is consists of a generator and a discriminator.The generator is a well-designed U-Net.The discriminator uses PatchGAN structure to improve the details of the generated solar image,which guides the generator to create a pseudo realistic solar image.The image generation model and the training process are optimized, and the generator is jointly trained with the discriminator.So the generation model which can stably generate cloudless solar image is obtained.Extensive experiment results on Huairou Solar Observing Station,National Astronomical Observatories,and Chinese Academy of Sciences(HSOS,NAOC and CAS)datasets show that Pix2Pix is superior to the traditional methods based on physical prior knowledge in peak signal-to-noise ratio,structural similarity,perceptual index,and subjective visual effect.The result of the PSNR,SSIM and PI are 27.2121 dB,0.8601 and 3.3341.

    Keywords: Pix2Pix;solar image;cloud removal

    1 Introduction

    The key to the research of the field of solar physics is to study the solar image to understand the structure and evolution of solar activity.Since the 1960s, observatories around the world have accumulated a large number of solar image data by monitoring solar activity.However, researchers are facing many difficulties in analyzing these images.Many of the observed images are obscured by clouds.For example, at the Big Bear Solar Observatory (BBSO) in California, USA, and the days that the observations were affected by clouds(may be from just a few images to large portion of the images during the day) occupy 55% of total days based on the site survey of the Global Oscillation Network Group(GONG)[1].At other Observatories in the world,the percentage may be higher.In these days, instruments work normally; however, if cloud cover the Sun, their shadows will degrade the observed images.Therefore,it is of great significance for all ground-based observation stations to remove the contamination of cloud on the full-disk solar images[2].Removing the effects of the clouds from the affected solar images becomes an urgent problem.As a key station in the world,the Halpha images of the solar chromosphere taken by Huairou Solar Observing Station (HSOS) provide ideal information for the detailed study of the subtle structure of the sun.There are some cloud-covered full disk images and normal full-disk images,which were observed by the HSOS(Fig.1).Therefore,the research object is combined with the deep learning method,and use Pixel to Pixel network to get more cloudless full-disk Halpha images from the cloud-covered full-disk Halpha images.

    Figure 1:The top shows cloud-covered full-disk images and the bottom shows cloudless full-disk images,which were observed by the Huairou Solar Observing Station(HSOS)in 2011

    The contributions of our work are as follows:

    New method on cloud removal.Pix2Pix [3] is used for image cloud removal, which does not rely on the physical scattering model,while adopts the alternative image-to-image translation proposed in 2017.

    U-Net Generator.Inspired by the global-first property of visual perception,the embedded U-Net Generator are designed to produce images with more details.

    A joint training scheme.A joint training scheme is developed for updating the U-Net Generator through reasonably combining two kinds of loss functions.

    The Perceptual Index(PI).PI is introduced for quantitative evaluation from the perceptual perspective.In addition,extensive experiments on solar dataset indicate that Pix2Pix performs favorably against the state-of-the-art methods.Especially,results are outstanding in visual perception.

    The rest of the paper is structured as:Section 2 discusses the relevant work of processing solar images by traditional method and deep learning.Section 3 explains the image generation algorithm based on the Pix2Pix network,describes the process steps of the overall framework of the algorithm.Section 3 also gives the network structure diagram and loss function.Section 4 first explains how to generate training set and test set,and then compares and analyzes the effects of different modules in the algorithm presented on model performance.Finally,a large number of comparative experiments are carried out to analyze and evaluate the effectiveness of the proposed algorithm.The evaluation mainly starts from two aspects:subjective visual effect and objective evaluation index.Finally, the conclusion of the article will be presented.

    2 Related Work

    2.1 The Traditional Method–DCP

    Early cloud removal methods are mostly prior-based methods, and they can achieve a good cloud removal effect to a certain extent.Dark channel prior(DCP [4]) method,which estimates the transmission map by investigating the dark channel prior.Hu[5]propose a two-stage haze and thin cloud removal method based on homomorphic filtering and sphere model improved dark channel prior.Xu [6] propose a fast haze removal algorithm based on fast bilateral filtering combined with dark colors prior.Xu[7]propose a method based on signal transmission and spectral mixture analysis for pixel correction.HoanN[8]propose a cloud removal of remote sensing algorithm image based on multi-output support vector regression.Most of these approaches depend on the physical scattering model[9],which is formulated as Eqs.(1):

    whereIis the observed hazy image,Jis the scene radiance,tis the transmission map,Ais the atmospheric light andzis the pixel location.The solution of the cloudless image depends on the estimation of the atmospheric light and the transmission map.

    DCP method on Fig.2a produces a cloudless image with rich details compared with DCP method used on Fig.2c.Therefore,the prior may be easily violated in practice,which leads to an inaccurate estimation of transmission map so that the quality of the cloud removal image is not desirable.

    Figure 2:Examples of DCP method used on different images.(a) is the forest image affected by the cloud.(c) is the full disk solar image similarly affected.(b) and (d) are DCP processed images respectively

    2.2 Deep Learning-Generative Adversarial Network

    In recent years,researchers in the field of solar physics have gradually begun to explore the use of deep learning[10]to analyze and process solar activity observation data.The study of GAN[11]has made great progress.GAN is widely used in computer vision.In particular,GAN has achieved good results in image generation.

