耦合SVM和Cloud-Score算法的Sentinel-2影像云检测模型研究

doi:10.11873/j.issn.1004-0323.2022.3.0713

遥感技术与应用

2022, Vol. 37

Issue (3): 713-720 DOI: 10.11873/j.issn.1004-0323.2022.3.0713

遥感应用

耦合SVM和Cloud-Score算法的Sentinel-2影像云检测模型研究

李健锋^1,^3,^4,⁵(

),刘思琪^1,^3,^4,⁵,李劲彬^1,^3,^4,⁵,彭飚^1,^3,^4,⁵,叶虎平²(

)

^1.陕西地建土地工程技术研究院有限责任公司，陕西西安 710021
^2.中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室，北京 100101
^3.陕西省土地工程建设集团有限责任公司，陕西西安 710075
^4.自然资源部退化及未利用土地整治工程重点实验室，陕西西安 710075
^5.陕西省土地整治工程技术研究中心，陕西西安 710075

Research on Cloud Detection Model of Sentinel-2 Image Coupled with SVM and Cloud-Score Algorithm

Jianfeng Li^1,^3,^4,⁵(

),Siqi Liu^1,^3,^4,⁵,Jinbin Li^1,^3,^4,⁵,Biao Peng^1,^3,^4,⁵,Huping Ye²(

)

^1.Institute of Land Engineering and Technology，Shaanxi Provincial Land Engineering Construction Group Co. ，Ltd. ，Xi'an 710021，China
^2.State Key Laboratory of Resources and Environmental Information System，Institute of Geographic Sciences and Natural Resources Research，Chinese Academy of Sciences，Beijing 100101，China
^3.Shaanxi Provincial Land Engineering Construction Group Co. ，Ltd. ，Xi'an 710075，China
^4.Key Laboratory of Degraded and Unused Land Consolidation Engineering，the Ministry of Natural Resources，Xi’an 710075，China
^5.Shaanxi Provincial Land Consolidation Engineering Technology Research Center，Xi’an 710075，China

全文: PDF(5926 KB) HTML

摘要：

云覆盖阻碍了光学遥感卫星对地观测的有效范围，快速、准确的云检测是遥感应用产品生成过程中的重要一步。针对Google Earth Engine云平台中缺乏适用且高质量的云检测模型，以热带多云的斯里兰卡为研究区，构建了耦合SVM和Cloud-Score算法的Sentinel-2影像云检测模型，通过实验从目视判读与定量分析两个角度对比了其与QA60法、Cloud-Score算法以及Fmask的云检测精度，并在海南岛和亚马逊森林两个地区进行了云检测测试。研究结果表明：Fmask模型的云检测性能最低，总体精度仅为63.45%，存在严重的水体误分为云的现象，但其漏提率极低；QA60法对卷云识别不足，漏提率较高，同时存在一定的误分现象，并且低空间分辨率影响了云体边界提取结果的细节性；Cloud-Score算法的云检测性能明显好于QA60法，总体精度达到了89.83%，误提率仅为2.17%，但仍存在部分卷云漏提的现象；相比于其他3种云检测方法，本文提出的云检测模型总体精度最高，达到了98.21%，并且拥有极低的漏提率和误提率，能比较精准地识别出云体的边界，可满足Sentinel-2遥感产品的云检测预处理需求。

关键词： 云检测; SVM; Cloud-Score算法; Sentinel-2; Fmask

Abstract:

Cloud coverage hinders the effective range of earth observation by optical remote sensing satellite. Rapid and accurate cloud detection is an important step in the product generation process of remote sensing application. In view of the lack of suitable and high-quality cloud detection model in Google Earth Engine cloud platform， this study takes tropical cloudy Sri Lanka as the study area， constructs a Sentinel-2 image cloud detection model coupled with SVM and Cloud-Score algorithm. Through experiments， the cloud detection accuracy of this method is compared with that of QA60 method， Cloud-Score algorithm and Fmask from the point of view of visual interpretation and quantitative analysis. The results show that the cloud detection performance of Fmask model is the lowest， and the overall accuracy is only 63.45%. It has a serious phenomenon that water body is mistakenly divided into clouds， but its omission error is very low. The QA60 method has insufficient recognition of cirrus clouds， and the omission error is high. At the same time， it has a certain phenomenon of misclassification， and the low spatial resolution affects the details of cloud boundary extraction results. The cloud detection performance of the Cloud-Score algorithm is obviously better than that of the QA60 method， the overall accuracy is 89.83%， and the commission error is only 2.17%， but there is still a phenomenon that some cirrus clouds are missed. Compared with the other three cloud detection methods， the cloud detection model proposed in this study has the highest overall accuracy， reaching 98.21%， and has extremely low omission error and commission error. The model can accurately identify the boundary of the cloud， and can meet the cloud detection preprocessing requirements of Sentinel-2 remote sensing products.

