浏览全部资源
扫码关注微信
Published： 07 January 2023 ，
扫 描 看 全 文
杨彬，郭金源，何鹏，叶小敏，刘建强.2023.面向HY-1C卫星CZI陆地遥感图像的云检测方法研究.遥感学报，27（1）： 55-67
Yang B，Guo J Y，He P，Ye X M and Liu J Q. 2023. Research on cloud detection for HY-1C CZI remote sensing images collected over lands. National Remote Sensing Bulletin， 27（1）：55-67
搭载在中国首颗海洋水色业务卫星HY-1C上的海岸带成像仪CZI（Coast Zone Imager）于2019年6月开始业务化运行，其获取的大量海岸带、陆地和海洋数据对于海洋灾害与环境监测研究具有重要意义。CZI对地观测受云干扰，影响数据的后续应用。现有的云检测算法大都基于RGB图像或者包含热红外的多光谱展开，对于HY-1C CZI这类RGB-近红外4个波段遥感图像研究较少。为此，本文提出了一种针对HY-1C CZI遥感图像的非监督遥感图像云检测方法。该方法包含训练样本选择、特征提取、支持向量机SVM（Support Vector Machine）分类和后处理这4个过程。在训练样本选择中，结合暗通道反射率、归一化植被指数和白度指数，提出了一种训练样本自动提取算法。该算法使用白度指数作为遥感图像细节信息提取数据源，并通过逐步细化过程精确提取样本。针对特征提取，选取图像的空—谱特征信息，包含反射率、光谱指数、纹理和结构特征，使云与非云区域的差异最大化。基于自动提取的训练样本及其特征描述，采用SVM对CZI遥感数据进行初分类，并在此基础上进行导向滤波、孔洞填充和几何判断后处理，以获取云检测结果。该算法的优势在于：（1）无需人工标注即可自动获取训练样本；（2）能够充分利用近红外波段信息。本文将该算法运用于植被、土壤、湿地和冰雪场景这4种典型场景中，并与目前流行的非监督云检测算法对比分析。相较于其他云检测算法，定性分析结果表明本文云检测结果与人工标注的云分布真实图具有较好的一致性；定量结果表明本文提出的算法在各个场景上都具有最低的错误率。通过以上对比分析，表明本文提出的云检测算法在不同的场景下识别结果都更加准确，证明了本文算法对于HY-1C CZI陆地遥感图像云检测的有效性。
The Coast Zone Imager (CZI) onboard the Chinese first marine aqua-color satellite HY-1C started operational operations in June 2019. The data acquired by CZI have the characteristics of medium resolution
large width and high revisit period and taking into account the requirements of ocean water color
terrestrial ecology and polar glaciers. Therefore
the large amount of coastal
land
and ocean data acquired by CZI is of great significance for marine disaster and environmental monitoring research. However
related studies have shown that clouds cover an average of 68% of the earth's surface. CZI data is severely affected by cloud
which will then have a strong impact on its subsequent applications. The effective identification of clouds in remote sensing images is extremely important for the application of CZI images. Most of the existing cloud detection algorithms are based on RGB images or multi-spectral images including thermal infrared band. There are few researches on cloud detection algorithms for RGB-NIR four-band remote sensing images
such as HY-1C CZI. The objective of this paper is thus to propose an unsupervised cloud detection method for HY-1C CZI remote sensing images that makes full use of NIR band information. The method includes four processes: training samples selection
feature extraction
Support Vector Machine (SVM) classification
and post-processing. In the selection of training samples
combining dark channel reflectivity
normalized vegetation index and whiteness index of the image
this paper proposes an automatic training sample extraction algorithm
which uses the whiteness index to obtain detail information
and accurately extract cloud/non-cloud samples through a gradual refinement process. For feature extraction
the spatial spectrum feature information of CZI remote sensing image is selected
including reflectance
spectral index
texture and structure features
to characterize remote sensing image features
and maximize the feature difference between cloud and non-cloud regions. Based on the above automatically extracted sample and its feature description
SVM is used to initially classify the CZI remote sensing data
and then the guided filtering
hole filling and geometric judgment post-processing are performed to obtain the final high-precision cloud detection results. This paper applies the algorithm to four typical scenarios (vegetation
soil
wetland
and ice and snow scenarios)
and compares and analyzes it with the currently popular unsupervised cloud detection algorithms. Compared with other cloud detection algorithms
the qualitative analysis results show that the cloud detection results in this paper are in good agreement with real cloud distribution image labeled by human. In addition
the most commonly used error rate metric is also used to quantitatively evaluate the cloud detection results. It shows that the error rates of the proposed algorithm in vegetation
soil
wetland
ice and snow scenes are 0.027
0.064
0.026
and 0.049
respectively; and that has the lowest error rate in four scenarios. Through the above comparative analysis
the detection results of the proposed algorithm in different scenarios are more accurate
which demonstrates the effectiveness of the proposed algorithm for cloud detection from HY-1C CZI data.