    Densely Connected Pyramid Dehazing Network(DCPDN)[12]implements GAN on image cloud removal which learns transmission map and atmospheric light simultaneously in the generators by optimizing the final image cloud removal performance for cloudless images.Zhang et al.[13]proposed a real-time image processing system for detecting and removing cloud shadows on Halpha full-disk solar.Luo [14] identified that heavy cloud covered images by calculating the ratio of major and minor axes of a fitted ellipse.Sun[15]proposed the Cloud-Aware Generative Network.The network consists of two stages:the first is a recurrent convolution network for potential cloud region detection and the second is an auto encoder for cloud removal.Yang [16] proposed the disentangled cloud removal network,which uses unpaired supervision.The network proposed by Yang[16]contains three generators:the generator for the cloudless image, the generator for the atmospheric light, and the generator for transmission map.Zi[17]proposed a method to remove thin cloud from multispectral images,which combines the traditional method with the deep learning method.Firstly,Convolution Neural Network is used to estimate the thickness of thin cloud in different bands.Then, according to the traditional thin cloud imaging model, the thin cloud thickness image is subtracted from the cloud image to get a clear cloud image.DehazeGAN [18] draws lessons from the differential programming to draw lessons from GAN for simultaneous estimations of the atmospheric light and the transmission map.The use of GAN in image cloud removal task is still in the beginning.The current cloud removal methods via GAN all depend on the physical scattering model.Through the research on the development of GAN, it shows that CycleGAN realizes the transformation of unmatched data image.The image training set does not need paired data,so it is widely used.But the training set does not match,it can’t be trained in absolute mapping relationship,only the real mapping relationship can be predicted.Therefore,the mapping relationship learned will deviate,which leads to unexpected transformation style of training results.The non-matching data is the input of two groups of completely unrelated data,which can achieve random image style conversion.

    Until now,few papers discuss how to deal with image cloud removal independent of the physical scattering model.As discussed in Introduction, it is meaningful to investigate a model-free cloud removal method via GAN.

    3 Cloud Removal Method Based on Pix2Pix

    GAN is an unsupervised learning,it can’t realize the conversion between pixels.Some researchers propose to use Conditional Generation Adversarial Network to complete the work of image to image,which is called Pix2Pix.It realizes the transformation of matching data image.

    Pix2Pix Network adopts a fully supervised method (Fig.3) that is to train the model with fully matched input and output images,and generate the target image of the specified task from the input image through the trained model.The algorithm is mainly divided into two stages:training and testing.In the training phase,the Pix2Pix network is trained with paired solar images,and then the network model is optimized by iterating the generation network and decision network to optimize the network parameters.In the test phase,the cloud-covered image is input into the trained Pix2Pix network to get the cloudless image.

    Figure 3:The flow chart of network

    The generator adopts the U-Net [19] architecture (Fig.4a).Eight convolution layers and eight deconvolution layers are used to generate pseudo samples.In the design of the discriminator(Fig.4b),the network structure of 5 convolution layers and leaky relu layer is adopted.In generator G, the training Halpha images is input,and convolution operation is performed through 8 convolution layers.The activation function used in this part is leaky relu function,and the batch normalization method[20]is used in each layer to enhance the convergence performance of the model.

    3.1 Generator

    An 8-level U-Net architecture is employed for pixel-level feature learning.The architecture comprises of three parts:encoding network,decoding network,and a bridge that connects both the networks(Tab.1).The complete network is constructed using 4×4 convolution layers with a stride of 2 for down-sampling and up-sampling.

    U-Net architecture is used as Generator.U-Net architecture consists of two paths:a contractive path and an expansive path and both are symmetric to each other.It yields an architecture like Ushape(Fig.5)(Thus called as U-Net).The network on the left side is a contracting path that is like a traditional CNN involving convolution and activations.On the right side of Fig.5 is an expansive path which includes up-sampling layers and the corresponding convolutional layers on the left side.Both the network paths are merged to compensate for the loss of information.As a result,the architecture preserves the same resolution of images as in input network layer.

    Figure 4:The architecture of Pix2Pix.Pix2Pix includes two parts:the U-Net generator and the Patch GAN discriminator.(a)Generator(b)Discriminator

    Table 1:Structure of the U-Net network

    Table 1:Continued

    Figure 5:The structure of Generator

    3.2 Discriminator

    The discriminator uses PatchGAN(Fig.6).PatchGAN makes the model more efficient and the detail achieves a better effect.The discriminator splices the image generated by the generator with the condition image.The number of convolution kernels in the first down-sampling layer is set to 64.The number of convolution kernels in each layer is set to twice that of the upper layer.The number of convolution kernels in the last down-sampling layer is set to 1.The first three down-sampling layers have a stride size of 2.The length and width of each image are half of the origin.The last two subsampling layers have a stride size of 1,keeping the image size unchanged.Finally,the results are obtained through the Sigmoid layer(Fig.4).

    The deeper the subsampling convolution layer is,the more accurate the extracted features will be.The size of the input image is 512×512,and each time the image is subsampled,the length and width of the image are changed to half of the original image.The feature image extracted from each layer of convolution is used as the criterion for discriminator.The size of feature image is the result of pixel,full image and patch.Fig.7 indicated that the experimental results based on the patch were the best.So the PatchGAN is selected to be the discriminator.