Key words: Cloud detection SVM Cloud-Score algorithm Sentinel-2 Fmask

收稿日期: 2021-04-17 出版日期: 2022-08-25

ZTFLH:

P407

基金资助: 国家重点研发项目(2019YFE0126500);高分辨率对地观测系统国家重大专项(21?Y20B01?9001?19/22);陕西地建—西安交大土地工程与人居环境技术创新中心开放基金资助项目(2021WHZ0090);陕西省土地工程建设集团内部科研项目(DJNY 2022?29);中央高校基本科研业务费资助项目(300102352502)

通讯作者: 叶虎平 E-mail: ljf_sxdj@126.com;yehp@igsnrr.ac.cn

作者简介: 李健锋(1994-),男，浙江义乌人，硕士，工程师，主要从事定量遥感研究。E?mail:ljf_sxdj@126.com

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李健锋
	刘思琪
	李劲彬
	彭飚
	叶虎平

引用本文:

李健锋,刘思琪,李劲彬,彭飚,叶虎平. 耦合SVM和Cloud-Score算法的Sentinel-2影像云检测模型研究[J]. 遥感技术与应用, 2022, 37(3): 713-720.

Jianfeng Li,Siqi Liu,Jinbin Li,Biao Peng,Huping Ye. Research on Cloud Detection Model of Sentinel-2 Image Coupled with SVM and Cloud-Score Algorithm. Remote Sensing Technology and Application, 2022, 37(3): 713-720.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2022.3.0713 或 http://www.rsta.ac.cn/CN/Y2022/V37/I3/713

