注意力机制下多尺度特征融合生成对抗网络的白天海雾监测

方旭源; 金炜; 符冉迪; 李纲; 何彩芬; 尹曹谦

doi:10.11834/jrs.20221621

AI+遥感 | 浏览量 : 0 下载量: 227 CSCD: 0 更多指标

R-PDF
PDF
导出
分享
收藏
专辑

注意力机制下多尺度特征融合生成对抗网络的白天海雾监测
Daytime sea fog detection based on multi-scale feature fusion of generated adversarial network under attention mechanism
2023年27卷第12期页码：2736-2747
纸质出版日期： 2023-12-07 ，
DOI： 10.11834/jrs.20221621

扫描看全文

方旭源，金炜，符冉迪，李纲，何彩芬，尹曹谦.2023.注意力机制下多尺度特征融合生成对抗网络的白天海雾监测.遥感学报，27（12）： 2736-2747

Fang X Y，Jin W，Fu R D，Li G，He C F and Yi C Q. 2023. Daytime sea fog detection based on multi-scale feature fusion of generated adversarial network under attention mechanism. National Remote Sensing Bulletin， 27（12）：2736-2747
方旭源，金炜，符冉迪，李纲，何彩芬，尹曹谦.2023.注意力机制下多尺度特征融合生成对抗网络的白天海雾监测.遥感学报，27（12）： 2736-2747 DOI： 10.11834/jrs.20221621.

Fang X Y，Jin W，Fu R D，Li G，He C F and Yi C Q. 2023. Daytime sea fog detection based on multi-scale feature fusion of generated adversarial network under attention mechanism. National Remote Sensing Bulletin， 27（12）：2736-2747 DOI： 10.11834/jrs.20221621.

摘要

海雾是海上一种常见的天气现象，它使能见度降低，给海上交通和作业带来极大威胁。传统的卫星遥感海雾监测算法在准确率、可移植性及自动化程度等方面都有待改善。本文在注意力机制下，利用卫星遥感云图，提出一种多尺度特征融合生成对抗网络的白天海雾监测方法。该方法引入通道注意力机制，通过学习不同输入通道的权重，提升了网络对于重要通道云图的关注度；在此基础上，采用多尺度特征融合以获取海雾的多尺度信息，使提取的特征能兼顾海雾的整体及细节特性；为了进一步提高算法对于对海雾边缘的界定能力，本文引入对抗网络对海雾监测的生成网络进行监督，从而得到更精细的海雾区域。在测试云图的海雾监测实验中，命中率（POD）、临界成功指数（CSI）及误报率（FAR）分别为90.5%、81.28%和10.86%，均优于传统海雾监测方法以及其他基于深度学习的方法，这表明本文方法可以有效提升海雾监测的精度，研究成果对于海上船只航行、渔业生产、国防军事等具有重要意义。

Abstract

Sea fog is a common weather phenomenon at sea. It will reduce visibility at sea and greatly threaten maritime traffic and other operations. Traditional sea fog detection algorithms using satellite remote sensing have low accuracy

poor portability

and low automation. Although some existing deep learning-based sea fog monitoring algorithms have been improved

they do not consider the spectral characteristics of sea fog in different channels. The accuracy of sea fog monitoring is also low

especially in edge recognition.

A daytime sea fog detection method

which is based on multi-scale feature fusion of generated adversarial network under attention mechanism

is proposed to improve the accuracy of sea fog detection. First

according to the spectral response of sea fog in different imaging channels of meteorological satellite

the satellite cloud images of different imaging channels that can reflect the characteristics of sea fog are selected as the input of the network. Meanwhile

a channel attention mechanism is introduced to calculate the weights of different input channels for prioritizing significant imaging channels within multichannel input. Then

a multi-scale feature fusion mechanism is adopted to fuse the feature maps of different levels of the network for obtaining the multi-scale features of the sea fog. In this way

the problem of losing detailed features in cloud images caused by the pooling operation of the traditional deep network can be solved. Finally

given the difficulty of traditional methods to accurately describe the edge of sea fog

a generation network for sea fog detection supervised by an adversarial network is used to accurately define the edge of sea fog and reduce the false alarm rate.

This study takes the Yellow Sea and the Bohai Sea (116.5°—128.25°E，30°—42.5°N) as the research area. Given that March to June each year is the period of high incidence of sea fog in the Yellow Sea and the Bohai Sea

we produce a dataset based on the weather satellite monitoring report of the National Meteorological Center from March to June 2017—2020. After training the model

concerning the quantitative indicators of sea fog detection

our method achieves a probability of detection of 90.5%

a critical success index of 81.28%

and a false positive rate of 10.86%

which are better than those of other methods.