    Figure 6:The structure of Discriminator

    Figure 7:PatchGAN.The size of feature image is the result of pixel,full image and patch

    3.3 Loss Function

    The following is the loss function of Pix2Pix Network (Eqs.(2)).WhereD(x, y) represents the result of the input objectxand output objectyof the real matching data for the discriminatorD,whileD(x,G(x,z))is the result of the imageG(x,z)generated by the generator for the discriminator.LCGAN(G,D)represents the loss function of CGAN.Erepresents the expectation.

    In addition to the above-mentioned optimization function, Pix2Pix optimizes the network by addingLossL1[21]as the traditional loss function(Eqs.(3)).

    The loss function of the final generator is shown in Eqs.(4),whereλis a hyperparameter,which can be adjusted as appropriate.Whenλ=0,the loss function ofLossL1is not used:

    4 Experimental Results

    In this section,the data set is constructed to demonstrate the effectiveness of the proposed method.And four methods:Dark channel prior network(DCP),CGAN(Pix2Pix model withoutLossL1),L1 model(Pix2Pix model withoutLossGAN),CycleGAN are compared with the proposed method.

    4.1 Data Preprocessing

    The data set is constructed which are partly provided by HSOS.The data set includes two parts:the full-disk Halpha solar images obscured by cloud and the cloudless full-disk Halpha solar images.82 typical pairs of Halpha images are selected as original training set,and 15 pairs of them are chosen to test the performance of the proposed method.Data augmentation is also critical for network in variance and robustness when a small number of training images are available.Flipping, shearing,zooming,and rotation are the main methods(Tab.2).In order to obtain a usable model,only those images with distinct features are selected as training samples.Finally,2731 samples are generated from 97 high-quality Halpha full-disk solar images.The proposed method takes 2566 pairs as inputs that are resized to 512×512 and sent to the enhanced Pix2Pix architecture to generate an appropriate weight model,which is used to removing cloud in Halpha images.

    Table 2:Parameters of data enhancement of the network

    4.2 Quality Measures

    To better evaluate the performance of the proposed method, three image quality evaluation methods:the Peak Signal to Noise Ratio (PSNR) [22], the Structural Similarity (SSIM) [22] and Perceptual Index(PI)[23]can be used as image quality evaluation metrics.

    Peak Signal to Noise Ratio (PSNR).The PSNR is a full-reference image quality evaluation indicator.Let MSE denote the mean square error between the current imageXand the reference imageY;letHandWdenote the image height and width,respectively.iandjrepresents the position of the pixel.Letndenote the number of bits per pixel(generally 8),meaning that the number of possible gray levels of a pixel is 256.The PSNR is expressed in units of dB.The larger the PSNR is,the smaller the distortion.The MSE(Eqs.(5))and PSNR(Eqs.(6))are calculated as follows:

    Structural Similarity(SSIM).The SSIM is another full-reference image quality evaluation metric that measures image similarity from three perspectives:brightness, contrast, and structure.SSIM values closer to 1 indicate greater similarity between the originalXand reconstructed image blocksYand represent a better reconstruction effect.The formula for calculating the SSIM(Eqs.(7))is as follows:

    where,μxandμyrepresent the means of image blocksXandY,respectively;σx,σyandσxyrepresent the variances of image blocksX,Yand their covariance,respectively;C1andC2are constants.

    Perceptual Index (PI).The PSNR and SSIM are the most commonly used objective indicators for image evaluation.PSNR is based on the error between corresponding pixels, which is based on error-sensitive image quality evaluation.SSIM is a full reference image quality evaluation index,which measures image similarity from brightness, contrast and structure.Since these measures do not consider the visual characteristics of the human eye,the evaluation results are often inconsistent with human subjective perception.PI(Eqs.(8))is a new criterion which bridges the visual effect with computable index.And it has been recognized to be effective in image super-resolution [24] .In the experiment, PI is used to evaluate the performance of image cloud removal.The higher the image quality is,the lower PI is.

    where,MaandNIQEare two image qualification indexes which are detailed in[25].

    4.3 Training Details

    4.3.1 The Number of Iterations

    The loss value is recorded every 1000 iterations (Fig.8).It can be seen from the change trend that the local minimum is reached around 1000,000 times,and then the discriminator continues to be trained to make the judgment more accurate.After 1000,000 times, the generated image is basically close to the target image and it tends to be stable, so the network trained by 1026,400 iterations is selected.

    Figure 8:(a) is the change curve of LossGAN; values.The abscissa is the number of iterations and the ordinate is the value of the Generator loss function.(b) is the change curve of LossL1 values.The abscissa is the number of iterations and the ordinate is the value of the LossL1 function

    4.3.2 The Value of λ

    The adjustment of this parameter is mainly to consider the weight of the two loss functions.It aims to make the detail information of the generated image closer to the real image.That is,make the generator more accurate.So consider takingλto 100 and 0 respectively.Whenλ=0,the loss function only hasLossGANand it doesn’t hasLossL1Block effect will appear when loss function is defined asLossGAN,block uniform stripes will appear in the image,causing image distortion(Fig.9).When loss function is defined asLoss=LossGAN+LossL1block effect of the image is significantly weakened or even disappeared, which improves the texture clarity of the image.In the experimental comparison of parameter sizes,LossGANandLossL1are not on the same order of magnitude,and the influence ofLossL1should be appropriately increased without affecting the function ofLossGAN(Fig.8).Therefore,the weight is increased to make the generated image closer to the target image.