图1 研究区位置

表1 影像具体信息

图2 耦合SVM和Cloud-Score算法的云检测模型

图3 不同模型云检测结果

表2 不同模型云检测精度

表3 影像具体信息

图4 云检测结果

1	Foga S， Scaramuzza P L， Guo S， et al. Cloud detection algorithm comparison and validation for operational Landsat data products［J］. Remote Sensing of Environment， 2017， 194： 379-390. DOI： 10.1016/j.rse.2017.03.026 . doi: 10.1016/j.rse.2017.03.026
2	Li Z， Shen H， 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. DOI： 10.1016/j.isprsjprs.2019.02.017 . doi: 10.1016/j.isprsjprs.2019.02.017
3	Sun L， Yang X， Jia S， et al. Satellite data cloud detection using deep learning supported by hyperspectral data［J］. International Journal of Remote Sensing， 2020， 41（4）： 1349-1371. DOI： 10.1080/01431161.2019.1667548 . doi: 10.1080/01431161.2019.1667548
4	Wang C， Liu Y， Guo L， et al. A smart agricultural service platform for crop planting， monitoring and management-PIE-engine landscape［C］∥ 2021 9th International Conference on Agro-Geoinformatics （Agro-Geoinformatics）. IEEE， 2021： 1-6.DOI：10.1109/Agro-Geoinformatics50104.2021.9530347 . doi: 10.1109/Agro-Geoinformatics50104.2021.9530347
5	Gorelick N， Hancher M， Dixon M， et al. Google Earth Engine： Planetary-scale geospatial analysis for everyone［J］. Remote sensing of Environment， 2017， 202： 18-27. DOI： 10.1016/j.rse.2017.06.031 . doi: 10.1016/j.rse.2017.06.031
6	Xiong J， Thenkabail P S， Gumma M K， et al. Automated cropland mapping of continental Africa using Google Earth Engine cloud computing［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2017， 126： 225-244. DOI： 10.1016/j.isprsjprs.2017.01.019 . doi: 10.1016/j.isprsjprs.2017.01.019
7	Carrasco L， O’Neil A W， Morton R D， et al. Evaluating combinations of temporally aggregated Sentinel-1， Sentinel-2 and Landsat 8 for land cover mapping with Google Earth Engine［J］. Remote Sensing， 2019， 11（3）： 288. DOI： 10.3390/rs11030288 . doi: 10.3390/rs11030288
8	Wang L， Diao C， Xian G， et al. A summary of the special issue on remote sensing of land change science with Google Earth Engine［J］. 2020，248：112002. DOI：10.1016/j.rse. 2020.112002 . doi: 10.1016/j.rse. 2020.112002
9	ESA. Level-1C Cloud Masks-Sentinel-2 MSI Technical Guide-Sentinel Online［EB/OL］..
10	Housman I W， Chastain R A， Finco M V. An evaluation of forest health insect and disease survey data and satellite-based remote sensing forest change detection methods： Case studies in the United States［J］. Remote Sensing， 2018， 10（8）： 1184. DOI： 10.3390/rs10081184 . doi: 10.3390/rs10081184
11	Research EO. Cloud Masks at Your Service［EB/OL］. .
12	Clerc S， Devignot O， Pessiot L. S2 MPC data quality report［R］. 2015.
13	Coluzzi R， Imbrenda V， Lanfredi M， et al. A first assessment of the Sentinel-2 Level 1-C cloud mask product to support informed surface analyses［J］. Remote Sensing of Environment， 2018， 217： 426-443. DOI： 10.1016/j.rse.2018.08.009 . doi: 10.1016/j.rse.2018.08.009
14	Nguyen M D， Baez-Villanueva O M， Bui D D， et al. Harmonization of Landsat and Sentinel 2 for crop monitoring in drought prone areas： Case studies of Ninh Thuan （Vietnam） and Bekaa （Lebanon）［J］. Remote Sensing，2020，12（2）：281. DOI： 10.3390/rs12020281 . doi: 10.3390/rs12020281
15	Qiu S， Zhu Z， He B. Fmask 4.0： Improved cloud and cloud shadow detection in Landsats 4-8 and Sentinel-2 imagery［J］. Remote Sensing of Environment， 2019， 231： 111205. DOI： 10.1016/j.rse.2019.05.024 . doi: 10.1016/j.rse.2019.05.024
16	Main-Knorn M， Pflug B， Louis J， et al. Sen2Cor for Sentinel-2［C］∥ Image and Signal Processing for Remote Sensing XXIII. International Society for Optics and Photonics， 2017， 10427： 1042704. DOI： 10.1117/12.2278218 . doi: 10.1117/12.2278218
17	Hagolle O， Huc M， Auer S， et al. MAJA algorithm theoretical basis document［R］. 2017.
18	Zupanc A. Improving cloud detection with machine learning［R］. 2017.
19	Ke G， Meng Q， Finley T， et al. Lightgbm： A highly efficient gradient boosting decision tree［J］. Advances in Neural Information Processing Systems，2017，30：3146-3154. DOI：10.1080/09512748.2017.1375000 . doi: 10.1080/09512748.2017.1375000
20	Chung C. What are the strategic and economic implications for South Asia of China's Maritime Silk Road initiative？［J］. The Pacific Review，2018，31（3）：315-332. DOI： 10.1080/0951 2748.2017.1375000 . doi: 10.1080/0951 2748.2017.1375000
21	Drusch M， Del Bello U， Carlier S， et al. Sentinel-2： ESA's optical high-resolution mission for GMES operational services［J］. Remote Sensing of Environment，2012，120：25-36. DOI： 10.1016/j.rse.2011.11.026 . doi: 10.1016/j.rse.2011.11.026
22	Sanchez A H， Picoli M C A， Camara G， et al. Comparison of Cloud cover detection algorithms on Sentinel-2 images of the amazon tropical forest［J］. Remote Sensing， 2020， 12（8）： 1284. DOI： 10.3390/rs12081284 . doi: 10.3390/rs12081284
23	Li Jianfeng， Ye Huping， Zhang Zongke， et al. Spatiotemporal change analysis of Sri Lanka inland water based on Landsat imagery［J］. Geo-Information Science， 2019，21 （5）：781-8.
23	李健锋，叶虎平，张宗科，等. 基于Landsat影像的斯里兰卡内陆湖库水体时空变化分析［J］. 地球信息科学学报，2019，21（5）：781-788.
24	Deng Naiyang， Tian Yingjie. A new method of data mining-support vector machine［M］. Beijing：Science Publication， 2004.
24	邓乃扬，田英杰. 数据挖掘中的新方法：支持向量机［M］. 北京：科学出版社， 2004.
25	Guo Y， Jia X， Paull D. Effective sequential classifier training for SVM-based multitemporal remote sensing image classification［J］. IEEE Transactions on Image Processing， 2018， 27（6）： 3036-3048. DOI： 10.1109/TIP.2018.2808767 . doi: 10.1109/TIP.2018.2808767
26	Shaharum N S N， Shafri H Z M， Ghani W A W A K， et al. Oil palm mapping over Peninsular Malaysia using Google Earth Engine and machine learning algorithms［J］. Remote Sensing Applications： Society and Environment， 2020， 17： 100287. DOI： 10.1016/j.rsase.2020.100287 . doi: 10.1016/j.rsase.2020.100287
27	Hsu C W， Chang C C， Lin C J. A practical guide to support vector classification［R］. Department of Computer Science，2003.
28	Baetens L， Desjardins C， Hagolle O. Validation of copernicus Sentinel-2 cloud masks obtained from MAJA， Sen2Cor， and FMask processors using reference cloud masks generated with a supervised active learning procedure［J］. Remote Sensing， 2019， 11（4）： 433. DOI： 10.3390/rs11040433 . doi: 10.3390/rs11040433
29	Congalton R G. A review of assessing the accuracy of classifications of remotely sensed data［J］. Remote Sensing of Environment， 1991， 37（1）： 35-46. DOI： 10.1016/0034-4257（91）90048-B . doi: 10.1016/0034-4257（91）90048-B

