A Novel ResUNet Architecture for Thin Cloud and Boundary Detection in Landsat 8 Remote Sensing Imagery
Source abstract
Abstract
To address the challenges of thin cloud detection and imprecise cloud boundary segmentation in Landsat 8 remote sensing imagery, this paper proposes a systematic approach that comprehensively enhances cloud detection accuracy from data preprocessing to network architecture optimisation. First, through empirical analysis, an optimised band input combination was determined (removing the panchromatic Band 8 and thermal infrared Band 11), effectively suppressing urban background noise. Subsequently, an enhanced ResUNet model was designed, innovatively integrating an Atrous Spatial Pyramid Pooling (ASPP) module with an attention gate (AG) mechanism. The ASPP module enhances detection capabilities for thin clouds and diffuse cloud masses by aggregating multi-scale global contextual information. The attention-gated mechanism finely tunes feature fusion during the decoding phase, suppressing interference from highly reflective surface features to achieve precise cloud boundary segmentation. Experiments conducted on the Landsat 8 dataset featuring typical urban scenes demonstrate that the proposed method significantly outperforms mainstream models across both conventional and boundary-specific metrics, achieving an overall accuracy (OA) of 0.9717, a mean intersection over union (mIoU) of 0.8102, and, notably, a mean bounding box intersection over union (mB-IoU) of 0.4154 and a mean bounding box F1 score of 0.5356, representing improvements of 16.3% and 12.5%, respectively, over existing methods. This research provides an efficient and robust technical framework for cloud detection tasks in complex urban environments, laying the foundation for high-precision processing of remote sensing imagery and subsequent quantitative analysis.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing in Agriculture · Solar Radiation and Photovoltaics · Atmospheric aerosols and clouds
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Sichuan University of Science & Engineering, Yibin 644000, China
Funding
National Natural Science Foundation of China
References (47)
Show source-provided references
1. Zhu, Z., Qiu, S., He, B., and Deng, C. (2018). Cloud and cloud shadow detection for Landsat images: The fundamental basis for analyzing Landsat time series. Remote Sensing Time Series Image Processing, CRC Press. [1st ed.].10.1201/9781315166636-1 ↗
2. Ssl4eo-l: Datasets and foundation models for landsat imagery
3. Multi-sensor cloud and cloud shadow segmentation with a convolutional neural network10.1016/j.rse.2019.05.022 ↗
4. Cloud and cloud shadow detection in Landsat imagery based on deep convolutional neural networks10.1016/j.rse.2019.03.007 ↗
5. Object-based cloud and cloud shadow detection in Landsat imagery10.1016/j.rse.2011.10.028 ↗
6. Cloud detection algorithm comparison and validation for operational Landsat data products10.1016/j.rse.2017.03.026 ↗
7. Automated detection of cloud and cloud shadow in single-date Landsat imagery using neural networks and spatial post-processing10.3390/rs6064907 ↗
8. Improvement of the Fmask algorithm for Sentinel-2 images: Separating clouds from bright surfaces based on parallax effects10.1016/j.rse.2018.04.046 ↗
9. Improvement and expansion of the Fmask algorithm: Cloud, cloud shadow, and snow detection for Landsats 4–7, 8, and Sentinel 2 images10.1016/j.rse.2014.12.014 ↗
10. Fmask 4.0: Improved cloud and cloud shadow detection in Landsats 4–8 and Sentinel-2 imagery10.1016/j.rse.2019.05.024 ↗
11. A cloud detection algorithm for satellite imagery based on deep learning10.1016/j.rse.2019.03.039 ↗
12. Wang, Z., Zhao, L., Meng, J., Han, Y., Li, X., Jiang, R., Chen, J., and Li, H. (2024). Deep learning-based cloud detection for optical remote sensing images: A Survey. Remote Sens., 16.10.3390/rs16234583 ↗
13. Deep learning for multi-modal classification of cloud, shadow and land cover scenes in PlanetScope and Sentinel-2 imagery10.1016/j.isprsjprs.2019.08.018 ↗
14. Comparison of cloud detection algorithms for Sentinel-2 imagery10.1016/j.srs.2020.100010 ↗
