Cloud detection is an effective measure to improve the utilization rate and application range of remote sensing images. However, most of the existing cloud detection algorithms face with two problems: the difficulty in distinguishing complex underlying surfaces like ice and snow from cloud and the requirement of a large number of manually labeled cloud samples for model training. To improve the performance of cloud recognition, we propose a cloud detection algorithm based on Attention U-Net for Landsat images. Firstly, convolution operation is conducted to extract the shallow features of cloud in coding modules. Then, deconvolution, jump connection and attention mechanism are integrated to mine deeper cloud features in decoding modules. Finally, a small number of public Landsat image cloud samples are used for training to achieve end-to-end pixel-level cloud recognition. Compared with traditional machine learning algorithms, experimental results indicate that the proposed algorithm has higher overall accuracy, lower false detection rate and missed detection rate of thin cloud and shadow.
[1] 李炳燮, 马张宝, 齐清文, 等. Landsat TM遥感影像中厚云和阴影去除[J]. 遥感学报, 2010, 14(3):534-545. Li B X, Ma Z B, Qi Q W, et al. Cloud and shadow removal from Landsat TM data[J]. Journal of Remote Sensing, 2010, 14(3):534-545. (in Chinese)
[2] 陈梦露, 李存军, 官云兰, 等. 基于Landsat 8影像的厚云及云影去除方法[J]. 北京测绘, 2019, 33(4):382-386. Chen M L, Li C J, Guan Y L, et al. Thick cloud and cloud shadow removal method based on Landsat 8 image[J]. Beijing Surveying and Mapping, 2019, 33(4):382-386. (in Chinese)
[3] 周伟, 关键, 姜涛, 等. 多光谱遥感影像中云影区域的检测与修复[J]. 遥感学报, 2012, 16(1):132-142. Zhou W, Guan J, Jiang T, et al. Automatic detection and repairing of cloud and shadow regions in multi-spectral remote sensing images[J]. Journal of Remote Sensing, 2012, 16(1):132-142. (in Chinese)
[4] Zhang Y, Rossow W B, Lacis A A, et al. 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] Bley S, Deneke H. A threshold-based cloud mask for the high-resolution visible channel of Meteosat second generation SEVIRI[J]. Atmospheric Measurement Techniques, 2013, 6(10):2713-2723.
[6] 陈奋, 闫冬梅, 赵忠明. 基于无抽样小波的遥感影像薄云检测与去除[J]. 武汉大学学报(信息科学版), 2007, 32(1):71-74. Chen F, Yan D M, Zhao Z M. Haze detection and removal in remote sensing images based on undecimated wavelet transform[J]. Geomatics and Information Science of Wuhan University, 2007, 32(1):71-74. (in Chinese)
[7] 孙汝星, 范荣双. 基于支持向量机的多特征融合影像云检测[J]. 测绘与空间地理信息, 2018, 41(6):153-156. Sun R X, Fan R S. Multi-feature fusion image cloud detection based on SVM[J]. Geomatics & Spatial Information Technology, 2018, 41(6):153-156. (in Chinese)
[8] Molnar G, Coakley Jr J A. Retrieval of cloud cover from satellite imagery data:a statistical approach[J]. Journal of Geophysical Research:Atmospheres, 1985, 90(D7):12960-12970.
[9] 刘志刚, 李元祥, 黄峰. 基于动态聚类的MODIS云检测算法[J]. 遥感信息, 2007(4):33-35. Liu Z G, Li Y X, Huang F. Cloud detection of MODIS satellite images based on dynamical cluster[J]. Remote Sensing Information, 2007(4):33-35. (in Chinese)
[10] Ishida H, Oishi Y, Morita K, et al. Development of a support vector machine based cloud detection method for MODIS with the adjustability to various conditions[J]. Remote Sensing of Environment, 2018, 205:390-407.
[11] Xie F, Shi M, Shi Z, et al. Multilevel cloud detection in remote sensing images based on deep learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations Remote Sensing of Environment, 2017, 10(8):3631-3640.
[12] Heydari S S, Mountrakis G. Meta-analysis of deep neural networks in remote sensing:a comparative study of mono-temporal classification to support vector machines[J]. ISPRS Journal of Photogrammetry Remote Sensing, 2019, 152:192-210.
[13] Ghasemian N, Akhoondzadeh M. Introducing two random forest based methods for cloud detection in remote sensing images[J]. Advances in Space Research, 2018, 62(2):288-303.
[14] Shao Z, Pan Y, Diao C. Cloud detection in remote sensing images based on multiscale featuresconvolutional neural network[J]. IEEE Transactions on Geoscience Remote Sensing, 2019, 57(6):4062-4076.
[15] 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. Hu G S, Chen C C, Liang D. Cloud detection for Landsat images by combination of ACCA with WSVM[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(8):848-854. (in Chinese)
[16] Li Y, Chen W, Zhang Y, et al. Accurate cloud detection in high-resolution remote sensing imagery by weakly supervised deep learning[J]. Remote Sensing of Environment, 2020, 250:112045.
[17] 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.
[18] Jeppesen J H, Jacobsen R H, Inceoglu F, et al. A cloud detection algorithm for satellite imagery based on deep learning[J]. Remote Sensing of Environment, 2019, 229:247-259.
[19] 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 Remote Sensing, 2019, 150:197-212.
[20] Trebing K, Stanczyk T, Mehrkanoon S. SmaAt-Unet:precipitation nowcasting using a small Attention-Unet architecture[J]. Pattern Recognition Letters, 2021, 145:178-186.
[21] Ronneberger O, Fischer P, Brox T. U-Net:convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and ComputerAssisted Intervention. Cham:Springer, 2015:234-241.
[22] 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.
[23] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1):1929-1958.
