基于深度卷积神经网络的云检测方法

doi:10.13474/j.cnki.11-2246.2021.0107

测绘通报 ›› 2021, Vol. 0 ›› Issue (4): 33-39.doi: 10.13474/j.cnki.11-2246.2021.0107

基于深度卷积神经网络的云检测方法

段雅鸣^1,2, 张锦水^1,2, 朱爽^1,3

1. 北京师范大学地理科学学部遥感科学国家重点实验室, 北京 100875;
2. 北京师范大学地理科学学部北京市陆表遥感数据产品工程技术研究中心, 北京 100875;
3. 北京工业职业技术学院, 北京 100042

收稿日期:2020-05-14 修回日期:2021-02-03 出版日期:2021-04-25 发布日期:2021-04-30
通讯作者: 张锦水。E-mail:zhangjs@bnu.edu.cn
作者简介:段雅鸣(1995-),男,硕士,主要研究方向为遥感大数据挖掘。E-mail:dymwan@gmail.com
基金资助:
高分辨率对地观测系统重大专项（民用部分）（20-Y30F10-9001-20/22）

Cloud detection method based on deep convolutional neural network

DUAN Yaming^1,2, ZHANG Jinshui^1,2, ZHU Shuang^1,3

1. State Key Laboratory of Remote Sensing Science, Jointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of Sciences, Beijing 100875, China;
2. Beijing Engineering Research Center for Global Land Remote Sensing Products, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China;
3. Beijing Polytechnic College, Beijing 100042, China

Received:2020-05-14 Revised:2021-02-03 Online:2021-04-25 Published:2021-04-30

摘要/Abstract

摘要： 本文将Fmask云检测结果作为标记样本对深度卷积神经网络进行训练以实现云检测。在仅利用可见光波段和近红外波段的前提下，本文方法的云检测总体精度达到87.65%，高于Fmask的86.92%，而且单景Landsat 8影像的识别用时18 s，远低于Fmask的72 s，具有更高的精度和效率。另外，该方法适用于不同的地表土地覆盖类型，具有很强的泛化能力，是一个通用性强的算法，为进一步的遥感应用打下基础。

关键词: 云检测, 深度卷积神经网络, Fmask, Landsat 8, 强泛化能力

Abstract: This paper introduces Fmask cloud detection results as training label into the deep convolutional neural network (DCNN) for cloud detection. Under the premise of using only the visible light band and the near infrared band, the overall accuracy of cloud detection method in this paper reaches 87.65%, which is higher than 86.92% of Fmask. It costs 18 seconds for processing a single Landsat 8 image, which is much lower than 72 seconds that Fmask costing. In addition, this method is suitable for various type of land cover in target image, and has a strong generalization ability for further application.

Key words: cloud detection, deep convolutional neural network, Fmask, Landsat 8, strong generalization ability

中图分类号:

P237

段雅鸣, 张锦水, 朱爽. 基于深度卷积神经网络的云检测方法[J]. 测绘通报, 2021, 0(4): 33-39.

DUAN Yaming, ZHANG Jinshui, ZHU Shuang. Cloud detection method based on deep convolutional neural network[J]. Bulletin of Surveying and Mapping, 2021, 0(4): 33-39.

参考文献

[1] IRISH R R. Landsat 7 automatic cloud cover assessment[J]. Proceedings of SPIE-The International Society for Optical Engineering, 2000, 4049:348-355.
[2] ZHU Z, WOODCOCK C E. Object-based cloud and cloud shadow detection in Landsat imagery[J]. Remote Sensing of Environment, 2012, 118:83-94.
[3] MONTANARO M, GERACE A, LUNSFORD A, et al. Stray light artifacts in imagery from the Landsat 8 thermal infrared sensor[J]. Remote Sensing, 2014, 6:10435-10456.
[4] ZHANG Y. Calculation of radiative fluxes from the surface to top of atmosphere based on ISCCP and other global data sets:refinements of the radiative transfer model and the input data[J]. Journal of Geophysical Research Atmospheres, 2004, 109(D19):1-27.
[5] ZHU Z, WOODCOCK C E. Automated cloud, cloud shadow, and snow detection in multitemporal Landsat data:an algorithm designed specifically for monitoring land cover change[J]. Remote Sensing of Environment, 2014, 152:217-234.
[6] HAGOLLE O, HUC M, PASCUAL D V, et al. A multi-temporal method for cloud detection, applied to Formosat-2, VENμS, Landsat and Sentinel-2 images[J]. Remote Sensing of Environment, 2010, 114:1747-1755.
[7] ZHANG Y, GUINDON B, CIHLAR J. An image transform to characterize and compensate for spatial variations in thin cloud contamination of Landsat images[J]. Remote Sensing of Environment, 2002, 82:173-187.
[8] 胡根生,陈长春,梁栋.联合云量自动评估和加权支持向量机的Landsat图像云检测[J].测绘学报,2014,43(8):848-854.
[9] LEE J. A neural network approach to cloud classification[J]. IEEE Transactions on Geoscience & Remote Sensing, 1990, 28(5):846-855.
[10] 付华联,冯杰,李军,等.基于随机森林的FY-2G云检测方法[J].测绘通报,2019(3):61-66.
[11] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017,60(6):84-90.
[12] LI Z W, SHEN H F, CHENG Q, et al. Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150:197-212.
[13] DENG L, YLI D. Deep Learning:methods and applications[J]. FNT in Signal Processing, 2014, 7:197-387.
[14] LI Q, CAI W, WANG X, et al. Medical image classification with convolutional neural network[C]//Proceedings of 13th international conference on control automation robotics & vision (ICARCV). Singapore:IEEE, 2014:844-848.
[15] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas:IEEE, 2016:770-778.
[16] ZHAO H, SHI J, QI X, et al. Pyramid scene parsing network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu:IEEE, 2017:6230-6239.
[17] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of Medical Image Computing and Computer-Assisted Intervention (MICCAI). Munich:Springer International Publishing, 2015:234-241.
[18] ZOU Z, SHI Z. Ship detection in spaceborne optical image with SVD Networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(10):1-14.
[19] KANG M, LENG X, LIN Z, et al. A modified faster R-CNN based on CFAR algorithm for SAR ship detection[C]//Proceedings of 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP). Shanghai:IEEE, 2017:1-4.

