Considering that traditional cloud detection methods are difficult to apply to high spatial resolution satellite remote sensing images, this paper employs deep learning to carry out pixel-level cloud detection research for SPOT6/7 satellite remote sensing images. Firstly, a practical software named as CloudLabel was developed based on the cloud labeling method of region growing to build accurate and reasonable datasets for model training and testing. Cloud Label integrates multiple morphological processing methods, which could effectively preserve the edge details of cloud areas. Compared with the existing Labelme labeling CloudLabel improves the pixel-level cloud detection accuracy by 3%. Secondly, the involution module was introduced into the original DeeplabV3+ model, and combined with the Poly learning rate change strategy, a cloud detection method based on the RedNet-DeeplabV3+ model was proposed. Experimental results demonstrated that the proposed method outperformed other deep learning network models such as DeeplabV3+, U-net and DANet, achieving a cloud detection accuracy of over 93%. In addition, to verify the universality of the proposed method, cloud detection was performed on other types of high spatial resolution remote sensing images such as aerial photos and geographic information system data, and the recognition accuracy exceeded 87.2%.
KingM D, PlatnickS, MenzelW P,et al.Spatial and temporal distribution of clouds observed by MODIS onboard the terra and aqua satellites[J].IEEE Trans Geosci Remote Sens,2013,51(7):3826-3852.
[2]
宫鹏.遥感科学与技术中的一些前沿问题[J].遥感学报,2009,13(1):13-23.
[3]
GONGPeng.Some essential questions in remote sensing science and technology[J].Journal of Remote Sensing,2009,13(1):13-23.(in Chinese)
[4]
PuissantA, HirschJ, WeberC.The utility of texture analysis to improve per pixel classification for high to very high spatial resolution imagery[J].Int J Remote Sens,2005,26(4):733-745.
[5]
PlatnickS, KingM D, AckermanS A,et al.The MODIS cloud products:algorithms and examples from terra[J].IEEE Trans Geosci Remote Sens,2003,41(2):459-473.
GUOWenxin, CHEHuizheng, CHENQuanliang,et al.Comparison and analysis of cloud optical properties over Beijing based on satellite data and sky radiometer[J].Desert and Oasis Meteorology,2021,15(6):95-102.(in Chinese)
TANKai, ZHANGYongjun, TONGXin,et al.Automatic cloud detection for Chinese high resolution remote sensing satellite imagery[J].Acta Geodaetica et Cartographica Sinica,2016,45(5):581-591.(in Chinese)
[10]
康一飞.光学遥感卫星影像云检测方法及应用[D].武汉:武汉大学,2018.
[11]
KANGYifei.Methods and applications of cloud detection for optical remote sensing satellite imagery[D].Wuhan:Wuhan University,2018.(in Chinese)
JIALiangliang, WANGXiaoqin, WANGFeng.Cloud detection based on band operation texture feature for GF-1 multispectral data[J].Remote Sensing Information,2018,33(5):62-68.(in Chinese)
ZHANGYong, LIUHui, ZHENGYingfei,et al.Effect validation and analysis of classified products outputted by artificial intelligent nowcasting model[J].Desert and Oasis Meteorology,2023,17(1):115-121.(in Chinese)
YUANKai, PANGJing, LIWujie,et al.Application evaluation of deep learning models in radar echo nowcasting in Wuhan in flood season of 2021[J].Journal of Arid Meteorology,2023,41(1):173-185.(in Chinese)
CHENYang, FANRongshuang, WANGJingxue,et al.Cloud detection of ZY-3 satellite remote sensing images based on deep learning[J].Acta Optica Sinica,2018,38(1):0128005.(in Chinese)
[20]
SHIM Y, XIEF Y, ZIY.Cloud detection of remote sensing images by deep learning[C]//Proceedings of 2016 IEEE International Geoscience and Remote Sensing Symposium.Beijing:IEEE,2016:701-704.
LIUBo, DENGJuan, SONGYang,et al.Cloud detection method for high-resolution remote sensing image based on convolutional neural network[J].Geospatial Information,2017,15(11):12-15.(in Chinese)
[23]
MohajeraniS, KrammerT A, SaeediP.A cloud detection algorithm for remote sensing images using fully convolutional neural networks[C]//Proceedings of IEEE 20th International Workshop on Multimedia Signal Processing.Vancouver:IEEE,2018:1-5.
HUANGJing, SHEYong, FANYujiang.Case analysis of deep learning methods for predicting radar echoes of hail clouds in Aksu region[J].Desert and Oasis Meteorology,2024,18(2):107-113.(in Chinese)
[26]
CHENL C, PapandreouG, KokkinosI,et al.DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution and fully connected CRFs[J].IEEE Trans Pattern Anal Mach Intell,2018,40(4):834-848.
[27]
CHENL C, ZHUYukun, PapandreouG,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of 15th European Conference on Computer Vision.Munich:Springer,2018:833-851.
[28]
HEKaiming, ZHANGXiangyu, RENShaoqing,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Trans Pattern Anal Mach Intell,2015,37(9):1904-1916.
[29]
LID, HUJ, WANGC,et al.Involution:inverting the inherence of convolution for visual recognition[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville:IEEE,2021:12316-12325.
[30]
LecunY, BottouL, BengioY,et al.Gradient-based learning applied to document recognition[J].Proc IEEE,1998,86(11):2278-2324.
[31]
RonnebergerO, FischerP, BroxT.U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention MICCAI 2015.Munich:Springer,2015:234-241.
[32]
FUJ, LIUJ, TIANH J,et al.Dual attention network for scene segmentation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach:IEEE,2019:3141-3149.
[33]
LIZ W, SHENH F, CHENGQ,et al.Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors[J].ISPRS J Photogramm Remote Sens,2019,150:197-212.