Browse > Article
http://dx.doi.org/10.7780/kjrs.2021.37.5.1.25

U-Net Cloud Detection for the SPARCS Cloud Dataset from Landsat 8 Images  

Kang, Jonggu (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Kim, Geunah (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Jeong, Yemin (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Kim, Seoyeon (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Youn, Youjeong (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Cho, Soobin (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Lee, Yangwon (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Publication Information
Korean Journal of Remote Sensing / v.37, no.5_1, 2021 , pp. 1149-1161 More about this Journal
Abstract
With a trend of the utilization of computer vision for satellite images, cloud detection using deep learning also attracts attention recently. In this study, we conducted a U-Net cloud detection modeling using SPARCS (Spatial Procedures for Automated Removal of Cloud and Shadow) Cloud Dataset with the image data augmentation and carried out 10-fold cross-validation for an objective assessment of the model. Asthe result of the blind test for 1800 datasets with 512 by 512 pixels, relatively high performance with the accuracy of 0.821, the precision of 0.847, the recall of 0.821, the F1-score of 0.831, and the IoU (Intersection over Union) of 0.723. Although 14.5% of actual cloud shadows were misclassified as land, and 19.7% of actual clouds were misidentified as land, this can be overcome by increasing the quality and quantity of label datasets. Moreover, a state-of-the-art DeepLab V3+ model and the NAS (Neural Architecture Search) optimization technique can help the cloud detection for CAS500 (Compact Advanced Satellite 500) in South Korea.
Keywords
Cloud detection; Deep learning; U-Net; Image data augmentation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Guo, Z., C. Li, Z. Wang, E. Kwok, and X. Wei, 2018, A cloud boundary detection scheme combined with ASLIC and CNN using ZY-3, GF-1/2 satellite imagery, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-3: 455-458.
2 Heidinger, A., 2011. Algorithm Theoretical Basis Document: ABI Cloud Mask, available at https://www.star.nesdis.noaa.gov/goesr/docs/ATBD/Cloud_Mask.pdf, Accessed on Jun. 11, 2013.
3 Hughes, M.J. and K. Robert, 2019. High-quality cloud masking of Landsat 8 imagery using convolutional neural networks, Remote Sensing, 11(21): 2591.   DOI
4 LeCun, Y., Y. Bengio, and G. Hinton, 2015. Deep learning, Nature, 521: 436-444.   DOI
5 Ronneberger, O., P. Fischer, and T. Brox, 2015. U-Net: convolutional networks for biomedical image segmentation, Proc. of Medical Image Computing and Computer-Assisted Intervention, Munich, DE, Oct. 5-9, pp. 234-241.
6 Shelhamer, E., J. Long, and T. Darrell, 2017. Fully convolutional networks for semantic segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 640-651.   DOI
7 Ozkan, S., M. Efendioglu, and C. Demirpolat, 2018. Cloud detection from RGB color remote sensing images with deep pyramid networks, Proc. of 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, ES, Jul. 22-27, pp. 6939-6942.
8 Derrien, M., 2013. Algorithm Theoretical Basis Document for Cloud Products, available at http://www.nwcsaf.org/documents/20182/30662/NWC-CDOP2-GEO-MFL-SCI-ATBD-Cloud_v1.1.pdf/a5bb6eca-871b-4707-9c76-e0be09915d94, Accessed on Oct. 15, 2016.
9 Jeppesen, J.H., R.H. Jacobsen, F. Inceoglu, and T.S. Toftegaard, 2019. A cloud detection algorithm for satellite imagery based on deep learning, Remote Sensing of Environment, 229(8): 247-259.   DOI
10 Li, Z., H. Shen, Q. Cheng, Y. Liu, S. You, and Z. He, 2019. Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors, ISPRS Journal of Photogrammetry and Remote Sensing, 150: 197-212.   DOI
11 Zhu Z. and C.E. Woodcock, 2012. Object-based cloud and cloud shadow detection in Landsat imagery, Remote Sensing of Environment, 118: 83-94.   DOI
12 Saha, S., 2018, A Comprehensive Guide to Convolutional Neural Networks, available at https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53, Accessed on Dec. 16, 2018.
13 Sandler, M., A. Howard, M. Zhu, A. Zhmoginov, and L. Chen, 2018. MobileNetV2: Inverted residuals and linear bottlenecks, Proc. of The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018, Salt Lake City, UT, USA, Jun. 18-23, pp. 4510-4520.