    Figure 9:The experimental results of different loss functions,When λ=0,the loss function only has LossGAN and no LossL1.When λ=100,the loss function has LossGAN and LossL1

    1,10,30,50,70,90,100 were set as the value ofλrespectively(Tab.3).Subjective comparison was conducted under the results of 1,026,400 iterations.As the value ofλincreases,the PSNR and SSIM significantly increases.And the overall perceived quality is better.The PSNR is 27.2121,which is 0.5 dB higher than other results,the SSIM is 0.8601,which is also higher than other results.The experimental results show that as the value ofλincreases,the PI significantly decreases(Fig.10).Therefore,from the three image quality evaluation methods,the choice of 100 as the value ofλis the best.

    Table 3:SSIM and PSNR results of different λ

    4.4 Results Analysis

    The method is performed on the tensorflow framework and a NVIDIA GeForce RTX2080ti GPU.During training,Adam optimizer[26]is adopted with a batch size of 1,and set a learning rate as 0.0002.The hyperparameters of loss function is set asλ= 100.The discriminator tended to converge after about 1,026,400 iterations on the training set.Fig.11 shows the results of test set in 2011.From left to right are the cloud covered Halpha images, the generated cloudless images and the real cloudless images.It can be seen that the model has a good generating effect on the test set.Dark thread-like features are filaments and bright patches surrounding sunspots are plages which are also associated with concentrations of magnetic fields.So the characteristic areas on the figure are restored and the cloud is removed.

    Figure 10:Experimental results with different λ values,PIs are shown at the bottom of each image

    4.5 Comparisons with Other Methods

    Fig.12 gives the comparison of visual effect in which the comparison results on proposed data set.DCP method suffers from color distortion,where the results are usually darker than the ground truth images and it is observed that there remains some cloud in the images.CGAN suffers from color distortion and it fails in details restoration.In the L1 loss model,the generated picture also loses detail information,and there is noise in the generated picture.Compared with CycleGAN,Pix2Pix makes the synthesized image look more like the ground truth image.It is obvious that Pix2Pix out-performs the above mentioned methods in details recovery,and it improves the cloud removal results qualitatively and quantitatively.

    Figure 11:The experimental results of the Pix2Pix model test

    Figure 12:Results of comparison between DCP, CGAN, L1 model, CycleGAN and the proposed method.PIs are shown at the bottom of each image

    The SSIM value obtained by Pix2Pix is 0.8601,and the PSNR value is 27.2121 dB(Tab.4).Both of them are higher than other four models.From these two indicators, the cloud removal effect of Pix2Pix model is better than other models, which is consistent with the subjective perception of the target image.According to the description of PI index, the lower the PI value, the higher the image quality.The PI value of the DCP model is the smallest(Fig.12).The image has been sharpened after DCP processing,but the goal of image cloud removal has not been achieved.After excluding the DCP model, the Pix2Pix model performs the best.From these three objective indicators, it can indirectly prove that the algorithm in this paper can better generate the details and features of the image,make the generated image closer to the real image and remove the influence of cloud on the full disk data set of solar image.The achieved results conclude the proposed model as an effective model among all the used models in this investigation.

    Table 4:SSIM and PSNR results of different models

    4.6 Limitation

    The proposed method is not very robust for heavily cloud scene(Fig.13),the details of solar image in heavily cloud can’t be recovered naturally.The size of data set is not big enough and core details of images can’t be learned.The limitation might be solved by applying enhancing blocks in the network.

    Figure 13:An example for heavily cloud scene

    5 Conclusion

    Imaging analysis and processing are critical components in solar physics.It is difficult for researchers to analyze solar activity in images obscured by clouds.Therefore,it is of great significance to remove the cloud from the image for all ground-based observations.This paper uses an image translation algorithm based on pixel to pixel network for image cloud removal.In this network, a U-Net generator and PatchGAN discriminator is used to improve the generated image details, so that the visual effect of the generated cloudless image is more realistic, and the goal of image cloud removal is realized.And it is compared with the traditional mainstream deep learning image generation algorithms.In these experiments, it be found that the model can learn more effective solar image features and synthesize clearer cloudless images by using the data set of the National Astronomical Observatories.The results of this study will be deployed to HSOS to improve the image quality of the full disk data set of solar image.The proposed method will also use image processor technology to develop corresponding processing software for astronomical observation researchers.The future work will focus on creating a larger data set from solar images,obtaining a data set with various solar activity conditions, making the network have better generalization capabilities, and studying some different quantitative performance indicators to evaluate our method.

    Acknowledgement:Authors are thankful to the Huairou Solar Observing Station (HSOS) which provided the data.Authors gratefully acknowledge technical and financial support from CAS Key Laboratory of Solar Activity,Media Computing Lab of Minzu University of China and New Jersey Institute of Technology.We acknowledge for the data resources from“National Space Science Data Center,National Science Technology Infrastructure of China.(https://www.nssdc.ac.cn).

    Funding Statement:Funding for this study was received from the open project of CAS Key Laboratory of Solar Activity (Grant No:KLSA202114) and the crossdiscipline research project of Minzu University of China(2020MDJC08).

    Conflicts of Interest:The authors declare that they have no conflicts of interest to report regarding the present study.