HY-1C海岸带成像仪云检测白度指数非监督
HY-1CCoast Zone Imager (CZI)cloud detectionwhiteness indexunsupervised
An Z Y and Shi Z W. 2015. Scene learning for cloud detection on remote-sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(8): 4206-4222 [DOI: 10.1109/JSTARS.2015.2438015http://dx.doi.org/10.1109/JSTARS.2015.2438015]
Cheng Y, Sun Y, Peng L, He Y and Zha M. 2022. An Improved Retrieval Method for Porphyra Cultivation Area Based on Suspended Sediment Concentration. Remote Sensing, 14(17): 4338 [DOI: 10.3390/rs14174338http://dx.doi.org/10.3390/rs14174338]
Choi Y-J, Ban H-J, Han H-J and Hong S. 2022. A Maritime Cloud-Detection Method Using Visible and Near-Infrared Bands over the Yellow Sea and Bohai Sea. Remote Sensing, 14(3): 793[DOI: 10.3390/rs14030793http://dx.doi.org/10.3390/rs14030793]
Deng C W, Li Z, Wang W Z, Wang S G, Tang L B and Bovik A C. 2019. Cloud detection in satellite images based on natural scene statistics and Gabor features. IEEE Geoscience and Remote Sensing Letters, 16(4): 608-612 [DOI: 10.1109/LGRS.2018.2878239http://dx.doi.org/10.1109/LGRS.2018.2878239]
Duan P，Zhang F and Liu C J. 2022. Extraction of the impervious surface of typical cities in Xinjiang based on Sentinel-2A/B and spatial difference analysis. National Remote Sensing Bulletin，26(7)： 1469-1482
段潘， 张飞， 刘长江. 2022. 基于 Sentinel-2A/B 的新疆典型城市不透水面提取及空间差异分析. 遥感学报，26(7): 1469-1482 [DOI： 10.11834/jrs.20210174http://dx.doi.org/10.11834/jrs.20210174]
Farbman Z, Fattal R, Lischinski D and Szeliski R. 2008. Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Transactions on Graphics, 27(3): 1-10 [DOI: 10.1145/1360612.1360666http://dx.doi.org/10.1145/1360612.1360666]
Gomez-Chova L, Camps-Valls G, Calpe-Maravilla J, Guanter L and Moreno J. 2007. Cloud-screening algorithm for ENVISAT/MERIS multispectral images. IEEE Transactions on Geoscience and Remote Sensing, 45(12): 4105-4118 [DOI: 10.1109/TGRS.2007.905312http://dx.doi.org/10.1109/TGRS.2007.905312]
Guo J, Yang J, Yue H and Li K. 2022. Unsupervised Domain Adaptation for Cloud Detection Based on Grouped Features Alignment and Entropy Minimization. IEEE Transactions on Geoscience and Remote Sensing, 60: 1-13 [DOI: 10.1109/tgrs.2021.3067513http://dx.doi.org/10.1109/tgrs.2021.3067513]
He K M, Sun J and Tang X O. 2011. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12): 2341-2353 [DOI: 10.1109/TPAMI.2010.168http://dx.doi.org/10.1109/TPAMI.2010.168]
Kang X D, Gao G H, Hao Q B and Li S T. 2019. A coarse-to-fine method for cloud detection in remote sensing Images. IEEE Geoscience and Remote Sensing Letters, 16(1): 110-114 [DOI: 10.1109/LGRS.2018.2866499http://dx.doi.org/10.1109/LGRS.2018.2866499]
Li J J，Cao J N，Zhu Y Y and Cheng B B. 2020. Built-up area detection from high resolution remote sensing images using geometric features. Journal of Remote Sensing, 24(3)： 233-244
