Cloud detection method based on deep convolutional neural network

doi:10.13474/j.cnki.11-2246.2021.0107

Abstract

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

CLC Number:

P237

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.

References

[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.