15. A multi-temporal method for cloud detection, applied to FORMOSAT-2, VENμS, LANDSAT and SENTINEL-2 images10.1016/j.rse.2010.03.002 ↗
16. Liu, Z., Chen, H., Li, W., Chen, K., Qi, Z., Liu, C., Zou, Z., and Shi, Z. (2024, January 7–12). Learning to detect cloud and snow in remote sensing images from noisy labels. Proceedings of the IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece.10.1109/IGARSS53475.2024.10640405 ↗
17. Cloud and cloud shadow segmentation for remote sensing imagery via filtered jaccard loss function and parametric augmentation10.1109/JSTARS.2021.3070786 ↗
18. Multilevel cloud detection in remote sensing images based on deep learning10.1109/JSTARS.2017.2686488 ↗
19. Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors10.1016/j.isprsjprs.2019.02.017 ↗
20. CSDFormer: A cloud and shadow detection method for landsat images based on transformer
21. Francis, A., Sidiropoulos, P., and Muller, J.P. (2019). CloudFCN: Accurate and robust cloud detection for satellite imagery with deep learning. Remote Sens., 11.10.3390/rs11192312 ↗
22. CloudX-net: A robust encoder-decoder architecture for cloud detection from satellite remote sensing images
23. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
24. Navab, N., Hornegger, J., Wells, W., and Frangi, A. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer. Lecture Notes in Computer Science, Vol. 9351.10.1007/978-3-319-24571-3 ↗
25. U-Net cloud detection for the SPARCS cloud dataset from Landsat 8 images
26. Mohajerani, S., and Saeedi, P. (August, January 28). Cloud-Net: An end-to-end cloud detection algorithm for Landsat 8 imagery. Proceedings of the IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.10.1109/IGARSS.2019.8898776 ↗
27. Segnet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
28. Lightweight U-Net for cloud detection of visible and thermal infrared remote sensing images10.1007/s11082-020-02500-8 ↗
29. Hughes, M.J., and Kennedy, R. (2019). High-quality cloud masking of Landsat 8 imagery using convolutional neural networks. Remote Sens., 11.10.3390/rs11212591 ↗
30. Cross-sensor adversarial domain adaptation of Landsat-8 and Proba-V images for cloud detection
31. Transferring deep learning models for cloud detection between Landsat-8 and Proba-V
32. Hollstein, A., Segl, K., Guanter, L., Brell, M., and Enesco, M. (2016). Ready-to-use methods for the detection of clouds, cirrus, snow, shadow, water and clear sky pixels in Sentinel-2 MSI images. Remote Sens., 8.10.3390/rs8080666 ↗
33. Zekoll, V., Main-Knorn, M., Alonso, K., Louis, J., Frantz, D., Richter, R., and Pflug, B. (2021). Comparison of masking algorithms for sentinel-2 imagery. Remote Sens., 13.10.3390/rs13010137 ↗
34. López-Puigdollers, D., Mateo-García, G., and Gómez-Chova, L. (2021). Benchmarking deep learning models for cloud detection in Landsat-8 and Sentinel-2 images. Remote Sens., 13.10.3390/rs13050992 ↗
35. Improved cloud detection for Landsat 8 images using a combined neural network model10.1080/2150704X.2019.1708503 ↗
36. ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data10.1016/j.isprsjprs.2020.01.013 ↗
37. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗
38. Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv.
39. SegFormer: Simple and efficient design for semantic segmentation with transformers
40. U.S. Geological Survey (2016). L8 Biome Cloud Validation Masks, U.S. Geological Survey Data Release.
41. NASA (2026, February 17). National Aeronautics and Space Administration. Landsat 8 Mission, Available online: https://science.nasa.gov/mission/landsat-8/.
42. Landsat-8: Science and product vision for terrestrial global change research10.1016/j.rse.2014.02.001 ↗
43. U.S. Geological Survey (2019). Landsat 8 (L8) Data Users Handbook, LSDS-1574.
44. Normalised difference spectral indices and urban land cover as indicators of land surface temperature (LST)
45. Cirrus clouds that adversely affect Landsat 8 images: What are they and how to detect them?10.1016/j.rse.2020.111884 ↗
46. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv.
47. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7–13). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.123 ↗