    高清视频免费观看一区二区| 久久精品国产鲁丝片午夜精品| av黄色大香蕉| 亚洲成色77777| 午夜日本视频在线| 国产高清国产精品国产三级 | 国产精品一区二区三区四区免费观看| 中文欧美无线码| 在线观看三级黄色| 在线免费十八禁| 亚洲人成网站高清观看| 国产精品一区二区三区四区免费观看| 国产伦精品一区二区三区视频9| 噜噜噜噜噜久久久久久91| 久久久久精品性色| 午夜视频国产福利| 日韩欧美 国产精品| 日韩三级伦理在线观看| 亚洲四区av| 尤物成人国产欧美一区二区三区| 国产黄片美女视频| 菩萨蛮人人尽说江南好唐韦庄| 久久青草综合色| 建设人人有责人人尽责人人享有的 | 99热这里只有是精品50| 国产白丝娇喘喷水9色精品| av福利片在线观看| 九九在线视频观看精品| 婷婷色麻豆天堂久久| 亚洲美女视频黄频| 丰满人妻一区二区三区视频av| 久久综合国产亚洲精品| 熟女人妻精品中文字幕| 国产日韩欧美亚洲二区| 大又大粗又爽又黄少妇毛片口| 在线观看免费视频网站a站| 插逼视频在线观看| 2018国产大陆天天弄谢| 亚洲精品第二区| 成年女人在线观看亚洲视频| 亚洲精品视频女| 久久久精品94久久精品| 久久99热6这里只有精品| 蜜桃在线观看..| 天天躁夜夜躁狠狠久久av| 国产国拍精品亚洲av在线观看| 男人和女人高潮做爰伦理| 一级爰片在线观看| 肉色欧美久久久久久久蜜桃| 啦啦啦在线观看免费高清www| 国产亚洲精品久久久com| av在线老鸭窝| 美女脱内裤让男人舔精品视频| 久久久久精品久久久久真实原创| 日本一二三区视频观看| 免费人成在线观看视频色| 永久网站在线| 亚洲精品国产色婷婷电影| 欧美xxxx性猛交bbbb| 成人午夜精彩视频在线观看| 久久久亚洲精品成人影院| 国产精品三级大全| 色视频www国产| 伦精品一区二区三区| 国产精品无大码| 一级毛片久久久久久久久女| 99久久人妻综合| 国产精品一区二区在线观看99| 亚洲欧美成人综合另类久久久| 午夜福利视频精品| 亚洲国产毛片av蜜桃av| 日韩av在线免费看完整版不卡| 国产一区亚洲一区在线观看| 亚洲精品成人av观看孕妇| 另类亚洲欧美激情| 3wmmmm亚洲av在线观看| 欧美成人一区二区免费高清观看| 大又大粗又爽又黄少妇毛片口| 午夜福利高清视频| 黄色怎么调成土黄色| 嘟嘟电影网在线观看| 看免费成人av毛片| 最近最新中文字幕免费大全7| 日本一二三区视频观看| 国产又色又爽无遮挡免| 最黄视频免费看| 91久久精品国产一区二区成人| 九九爱精品视频在线观看| 免费av不卡在线播放| 国产成人免费观看mmmm| av不卡在线播放| 免费人成在线观看视频色| 久久热精品热| 校园人妻丝袜中文字幕| videos熟女内射| 国产成人精品久久久久久| 又粗又硬又长又爽又黄的视频| 久久久久精品性色| 欧美激情极品国产一区二区三区 | 最近最新中文字幕大全电影3| 男女免费视频国产| 偷拍熟女少妇极品色| 18禁动态无遮挡网站| 三级经典国产精品| 日韩av免费高清视频| 少妇 在线观看| 亚洲,欧美,日韩| 精品久久久久久久久亚洲| 久久青草综合色| 久久精品国产a三级三级三级| 精品国产一区二区三区久久久樱花 | 久久韩国三级中文字幕| 黄色欧美视频在线观看| 国产黄色免费在线视频| 国产成人免费无遮挡视频| 国产在线一区二区三区精| 成年美女黄网站色视频大全免费 | 各种免费的搞黄视频| 五月天丁香电影| 久热这里只有精品99| 只有这里有精品99| 亚洲综合精品二区| 97超碰精品成人国产| 亚洲熟女精品中文字幕| 国内精品宾馆在线| 亚洲性久久影院| 最黄视频免费看| 大片免费播放器 马上看| 老女人水多毛片| 午夜福利高清视频| 狂野欧美白嫩少妇大欣赏| 中国美白少妇内射xxxbb| 日本午夜av视频| 嫩草影院入口| 97超碰精品成人国产| 精品久久久久久久久亚洲| 亚洲人成网站高清观看| 亚洲精品乱码久久久久久按摩| 99九九线精品视频在线观看视频| 久热久热在线精品观看| 欧美xxⅹ黑人| av国产精品久久久久影院| 极品少妇高潮喷水抽搐| 两个人的视频大全免费| 亚洲,一卡二卡三卡| 精品亚洲成a人片在线观看 | 欧美成人午夜免费资源| 亚洲精品乱码久久久久久按摩| 天美传媒精品一区二区| 中文字幕人妻熟人妻熟丝袜美| 欧美精品人与动牲交sv欧美| 一二三四中文在线观看免费高清| 亚洲丝袜综合中文字幕| 