The experimental results show that the proposed method can effectively improve the accuracy of sea fog identification

which is important for marine vessel navigation

fishery production

national defense

and military affairs.

关键词

海雾监测卫星遥感注意力机制生成对抗网络多尺度特征融合

Keywords

sea fog monitoringsatellite remote sensingattention mechanismgenerate adversarial networkmulti-scale feature fusion

references

Bendix J, Thies B, Cermak J and Nauß T. 2005. Ground fog detection from space based on MODIS daytime data—a feasibility study. Weather and Forecasting, 20(6): 989-1005 [DOI: 10.1175/WAF886.1http://dx.doi.org/10.1175/WAF886.1]

Cermak J and Bendix J. 2008. A novel approach to fog/low stratus detection using Meteosat 8 data. Atmospheric Research, 87(3/4): 279-292 [DOI: 10.1016/j.atmosres.2007.11.009http://dx.doi.org/10.1016/j.atmosres.2007.11.009]

Chen L. 2006. Studies on EOS/MODIS Data Processing and an Application on Monitoring Fog/Low Stratus by Daylight. Nanjing: Nanjing University of Information Science and Technology

陈林. 2006. EOS/MODIS资料的数据处理方法及其在白天低云大雾监测中的应用. 南京: 南京信息工程大学 [DOI: 10.7666/d.y863542http://dx.doi.org/10.7666/d.y863542]

Deng Y J, Wang J C and Cao J. 2013. Detection of daytime fog in South China Sea using MODIS data. Journal of Tropical Meteorology, 29(6): 1046-1050

邓玉娇, 王捷纯, 曹静. 2013. 基于MODIS遥感资料监测南海白天雾. 热带气象学报, 29(6): 1046-1050

Eyre J R, Brownscombe J L and Allam R J. 1984. Detection of fog at night using advanced very high resolution radiometer (AVHRR) imagery. Meteorological Magazine, 113(1346): 266-271

Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y. 2014. Generative adversarial nets//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal: MIT Press: 2672-2680

Huang H M, Lin L F, Tong R F, Hu H J, Zhang Q W, Iwamoto Y, Han X H, Chen Y W and Wu J. 2020. UNet 3+: a full-scale connected UNet for medical image segmentation//2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Barcelona: IEEE: 1055-1059 [DOI: 10.1109/ICASSP40776.2020.9053405http://dx.doi.org/10.1109/ICASSP40776.2020.9053405]

Hunt G E. 1973. Radiative properties of terrestrial clouds at visible and infra-red thermal window wavelengths. Quarterly Journal of the Royal Meteorological Society, 99(420): 346-369 [DOI: 10.1002/qj.49709942013http://dx.doi.org/10.1002/qj.49709942013]

Ishida H, Miura K, Matsuda T, Ogawara K, Goto A, Matsuura K, Sato Y and Nakajima T Y. 2014. Scheme for detection of low clouds from geostationary weather satellite imagery. Atmospheric Research, 143: 250-264 [DOI: 10.1016/j.atmosres.2014.02.015http://dx.doi.org/10.1016/j.atmosres.2014.02.015]

Li Y C, Sun H, Li X G, Tang Y and Xu M. 2001. Study on detection of daytime fog using GMS-5 weather satellite data. Journal of Nanjing Institute of Meteorology, 24(3): 343-349

李亚春, 孙涵, 李湘阁, 唐勇, 徐萌. 2001. 用GMS-5气象卫星资料遥感监测白天雾的研究. 南京气象学院学报, 24(3): 343-349 [DOI: 10.3969/j.issn.1674-7097.2001.03.007http://dx.doi.org/10.3969/j.issn.1674-7097.2001.03.007]

Lin T Y, Goyal P, Girshick R, He K M and Dollar P. 2020. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2): 318-327 [DOI: 10.1109/TPAMI.2018.2858826http://dx.doi.org/10.1109/TPAMI.2018.2858826]

Liu S X, Yi L, Zhang S P, Shi X M and Xue Y C. 2019. A study of daytime sea fog retrieval over the yellow sea based on fully convolutional networks. Transactions of Oceanology and Limnology, 41(6): 13-22

刘树霄, 衣立, 张苏平, 时晓曚, 薛允传. 2019. 基于全卷积神经网络方法的日间黄海海雾卫星反演研究. 海洋湖沼通报, 41(6): 13-22 [DOI: 10.13984/j.cnki.cn37-1141.2019.06.002http://dx.doi.org/10.13984/j.cnki.cn37-1141.2019.06.002]

