Journal
REMOTE SENSING
Volume 12, Issue 13, Pages -Publisher
MDPI
DOI: 10.3390/rs12132106
Keywords
Gaofen-5; deep learning; cloud detection; big data; MFGNet; quality assessment
Categories
Funding
- Major Projects of High-Resolution Earth Observation System [30-Y20A010-9007-17/18, 04-Y30B01-9001-18/20]
- 13th Five-Year Advance Research Project on Civil Space Technology of the National Defense Science and Technology Administration
Ask authors/readers for more resources
Recent developments in hyperspectral satellites have dramatically promoted the wide application of large-scale quantitative remote sensing. As an essential part of preprocessing, cloud detection is of great significance for subsequent quantitative analysis. For Gaofen-5 (GF-5) data producers, the daily cloud detection of hundreds of scenes is a challenging task. Traditional cloud detection methods cannot meet the strict demands of large-scale data production, especially for GF-5 satellites, which have massive data volumes. Deep learning technology, however, is able to perform cloud detection efficiently for massive repositories of satellite data and can even dramatically speed up processing by utilizing thumbnails. Inspired by the outstanding learning capability of convolutional neural networks (CNNs) for feature extraction, we propose a new dual-branch CNN architecture for cloud segmentation for GF-5 preview RGB images, termed a multiscale fusion gated network (MFGNet), which introduces pyramid pooling attention and spatial attention to extract both shallow and deep information. In addition, a new gated multilevel feature fusion module is also employed to fuse features at different depths and scales to generate pixelwise cloud segmentation results. The proposed model is extensively trained on hundreds of globally distributed GF-5 satellite images and compared with current mainstream CNN-based detection networks. The experimental results indicate that our proposed method has a higher F1 score (0.94) and fewer parameters (7.83 M) than the compared methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available