Application of Deep Learning Algorithm to Build an Automated Cloud Segmentation Model Based on Open Data Cube Framework
Main Article Content
Abstract
Cloud detection is a significant task in optical remote sensing to reconstruct the contaminated cloud area from multi-temporal satellite images. Besides, the rapid development of machine learning techniques, especially deep learning algorithms, can detect clouds over a large area in optical remote sensing data. In this study, the method based on the proposed deep-learning method called ODC-Cloud, which was built on convolutional blocks and integrating with the Open Data Cube (ODC) platform. The results showed that our proposed model achieved an overall 90% accuracy in detecting cloud in Landsat 8 OLI imagery and successfully integrated with the ODC to perform multi-scale and multi-temporal analysis. This is a pioneer study in techniques of storing and analyzing big optical remote sensing data.
Keywords:
Optical Remote Sensing, Landsat 8 OLI, automatic cloud detection, deep-learning, Open Data Cube.
References
M. Shi, F. Xie, Y. Zi, J. Yin, Cloud detection of remote sensing images by deep learning, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, 2016 (701-704) https://doi.org/10.1109/IGARSS.2016.7729176.
[2] X. Jin, J. Li, T.J. Schmit, J. Li, M.D. Goldberg, J. J. Gurka, Retrieving clear-sky atmospheric parameters from SEVIRI and ABI infrared radiances, Journal of Geophysical Research: Atmospheres, Aug. 2008, 113(D15). https://doi. org/10.1029/2008JD010040.
[3] R.R. Irish, J.L. Barker, S.N. Goward, T. Arvidson, Characterization of the Landsat-7 ETMϩ Automated Cloud-Cover Assessment (ACCA) Algorithm, American Society for Photogrammetry and Remote Sensing, 2006, pp. 1179-1188(10). https://doi.org/10.14358/PERS.72.10.1179.
[4] L. Zhu, M. Wang, J. Shao, C. Liu, C. Zhao, Y. Zhao, Remote sensing of global volcanic eruptions using Fengyun series satellites, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy, Jul. (2015) 4797–4800. https://doi.org/10.1109/IGARSS.2015.7326903.
[5] Z. Zhu and C. E. Woodcock, Object-based cloud and cloud shadow detection in Landsat imagery, Remote Sensing of Environment 118 (2012) 83–94. https://doi.org/10.1016/j.rse.2011.10.028.
[6] S. Qiu, B. He, Z. Zhu, Z. Liao, X. Quan, Improving Fmask cloud and cloud shadow detection in mountainous area for Landsats 4–8 images, Remote Sensing of Environment 199 (2017) 107–119. https://doi.org/10.1016/j.rse.2017.07.002.
[7] Y. Zhang, B. Guindon, J. Cihlar, An image transform to characterize and compensate for spatial variations in thin cloud contamination of Landsat images, Remote Sensing of Environment 82(2–3) (2002) 173–187. https://doi.org/10.1016/ S0034-4257(02)00034-2.
[8] F. Xie, M. Shi, Z. Shi, J. Yin, D. Zhao, Multilevel Cloud Detection in Remote Sensing Images Based on Deep Learning, IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing 10(8) (2017) 3631–3640. https://doi.org/10.1109/JSTARS.2017.2686488.
[9] J.H. Jeppesen, R.H. Jacobsen, F. Inceoglu, T.S. Toftegaard, A cloud detection algorithm for satellite imagery based on deep learning, Remote Sensing of Environment 229 (2019) 247–259. https://doi.org/10.1016/j.rse.2019.03.039.
[10] W. Huang, Y. Wang, X. Chen, Cloud detection for high-resolution remote-sensing images of urban areas using colour and edge features based on dual-colour models, International Journal of Remote Sensing 39(20(2018) 6657–6675. https://doi.org/ 10.1080/01431161.2018.1466069.
[11] Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, O. Ronneberger, 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation, International conference on medical image computing and computer-assisted intervention, Springer, Cham, 2016 (424–432) https://doi.org/10.1007/978-3-319-46723-8_49.
[12] O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation, International Conference on Medical image computing and computer-assisted intervention, Springer, Cham 2015(234-241) https://doi.org/10.1007/978-3-319-24574-4_28.
[13] Z. Zhang, Q. Liu, Y. Wang, Road Extraction by Deep Residual U-Net, IEEE Geosci. Remote Sensing Letter 15(5)(2018) 749–753. https://doi. org/10.1109/LGRS.2018.2802944.
[14] S. Mohajerani, T. A. Krammer, P. Saeedi, A Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks, IEEE 20th International Workshop on Multimedia Signal Processing (MMSP), Vancouver, BC, Aug. 2018 (1-5) https://doi.org/10.1109/MMSP.2018.8547095.