李军军， 曹建农， 朱莹莹， 程贝贝. 2020. 高分辨率遥感影像建筑区域局部几何特征提取. 遥感学报， 24(3)： 233-244 [DOI： 10.11834/jrs.20208506http://dx.doi.org/10.11834/jrs.20208506]
Li Z W, Shen H F, Li H F, Xia G S, Gamba P and Zhang L P. 2017. Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imagery. Remote Sensing of Environment, 191: 342-358 [DOI: 10.1016/j.rse.2017.01.026http://dx.doi.org/10.1016/j.rse.2017.01.026]
Liang C, Liu L, Liu J Q, Zou B, Zou Y R and Cui S X. 2020. Extracting mangrove information using MNF transformation based on HY-1C CZI spectral indices reconstruction data. Haiyang Xuebao, 42(4): 104-112
梁超, 刘利, 刘建强, 邹斌, 邹亚荣, 崔松雪. 2020. 基于HY-1C CZI影像光谱指数重构数据MNF变换的红树林提取. 海洋学报, 42(4): 104-112 [DOI: 10.3969/j.issn.0253-4193.2020.04.012http://dx.doi.org/10.3969/j.issn.0253-4193.2020.04.012]
Lin C-H, Lin B-Y, Lee K-Y and Chen Y-C. 2015. Radiometric normalization and cloud detection of optical satellite images using invariant pixels. ISPRS Journal of Photogrammetry and Remote Sensing, 106: 107-117 [DOI: 10.1016/j.isprsjprs.2015.05.003http://dx.doi.org/10.1016/j.isprsjprs.2015.05.003]
Liu J Q, Zeng T, Liang C, Zou Y R, Ye X M, Ding J, Zou B, Shi L J and Guo M H. 2020. Satellite HY-1C and its applications in monitoring of natural disasters. Satellite Application, (6): 26-34
刘建强, 曾韬, 梁超, 邹亚荣, 叶小敏, 丁静, 邹斌, 石立坚, 郭茂华. 2020. 海洋一号C卫星在自然灾害监测中的应用. 卫星应用, (6): 26-34 [DOI: 10.3969/j.issn.1674-9030.2020.06.008http://dx.doi.org/10.3969/j.issn.1674-9030.2020.06.008]
Liu J C，Liu J Q，Ding J and Lu Y C. 2022. A refined imagery algorithm to extract green tide in the Yellow Sea from HY-1C satellite CZI measurements[J]. Haiyang Xuebao， 44(5)： 1-11
刘锦超, 刘建强, 丁静, 陆应诚. 2022. HY-1C卫星CZI 载荷的黄海绿潮提取研究. 海洋学报, 44(5): 1-11 [DOI: 10.12284/hyxb2022097http://dx.doi.org/10.12284/hyxb2022097]
Luo S, Li H F and Shen H F. 2020. Deeply supervised convolutional neural network for shadow detection based on a novel aerial shadow imagery dataset. ISPRS Journal of Photogrammetry and Remote Sensing, 167: 443-457 [DOI: 10.1016/j.isprsjprs.2020.07.016http://dx.doi.org/10.1016/j.isprsjprs.2020.07.016]
Mahajan S and Fataniya B. 2019. Cloud detection methodologies: variants and development—A review. Complex & Intelligent Systems, 6(2): 251-261 [DOI: 10.1007/s40747-019-00128-0http://dx.doi.org/10.1007/s40747-019-00128-0]
Otsu N. 1979. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1): 62-66 [DOI: 10.1109/TSMC.1979.4310076http://dx.doi.org/10.1109/TSMC.1979.4310076]
Peng L K, Liu L C, Chen X H, Chen J, Cao X and Qiu Y A. 2021. Generalization ability of cloud detection network for satellite imagery based on DeepLabv3+. National Remote Sensing Bulletin, 25(5): 1169-1186
彭龙康, 刘励聪, 陈学泓, 陈晋, 曹鑫, 邱岳安. 2021. 遥感影像云检测网络泛化性能研究: 以DeepLabv3+为例. 遥感学报, 25(5): 1169-1186 [DOI: 10.11834/jrs.20210061http://dx.doi.org/10.11834/jrs.20210061]