亚洲欧美成人综合另类久久久| 男人和女人高潮做爰伦理| 欧美日本视频| 亚洲av男天堂| 免费在线观看成人毛片| 国产av码专区亚洲av| 精品久久久久久久久av| 国产精品伦人一区二区| 国产成人精品久久久久久| 中国国产av一级| 久久久久久人妻| 免费观看av网站的网址| 国产黄片视频在线免费观看| 亚洲丝袜综合中文字幕| 菩萨蛮人人尽说江南好唐韦庄| 在线免费十八禁| 99re6热这里在线精品视频| 亚洲综合色惰| 久久精品久久久久久久性| 黄色日韩在线| 中文精品一卡2卡3卡4更新| 韩国av在线不卡| 亚洲经典国产精华液单| av一本久久久久| 亚洲av不卡在线观看| 久久人妻熟女aⅴ| 深爱激情五月婷婷| 国产在线一区二区三区精| 午夜福利高清视频| 最后的刺客免费高清国语| 国产在线男女| av免费在线看不卡| 极品教师在线视频| 日韩人妻高清精品专区| 亚洲成人手机| 日日摸夜夜添夜夜添av毛片| av又黄又爽大尺度在线免费看| 亚洲精品成人av观看孕妇| 人人妻人人澡人人爽人人夜夜| 一级片'在线观看视频| 久久精品久久久久久久性| 黑丝袜美女国产一区| 国产精品欧美亚洲77777| 女的被弄到高潮叫床怎么办| 亚洲精品乱码久久久久久按摩| 久久韩国三级中文字幕| 欧美日本视频| 久久人人爽人人爽人人片va| 蜜桃亚洲精品一区二区三区| 国产乱人视频| av国产久精品久网站免费入址| 欧美变态另类bdsm刘玥| 十分钟在线观看高清视频www | 亚洲av在线观看美女高潮| 男女边摸边吃奶| 久久韩国三级中文字幕| 亚洲,欧美,日韩| 日韩三级伦理在线观看| 亚洲精品乱码久久久v下载方式| 中文字幕av成人在线电影| 久久韩国三级中文字幕| 免费看不卡的av| 亚洲美女视频黄频| 美女视频免费永久观看网站| 亚洲精品亚洲一区二区| 毛片女人毛片| 欧美最新免费一区二区三区| 青青草视频在线视频观看| videos熟女内射| 欧美精品一区二区免费开放| 狂野欧美白嫩少妇大欣赏| av福利片在线观看| 久久97久久精品| 秋霞伦理黄片| 日韩三级伦理在线观看| 亚洲av在线观看美女高潮| 国产精品国产三级专区第一集| 亚洲婷婷狠狠爱综合网| 亚洲在久久综合| 国产亚洲91精品色在线| 高清在线视频一区二区三区| 哪个播放器可以免费观看大片| 国产片特级美女逼逼视频| 久久久久国产网址| 免费大片18禁| 午夜视频国产福利| 久久久国产一区二区| 亚洲国产成人一精品久久久| 亚洲精品乱码久久久久久按摩| 国模一区二区三区四区视频| 国产伦理片在线播放av一区| xxx大片免费视频| 国产爽快片一区二区三区| 亚洲精品乱码久久久久久按摩| 一级毛片我不卡| 久久av网站| 国产一区亚洲一区在线观看| 伊人久久国产一区二区| 久久久久精品久久久久真实原创| 少妇 在线观看| 肉色欧美久久久久久久蜜桃| 97热精品久久久久久| 欧美激情国产日韩精品一区| 久久ye,这里只有精品| 国产 一区 欧美 日韩| 日本av免费视频播放| 在现免费观看毛片| 三级经典国产精品| 欧美zozozo另类| 蜜桃在线观看..| 在线观看三级黄色| 少妇精品久久久久久久| 99热网站在线观看| 老熟女久久久| 男女下面进入的视频免费午夜| 51国产日韩欧美| 亚洲国产高清在线一区二区三| 校园人妻丝袜中文字幕| 人人妻人人爽人人添夜夜欢视频 | 啦啦啦中文免费视频观看日本| 成年女人在线观看亚洲视频| 欧美精品国产亚洲| 在线观看一区二区三区激情| 美女国产视频在线观看| 99热这里只有精品一区| 国产一区二区在线观看日韩| 超碰97精品在线观看| 国产女主播在线喷水免费视频网站| 国产精品久久久久久av不卡| 欧美激情国产日韩精品一区| 国产精品女同一区二区软件| 在线播放无遮挡| 久久久国产一区二区| 中文字幕人妻熟人妻熟丝袜美| 3wmmmm亚洲av在线观看| 国产精品蜜桃在线观看| 精华霜和精华液先用哪个| 久久精品国产亚洲网站| 日韩欧美 国产精品| 亚洲综合精品二区| 九九在线视频观看精品| 女人十人毛片免费观看3o分钟| 国产成人午夜福利电影在线观看| 成人特级av手机在线观看| 免费少妇av软件| 美女国产视频在线观看| 极品少妇高潮喷水抽搐| 亚洲国产精品专区欧美| 老熟女久久久| 精品久久久久久电影网| 欧美日韩亚洲高清精品| 国产亚洲5aaaaa淫片| 国产片特级美女逼逼视频| 美女脱内裤让男人舔精品视频| 久久 