Liu Y J. 2019. Research on Image Semantic Segmentation Method Based on Generative Adversarial Network. Beijing: Beijing Jiaotong University

刘玉洁. 2019. 基于生成对抗网络的图像语义分割方法研究. 北京: 北京交通大学 [DOI: 10.26944/d.cnki.gbfju.2019.000067http://dx.doi.org/10.26944/d.cnki.gbfju.2019.000067]

Máttyus G, Luo W J and Urtasun R. 2017. DeepRoadMapper: extracting road topology from aerial images//2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE: 3458-3466 [DOI: 10.1109/ICCV.2017.372http://dx.doi.org/10.1109/ICCV.2017.372]

Pavolonis M. 2010. GOES-R Advanced Baseline Imager (ABI) Algorithm Theoretical Basis Document for Volcanic Ash

Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer: 234-241 [DOI: 10.1007/978-3-319-24574-4_28http://dx.doi.org/10.1007/978-3-319-24574-4_28]

Si G, Fu R D, He C F and Jin W. 2020. Daytime sea fog recognition based on remote sensing satellite and deep neural network. Journal of Optoelectronics·Laser, 31(10): 1074-1082

司光, 符冉迪, 何彩芬, 金炜. 2020. 结合遥感卫星及深度神经网络的白天海雾识别. 光电子·激光, 31(10): 1074-1082 [DOI: 10.16136/j.joel.2020.10.0172http://dx.doi.org/10.16136/j.joel.2020.10.0172]

Su J. 2001. A review of circulation dynamics of the coastal oceans near China. Acta Oceanologica Sinica, 23(4): 1-16

苏纪兰. 2001. 中国近海的环流动力机制研究. 海洋学报, 23(4): 1-16 [DOI: 10.3321/j.issn:0253-4193.2001.04.001http://dx.doi.org/10.3321/j.issn:0253-4193.2001.04.001]

Tian L, Wang X, Yang B Y and Wu X J. 2021. Overview of satellite remote sensing technology for marine atmospheric and environment observation. Science and Technology Review, 39(15): 54-66

田林, 王曦, 杨冰韵, 吴晓京. 2021. 海洋大气和环境卫星遥感技术进展. 科技导报, 39(15): 54-66

Tian Y J. 2016. Study of Algorithm of Detection of Daytime Sea Fog using FY-2 Geostationary Satellite Data. Guangzhou: South China University of Technology

田永杰. 2016. 基于风云2号静止卫星数据的白天海雾监测算法研究. 广州: 华南理工大学

Wang B H. 1983. Sea Fog. Ocean Press

王彬华. 1983. 海雾. 海洋出版社

Wang Z, Simoncelli E P and Bovik A C. 2003. Multiscale structural similarity for image quality assessment//The Thirty-Seventh Asilomar Conference on Signals, Systems and Computers. Pacific Grove: IEEE: 1398-1402 [DOI: 10.1109/ACSSC.2003.1292216http://dx.doi.org/10.1109/ACSSC.2003.1292216]

Xiao Y F, Zhang J, Cui T W and Qin P. 2017. Review of sea fog detection from satellite remote sensing data. Marine Sciences, 41(12): 146-154

肖艳芳, 张杰, 崔廷伟, 秦平. 2017. 海雾卫星遥感监测研究进展. 海洋科学, 41(12): 146-154 [DOI: 10.11759/hykx20170523001http://dx.doi.org/10.11759/hykx20170523001]

Zhang C G, Cai Y Y and Zhang J C. 2009. The application of monitoring sea fog in Taiwan strait using MODIS remote sensing data. Journal of Applied Meteorological Science, 20(1): 8-16

张春桂, 蔡义勇, 张加春. 2009. MODIS遥感数据在我国台湾海峡海雾监测中的应用. 应用气象学报, 20(1): 8-16 [DOI: 10.11898/1001-7313.20090102http://dx.doi.org/10.11898/1001-7313.20090102]

Zhang P and Wu D. 2019. Daytime sea fog detection method using Himawari-8 data. Journal of Atmospheric and Environmental Optics, 14(3): 211-220

张培, 吴东. 2019. 基于Himawari-8数据的日间海雾检测方法. 大气与环境光学学报, 14(3): 211-220 [DOI: 10.3969/j.issn.1673-6141.2019.03.006http://dx.doi.org/10.3969/j.issn.1673-6141.2019.03.006]

文章被引用时，请邮件提醒。

提交

高光谱影像三分支分组空谱注意力深度分类网络

改进CenterNet在遥感图像目标检测中的应用

大气无机氮沉降卫星遥感估算研究进展

陆表卫星遥感GLASS产品集的研发新进展