[15] B. Bischke, P. Helber, J. Folz, D. Borth, A. Dengel, Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks, IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, Sep. (2019) 1480–1484. https://doi.org/10.1109/ICIP.2019.8803050.
[16] S. Ji, S. Wei, M. Lu, Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set, IEEE Trans. Geosci. Remote Sensing 57(1) (2019) 574–586. https://doi.org/10.1109/TGRS. 2018.2858817.
[17] S. Mohajerani,P. Saeedi, Cloud-Net: An End-To-End Cloud Detection Algorithm for Landsat 8 Imagery, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 2019 (1029–1032) https:// doi.org/10.1109/IGARSS.2019.8898776.
[2] X. Jin, J. Li, T.J. Schmit, J. Li, M.D. Goldberg, J. J. Gurka, Retrieving clear-sky atmospheric parameters from SEVIRI and ABI infrared radiances, Journal of Geophysical Research: Atmospheres, Aug. 2008, 113(D15). https://doi. org/10.1029/2008JD010040.
[3] R.R. Irish, J.L. Barker, S.N. Goward, T. Arvidson, Characterization of the Landsat-7 ETMϩ Automated Cloud-Cover Assessment (ACCA) Algorithm, American Society for Photogrammetry and Remote Sensing, 2006, pp. 1179-1188(10). https://doi.org/10.14358/PERS.72.10.1179.
[4] L. Zhu, M. Wang, J. Shao, C. Liu, C. Zhao, Y. Zhao, Remote sensing of global volcanic eruptions using Fengyun series satellites, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy, Jul. (2015) 4797–4800. https://doi.org/10.1109/IGARSS.2015.7326903.
[5] Z. Zhu and C. E. Woodcock, Object-based cloud and cloud shadow detection in Landsat imagery, Remote Sensing of Environment 118 (2012) 83–94. https://doi.org/10.1016/j.rse.2011.10.028.
[6] S. Qiu, B. He, Z. Zhu, Z. Liao, X. Quan, Improving Fmask cloud and cloud shadow detection in mountainous area for Landsats 4–8 images, Remote Sensing of Environment 199 (2017) 107–119. https://doi.org/10.1016/j.rse.2017.07.002.
[7] Y. Zhang, B. Guindon, J. Cihlar, An image transform to characterize and compensate for spatial variations in thin cloud contamination of Landsat images, Remote Sensing of Environment 82(2–3) (2002) 173–187. https://doi.org/10.1016/ S0034-4257(02)00034-2.
[8] F. Xie, M. Shi, Z. Shi, J. Yin, D. Zhao, Multilevel Cloud Detection in Remote Sensing Images Based on Deep Learning, IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing 10(8) (2017) 3631–3640. https://doi.org/10.1109/JSTARS.2017.2686488.
[9] J.H. Jeppesen, R.H. Jacobsen, F. Inceoglu, T.S. Toftegaard, A cloud detection algorithm for satellite imagery based on deep learning, Remote Sensing of Environment 229 (2019) 247–259. https://doi.org/10.1016/j.rse.2019.03.039.
[10] W. Huang, Y. Wang, X. Chen, Cloud detection for high-resolution remote-sensing images of urban areas using colour and edge features based on dual-colour models, International Journal of Remote Sensing 39(20(2018) 6657–6675. https://doi.org/ 10.1080/01431161.2018.1466069.
[11] Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, O. Ronneberger, 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation, International conference on medical image computing and computer-assisted intervention, Springer, Cham, 2016 (424–432) https://doi.org/10.1007/978-3-319-46723-8_49.
[12] O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation, International Conference on Medical image computing and computer-assisted intervention, Springer, Cham 2015(234-241) https://doi.org/10.1007/978-3-319-24574-4_28.
[13] Z. Zhang, Q. Liu, Y. Wang, Road Extraction by Deep Residual U-Net, IEEE Geosci. Remote Sensing Letter 15(5)(2018) 749–753. https://doi. org/10.1109/LGRS.2018.2802944.
[14] S. Mohajerani, T. A. Krammer, P. Saeedi, A Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks, IEEE 20th International Workshop on Multimedia Signal Processing (MMSP), Vancouver, BC, Aug. 2018 (1-5) https://doi.org/10.1109/MMSP.2018.8547095.
[15] B. Bischke, P. Helber, J. Folz, D. Borth, A. Dengel, Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks, IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, Sep. (2019) 1480–1484. https://doi.org/10.1109/ICIP.2019.8803050.
[16] S. Ji, S. Wei, M. Lu, Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set, IEEE Trans. Geosci. Remote Sensing 57(1) (2019) 574–586. https://doi.org/10.1109/TGRS. 2018.2858817.
[17] S. Mohajerani,P. Saeedi, Cloud-Net: An End-To-End Cloud Detection Algorithm for Landsat 8 Imagery, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 2019 (1029–1032) https:// doi.org/10.1109/IGARSS.2019.8898776.