成人 亚洲| 亚洲,欧美,日韩| 日韩强制内射视频| 日韩在线高清观看一区二区三区| 男女边吃奶边做爰视频| 午夜免费观看性视频| 黑人高潮一二区| 99久久人妻综合| 看非洲黑人一级黄片| 久久99热6这里只有精品| 男女啪啪激烈高潮av片| 熟女人妻精品中文字幕| 纵有疾风起免费观看全集完整版| 国产老妇伦熟女老妇高清| 99精国产麻豆久久婷婷| 一区二区三区乱码不卡18| 九草在线视频观看| 久久韩国三级中文字幕| 人人妻人人澡人人爽人人夜夜| av在线播放精品| 日韩成人伦理影院| 丰满迷人的少妇在线观看| 午夜免费男女啪啪视频观看| 国国产精品蜜臀av免费| av视频免费观看在线观看| 777米奇影视久久| 乱码一卡2卡4卡精品| 又大又黄又爽视频免费| 99久久人妻综合| 日韩不卡一区二区三区视频在线| av线在线观看网站| 日本vs欧美在线观看视频 | 黄色日韩在线| 午夜老司机福利剧场| 免费av不卡在线播放| av卡一久久| 大香蕉久久网| 久久 成人 亚洲| www.av在线官网国产| 少妇裸体淫交视频免费看高清| 人人妻人人看人人澡| 日本猛色少妇xxxxx猛交久久| 亚洲国产精品国产精品| 少妇被粗大猛烈的视频| 成人二区视频| 日本av免费视频播放| 亚洲欧美一区二区三区国产| 天堂中文最新版在线下载| 亚洲成人手机| 性高湖久久久久久久久免费观看| 99九九线精品视频在线观看视频| 国产又色又爽无遮挡免| 久久久国产一区二区| 亚洲第一av免费看| 久久99热这里只有精品18| 晚上一个人看的免费电影| 日韩一本色道免费dvd| 老司机影院成人| 国产有黄有色有爽视频| 王馨瑶露胸无遮挡在线观看| 亚洲经典国产精华液单| 在线观看免费高清a一片| 91狼人影院| 91久久精品国产一区二区三区| 亚洲三级黄色毛片| 中文精品一卡2卡3卡4更新| 精品亚洲成a人片在线观看 | 亚洲第一av免费看| 高清av免费在线| 少妇精品久久久久久久| 各种免费的搞黄视频| 尤物成人国产欧美一区二区三区| 日韩精品有码人妻一区| 在线亚洲精品国产二区图片欧美 | 午夜视频国产福利| 97在线视频观看| 人妻 亚洲 视频| 亚洲av福利一区| 国产亚洲av片在线观看秒播厂| 最新中文字幕久久久久| 中文字幕亚洲精品专区| 99热国产这里只有精品6| 啦啦啦啦在线视频资源| 黄片无遮挡物在线观看| 亚洲成人一二三区av| 免费人妻精品一区二区三区视频| 国产精品国产三级国产专区5o| 男女啪啪激烈高潮av片| 亚洲欧美日韩另类电影网站 | 欧美一区二区亚洲| 熟女av电影| 成人特级av手机在线观看| 少妇的逼水好多| 亚洲国产欧美人成| 人妻 亚洲 视频| 一边亲一边摸免费视频| 男女无遮挡免费网站观看| 777米奇影视久久| 99热这里只有是精品50| 在线观看三级黄色| 日韩电影二区| 高清av免费在线| 久久这里有精品视频免费| 久久久精品94久久精品| 色5月婷婷丁香| 色视频在线一区二区三区| 欧美人与善性xxx| 国精品久久久久久国模美| 少妇高潮的动态图| 午夜福利影视在线免费观看| 两个人的视频大全免费| 99热这里只有是精品在线观看| 街头女战士在线观看网站| 香蕉精品网在线| 亚洲av成人精品一二三区| 国产大屁股一区二区在线视频| av又黄又爽大尺度在线免费看| 国产欧美日韩精品一区二区| 99九九线精品视频在线观看视频| 国产精品.久久久| 国模一区二区三区四区视频| 我的老师免费观看完整版| 国产成人aa在线观看| 国产精品偷伦视频观看了| 亚洲av不卡在线观看| 少妇被粗大猛烈的视频| 最近的中文字幕免费完整| 免费观看在线日韩| 最后的刺客免费高清国语| 九九在线视频观看精品| 夜夜骑夜夜射夜夜干| 成年美女黄网站色视频大全免费 | 日本vs欧美在线观看视频 | 成人综合一区亚洲| 最近最新中文字幕免费大全7| 国产v大片淫在线免费观看| 一区二区三区精品91| 熟女人妻精品中文字幕| 男人添女人高潮全过程视频| 日本色播在线视频| 免费黄色在线免费观看| 男女免费视频国产| 日本一二三区视频观看| 亚洲第一区二区三区不卡| 欧美精品亚洲一区二区| 亚洲美女黄色视频免费看| 欧美极品一区二区三区四区| 国产欧美另类精品又又久久亚洲欧美| 少妇的逼水好多| 国产黄片视频在线免费观看| 国产高清不卡午夜福利| 久久久久精品性色| 日本色播在线视频| 一个人免费看片子| 男女国产视频网站| 国产欧美亚洲国产| 