[1]	杨立娟,张建霞,林木生. 中国东部沿海四省一市PM_2.5浓度遥感估算方法研究[J]. 遥感技术与应用, 2021, 36(6): 1408-1415.
[2]	陈彦四,黄春林,侯金亮,韩伟孝,冯娅娅,李翔华,王静. 基于多时相Sentinel-2影像的黑河中游玉米种植面积提取研究[J]. 遥感技术与应用, 2021, 36(2): 324-331.
[3]	尹燕旻,贾立. 基于Sentinel-2的闪电河流域农作物分类研究[J]. 遥感技术与应用, 2021, 36(2): 400-410.
[4]	牟昱璇,邬明权,牛铮,黄文江,杨尽. 南方地区复杂条件下的耕地面积遥感提取方法[J]. 遥感技术与应用, 2020, 35(5): 1127-1135.
[5]	王明,刘正佳,陈元琰. 基于Sentinel-2波段/产品的图像云检测效果对比研究[J]. 遥感技术与应用, 2020, 35(5): 1167-1177.
[6]	李宏达,高小红,汤敏. 基于CNN的不同空间分辨率影像土地覆被分类研究[J]. 遥感技术与应用, 2020, 35(4): 749-758.
[7]	杨瑞,祁元,苏阳. 深度学习U-Net方法及其在高分辨卫星影像分类中的应用[J]. 遥感技术与应用, 2020, 35(4): 767-774.
[8]	李萌,年雁云,边瑞,白艳萍,马金辉. 基于多源遥感影像的青海云杉和祁连圆柏分类[J]. 遥感技术与应用, 2020, 35(4): 855-863.
[9]	李净,温松楠. 基于3种机器学习法的太阳辐射模拟研究[J]. 遥感技术与应用, 2020, 35(3): 615-622.
[10]	张永宏,杨晨阳,陶润喆,王剑庚,田伟. 基于FY-4A数据的青藏高原多时相云检测方法[J]. 遥感技术与应用, 2020, 35(2): 389-398.
[11]	束美艳,顾晓鹤,孙林,朱金山,陈婷婷,王凯,王权,杨贵军. 先验终端像元库支持下的GF-4多光谱影像自动云检测[J]. 遥感技术与应用, 2020, 35(1): 194-201.
[12]	梁丽娟, 黄万里张容焱, 林广发, 彭俊超, 梁春阳. Sentinel-2卫星影像融合方法与质量评价分析[J]. 遥感技术与应用, 2019, 34(3): 612-621.
[13]	徐凡, 张雪红, 石玉立. 基于激光雷达和航拍影像的城市地物分类研究[J]. 遥感技术与应用, 2019, 34(2): 253-262.
[14]	丁海宁. 黄土高原土壤铁元素含量遥感反演方法 [J]. 遥感技术与应用, 2019, 34(2): 275-283.
[15]	高书鹏, 史正涛, 刘晓龙, 柏延臣. 基于高时空分辨率可见光遥感数据的热带山地橡胶林识别[J]. 遥感技术与应用, 2018, 33(6): 1122-1131.

Viewed

Full text

Abstract

Cited

Shared

Discussed