Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.6.2.14

Cloud Detection from Sentinel-2 Images Using DeepLabV3+ and Swin Transformer Models  

Kang, Jonggu (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Park, Ganghyun (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)
Youn, Youjeong (Department of Spatial Information Engineering, Division of Earth Environmental System Science, Pukyong National University)
Choi, Soyeon (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.38, no.6_2, 2022 , pp. 1743-1747 More about this Journal
Abstract
Sentinel-2 can be used as proxy data for the Korean Compact Advanced Satellite 500-4 (CAS500-4), also known as Agriculture and Forestry Satellite, in terms of spectral wavelengths and spatial resolution. This letter examined cloud detection for later use in the CAS500-4 based on deep learning technologies. DeepLabV3+, a traditional Convolutional Neural Network (CNN) model, and Shifted Windows (Swin) Transformer, a state-of-the-art (SOTA) Transformer model, were compared using 22,728 images provided by Radiant Earth Foundation (REF). Swin Transformer showed a better performance with a precision of 0.886 and a recall of 0.875, which is a balanced result, unbiased between over- and under-estimation. Deep learning-based cloud detection is expected to be a future operational module for CAS500-4 through optimization for the Korean Peninsula.
Keywords
Cloud detection; Deep learning; Sentinel-2;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 ESA (European Space Agency), 2022. Cloud Masks, https://sentinels.copernicus.eu/web/sentinel/technical-guides/sentinel-2-msi/level-1c/cloud-masks, Accessed on Nov. 30, 2022.
2 REF (Radiant Earth Foundation), 2022. Sentinel-2 Cloud Cover Segmentation Dataset, https://mlhub.earth/data/ref_cloud_cover_detection_challenge_v1, Accessed on Nov. 30, 2022.
3 Chen, L.C., Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation, arXiv preprint arXiv:1802.02611. https://doi.org/10.48550/arXiv.1802.02611   DOI
4 Dosovitskiy, A., L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, 2020. An Image is Worth 16 × 16 Words: Transformers for Image recognition at scale, arXiv preprint arXiv:2010.11929. https://doi.org/10.48550/arXiv.2010.11929   DOI
5 Liu, Z., Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, 2021. Swin Transformer: Hierarchical vision transformer using shifted windows, arXiv preprint arXiv:2103.14030. https://doi.org/10.48550/arXiv.2103.14030   DOI
6 Kang, J., G. Kim, Y. Jeong, S. Kim, Y. Youn, S. Cho, and Y. Lee, 2021. U-Net cloud detection for the SPARCS cloud dataset from Landsat 8 images, Korean Journal of Remote Sensing, 37(5-1): 1149-1161. https://doi.org/10.7780/kjrs.2021.37.5.1.25   DOI