亚洲av免费高清在线观看| 天天躁夜夜躁狠狠久久av| 亚洲成人一二三区av| 99国产精品免费福利视频| av卡一久久| 三级国产精品欧美在线观看| 免费在线观看成人毛片| 亚洲欧美成人综合另类久久久| 成人美女网站在线观看视频| 成人漫画全彩无遮挡| 国产在线免费精品| 99久久精品国产国产毛片| 亚洲激情五月婷婷啪啪| 亚洲人成网站在线播| 五月玫瑰六月丁香| 亚洲,欧美,日韩| 国产免费一区二区三区四区乱码| 三级国产精品欧美在线观看| 久久精品国产亚洲网站| 日韩制服骚丝袜av| 人妻 亚洲 视频| 久久精品久久精品一区二区三区| 日本-黄色视频高清免费观看| 午夜激情福利司机影院| 少妇人妻 视频| 男女无遮挡免费网站观看| 人人妻人人添人人爽欧美一区卜 | 午夜免费鲁丝| 在线天堂最新版资源| 亚洲欧美日韩另类电影网站 | 日本黄色片子视频| 国产精品一及| 亚洲人成网站在线观看播放| 午夜福利视频精品| 久久热精品热| 99热这里只有精品一区| 日本猛色少妇xxxxx猛交久久| 日韩国内少妇激情av| 日本一二三区视频观看| 国产黄频视频在线观看| 精品亚洲成a人片在线观看 | 久久国产精品大桥未久av | 国产成人午夜福利电影在线观看| 91精品伊人久久大香线蕉| 国产成人精品久久久久久| 性色av一级| 国产成人免费观看mmmm| 国产精品不卡视频一区二区| videossex国产| 日韩一本色道免费dvd| 精品99又大又爽又粗少妇毛片| 亚洲自偷自拍三级| 精品少妇黑人巨大在线播放| 我要看黄色一级片免费的| 国产精品偷伦视频观看了| 国产日韩欧美亚洲二区| 久久影院123| 国产高清不卡午夜福利| 久久人人爽人人片av| 亚洲伊人久久精品综合| 国产精品国产av在线观看| 六月丁香七月| 亚洲av国产av综合av卡| av在线app专区| 噜噜噜噜噜久久久久久91| 国产高清不卡午夜福利| 三级国产精品片| av免费在线看不卡| 麻豆成人av视频| 国产精品久久久久成人av| 亚洲美女黄色视频免费看| tube8黄色片| 欧美性感艳星| 午夜福利在线观看免费完整高清在| 国产视频内射| 免费不卡的大黄色大毛片视频在线观看| 亚洲无线观看免费| 一本久久精品| 一区二区三区精品91| 一个人免费看片子| 精品少妇久久久久久888优播| 国产免费福利视频在线观看| 国产精品久久久久久精品古装| 五月玫瑰六月丁香| 人妻制服诱惑在线中文字幕| 久久久久网色| 亚洲欧洲国产日韩| 国产精品人妻久久久久久| 日韩欧美精品免费久久| 亚洲精品,欧美精品| 又黄又爽又刺激的免费视频.| 国产亚洲最大av| 成人亚洲欧美一区二区av| 建设人人有责人人尽责人人享有的 | 亚洲国产最新在线播放| 日本与韩国留学比较| 国产色爽女视频免费观看| 久久久久久久精品精品| 交换朋友夫妻互换小说| 99久久人妻综合| 成人18禁高潮啪啪吃奶动态图 | 欧美97在线视频| 一二三四中文在线观看免费高清| 亚洲精品乱码久久久久久按摩| 精品亚洲乱码少妇综合久久| 国产精品一区二区在线不卡| 全区人妻精品视频| 成年免费大片在线观看| 国产欧美另类精品又又久久亚洲欧美| 亚洲国产日韩一区二区| 国产精品99久久99久久久不卡 | 久久精品久久久久久噜噜老黄| 80岁老熟妇乱子伦牲交| 久久午夜福利片| 亚洲真实伦在线观看| 国产精品麻豆人妻色哟哟久久| 嫩草影院新地址| 男的添女的下面高潮视频| 日日啪夜夜爽| 深爱激情五月婷婷| 国产女主播在线喷水免费视频网站| 丝瓜视频免费看黄片| 一级二级三级毛片免费看| 三级国产精品欧美在线观看| 高清毛片免费看| 亚洲av电影在线观看一区二区三区| 欧美三级亚洲精品| 狠狠精品人妻久久久久久综合| 日韩强制内射视频| 午夜福利在线观看免费完整高清在| 中文字幕制服av| 激情 狠狠 欧美| 国产精品一区二区性色av| 亚洲不卡免费看| 欧美性感艳星| 亚洲av欧美aⅴ国产| 尤物成人国产欧美一区二区三区| 欧美日韩视频高清一区二区三区二| 在线看a的网站| 直男gayav资源| 黄色怎么调成土黄色| 日韩一本色道免费dvd| 国产色爽女视频免费观看| 国产成人免费无遮挡视频| 免费高清在线观看视频在线观看| 国产免费又黄又爽又色| 国产精品久久久久久av不卡| 黄片无遮挡物在线观看| 日韩一区二区视频免费看| 日韩免费高清中文字幕av| 在线观看一区二区三区| 日韩在线高清观看一区二区三区|