Ping B, Su F Z and Meng Y S. 2020. A cloud and cloud shadow detection method based on fuzzy c-means algorithm. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 1714-1727 [DOI: 10.1109/JSTARS.2020.2987844http://dx.doi.org/10.1109/JSTARS.2020.2987844]
Shen Y F, Liu J Q, Ding J, Jiao J N, Sun S J and Lu Y C. 2020. HY-1C COCTS and CZI observation of marine oil spills in the South China Sea. Journal of Remote Sensing, 24(8): 933-944
沈亚峰, 刘建强, 丁静, 焦俊男, 孙绍杰, 陆应诚. 2020. 海洋一号C星光学载荷对海面溢油的识别能力分析. 遥感学报, 24(8): 933-944 [DOI: 10.11834/jrs.20209475http://dx.doi.org/10.11834/jrs.20209475]
Sui S M，Jia S F and Hu X Q. 2022. Improvement of unified sample cloud detection technology and its application in GF-6 WFV cloud detection. National Remote Sensing Bulletin，26(4)：646-656
隋淞蔓， 夹尚丰， 胡学谦. 2022. 统一样本云检测技术在GF-6 WFV上的改进与应用. 遥感学报，26(4)： 646-656 [DOI： 10.11834/jrs.20220352http://dx.doi.org/10.11834/jrs.20220352]
Stubenrauch C J, Rossow W B, Kinne S, Ackerman S, Cesana G, Chepfer H, Di Girolamo L, Getzewich B, Guignard A, Heidinger A, Maddux B C, Menzel W P, Minnis P, Pearl C, Platnick S, Poulsen C, Riedi J, Sun-Mack S, Walther A, Winker D, Zeng S and Zhao G. 2013. Assessment of global cloud datasets from satellites: project and database initiated by the GEWEX radiation panel. Bulletin of the American Meteorological Society, 94(7): 1031-1049 [DOI: 10.1175/BAMS-D-12-00117.1http://dx.doi.org/10.1175/BAMS-D-12-00117.1]
Wang J J，Liu S H，Li S，Ye S, Wang X Q and Wang F Y. 2021. Optimization Algorithm for Polarization Remote Sensing Cloud Detection Based on Machine Learning［J］. Acta Photonica Sinica，50(2): 174-182
汪杰君, 刘少晖, 李树, 叶松, 王新强, 王方原. 2021. 基于机器学习的偏振遥感云检测优化算法.光子学报, 50(2): 174-182 [DOI: 10.3788/gzxb20215002.022A8001http://dx.doi.org/10.3788/gzxb20215002.022A8001]
Wang Y Y，Ma J J，Li J H，Hong J and Li Z Q. 2022. Review of cloud polarimetric remote sensing. National Remote Sensing Bulletin，26(5)： 852-872
王宇瑶， 麻金继， 李婧晗， 洪津， 李正强. 2022. 云偏振遥感综述. 遥感学报，26(5)： 852-872 [DOI： 10.11834/jrs.20221404http://dx.doi.org/10.11834/jrs.20221404]
Wang L M, Liu J, Gao J M, Yao B M, Yang F G and Zou J Q. 2019. Winter wheat early identification based on HY-1C/CZI data. Chinese Agricultural Science Bulletin, 35(33): 151-157
王利民, 刘佳, 高建孟, 姚保民, 杨福刚, 邹金秋. 2019. 基于HY-1C/CZI数据的冬小麦早期识别研究. 中国农学通报, 35(33): 151-157 [DOI: 10.11924/j.issn.1000-6850.casb20190600232http://dx.doi.org/10.11924/j.issn.1000-6850.casb20190600232]
Xie F Y, Shi M Y, Shi Z W, Yin J H and Zhao D P. 2017. Multilevel cloud detection in remote sensing images based on deep learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(8): 3631-3640 [DOI: 10.1109/JSTARS.2017.2686488http://dx.doi.org/10.1109/JSTARS.2017.2686488]
Xu L, Yan Q, Xia Y and Jia J Y. 2012. Structure extraction from texture via relative total variation. ACM Transactions on Graphics, 31(6): 139 [DOI: 10.1145/2366145.2366158http://dx.doi.org/10.1145/2366145.2366158]
Xu S Z and Zhong L X. 2021. Application of deep learning in cloud detection of remote sensing imagery. Remote Sensing Information, 36(3): 129-134