基于深度卷积神经网络的云检测方法

Cloud detection method based on deep convolutional neural network

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王春霞, 张俊, 李屹旭, 范成成. 一种基于Landsat 8的多波段组合水体指数模型[J]. 测绘通报, 2022, 0(5): 20-25.
[2]	王晓晓, 韩留生, 杨骥, 李勇, 张大富, 孙广伟, 范俊甫. Sentinel-2与Landsat 8数据组合下的多特征冬小麦面积提取[J]. 测绘通报, 2022, 0(3): 111-115.
[3]	刘广进, 王光辉, 毕卫华, 刘慧杰, 杨化超. 改进D-LinkNet模型在国产卫星影像云检测中的应用[J]. 测绘通报, 2021, 0(11): 54-58,64.
[4]	何佳君, 刘向铜, 涂梨平, 徐看, 何紫玲, 宋昊航, 刘欢. 南昌地区不透水面信息自动提取[J]. 测绘通报, 2020, 0(8): 1-4.
[5]	张永宏, 蔡朋艳, 陶润喆, 王剑庚, 田伟. 基于改进U-Net网络的遥感图像云检测[J]. 测绘通报, 2020, 0(3): 17-20,34.
[6]	徐世武, 曾珏, 张诗慧, 李长征, 李亭谕. 一种深度卷积神经网络土地利用场景照片的分类方法[J]. 测绘通报, 2020, 0(2): 24-28,42.
[7]	刘云峰, 杨珍, 韩骁, 付俊. 国产高分辨率卫星影像云检测方法分析[J]. 测绘通报, 2020, 0(11): 66-70.
[8]	刘金丽, 陈钊. Landsat 8多光谱数据辅助下的高分影像多尺度分割[J]. 测绘通报, 2019, 0(9): 38-43.
[9]	余长慧, 于海威, 张文, 孟令奎. 神经网络支持下的Sentinel-2卫星影像自动云检测[J]. 测绘通报, 2019, 0(8): 39-43.
[10]	孟庆祥, 吴玄. 基于深度卷积神经网络的高分辨率遥感影像场景分类[J]. 测绘通报, 2019, 0(7): 17-22.
[11]	殷亚秋, 冷玥, 赵玉灵, 安娜, 鞠星. 面向对象和GURLS结合的高空间分辨率遥感数据云检测[J]. 测绘通报, 2019, 0(5): 109-112,142.
[12]	付华联, 冯杰, 李军, 刘军. 基于随机森林的FY-2G云检测方法[J]. 测绘通报, 2019, 0(3): 61-66.
[13]	刘军, 郑群峰, 邢秀为, 陈训来, 陈潜, 钱静. 风云气象卫星影像自动精细云检测[J]. 测绘通报, 2019, 0(12): 45-49.
[14]	肖祥红, 刘海洋, 郭云开. 基于混合像元分解理论的路域植被等量水厚度遥感反演[J]. 测绘通报, 2019, 0(12): 83-86,95.
[15]	章晓洁, 邓艳芬, 张亚超, 蒋芸芸, 邱桔斐. 利用Sentinel-2A多光谱成像仪与Landsat 8陆地成像仪影像进行普陀山岛植被分类效果比较[J]. 测绘通报, 2019, 0(10): 97-100.