徐少壮, 钟来星. 2021. 深度学习在遥感影像云检测中的应用. 遥感信息, 36(3): 129-134 [DOI: 10.3969/j.issn.1000-3177.2021.03.018http://dx.doi.org/10.3969/j.issn.1000-3177.2021.03.018]
Yao Z, Jia J and Qian Y. 2020. MCNet: multi-scale feature extraction and content-aware reassembly cloud detection model for remote sensing images. Symmetry, 13(1): 28 [DOI: 10.3390/sym13010028http://dx.doi.org/10.3390/sym13010028]
Zang J X，Liu J Q，Yin X B, Zeng T and Zhou L. 2022. Study on sea ice classification of HY-1C satellite coastal zone imager images based on the optimal feature se. Haiyang Xuebao，44(5)： 35-46
臧金霞, 刘建强, 殷晓斌, 曾韬, 周磊. 2022. 基于最优特征集的 HY-1C卫星海岸带成像仪影像海冰分类方法研究. 海洋学报, 44(5): 35-46 [DOI: 10.12284/hyxb2022021http://dx.doi.org/10.12284/hyxb2022021]
Zhang B, Hu Y D and Hong J. 2021. Cloud detection of remote sensing images based on H-SVM with multi-feature fusion. Journal of Atmospheric and Environmental Optics, 16(1): 58-66
张波, 胡亚东, 洪津. 2021. 基于多特征融合的层次支持向量机遥感图像云检测. 大气与环境光学学报, 16(1): 58-66 [DOI: 10.3969/j.issn.1673-6141.2021.01.006http://dx.doi.org/10.3969/j.issn.1673-6141.2021.01.006]
Zhang C, Zhang X Z and Yang C J. 2021. Remote sensing image cloud and cloud shadow detection method based on RDA-net model. Laser and Optoelectronics Progress, 58(20): 498-508
张晨, 张秀再, 杨昌军. 2021. 基于RDA-Net模型的遥感影像云与云阴影检测方法. 激光与光电子学进展, 58(20): 498-508 [DOI: 10.3788/LOP202158.2028005http://dx.doi.org/10.3788/LOP202158.2028005]
Zhang Q and Xiao C. 2014. Cloud detection of RGB color aerial photographs by progressive refinement scheme. IEEE Transactions on Geoscience and Remote Sensing, 52(11): 7264-7275 [DOI: 10.1109/TGRS.2014.2310240http://dx.doi.org/10.1109/TGRS.2014.2310240]
Zhai H, Zhang H, Zhang L and Li P. 2018. Cloud/shadow detection based on spectral indices for multi/hyperspectral optical remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 144: 235-253 [DOI: 10.1016/j.isprsjprs.2018.07.006http://dx.doi.org/10.1016/j.isprsjprs.2018.07.006]
Zhou Q, Liu J Q, Wang J R, Deng S Q and Tian L Q. 2020. Water turbidity monitoring of Zhiyin and Huangjia Lakes in Wuhan for COVID-19 epidemic using HY-1C CZI Data. Geomatics and Information Science of Wuhan University, 45(5): 676-681
周屈, 刘建强, 王剑茹, 邓实权, 田礼乔. 2020. 利用HY-1C卫星CZI数据在COVID-19疫情期间武汉知音湖和黄家湖的浊度监测研究. 武汉大学学报(信息科学版), 45(5): 676-681 [DOI: 10.13203/j.whugis20200101http://dx.doi.org/10.13203/j.whugis20200101]
Zhu Z, Wang S X and Woodcock C E. 2015. Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4-7, 8, and Sentinel 2 images. Remote Sensing of Environment, 159: 269-277 [DOI: 10.1016/j.rse.2014.12.014http://dx.doi.org/10.1016/j.rse.2014.12.014]
Zhu Z and Woodcock C E. 2012. Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sensing of Environment, 118: 83-94 [DOI: 10.1016/j.rse.2011.10.028http://dx.doi.org/10.1016/j.rse.2011.10.028]
相关文章
相关作者
相关机构
京公网安备11010802024621