Cloud and Cloud Shadow Detection of GF-1 Images Based on the Swin-UNet Method

Cloud and cloud shadow detection in remote sensing images is an important preprocessing technique for quantitative analysis and large-scale mapping. To solve the problems of cloud and cloud shadow detection based on Convolutional Neural Network models, such as rough edges and insufficient overall ac...

Full description

Saved in:
Bibliographic Details
Published inAtmosphere Vol. 14; no. 11; p. 1669
Main Authors Tan, Yuhao, Zhang, Wenhao, Yang, Xiufeng, Liu, Qiyue, Mi, Xiaofei, Li, Juan, Yang, Jian, Gu, Xingfa
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.11.2023
Subjects
Accuracy
Algorithms
Artificial neural networks
cloud and cloud shadow detection
Cloud detection
Clouds
Datasets
Deep learning
Detection
Feature extraction
GF-1
Image processing
Image resolution
Image segmentation
Machine learning
Mathematical models
Methods
Modelling
Neural networks
Preprocessing
Remote sensing
Satellites
Semantics
Shadows
Swin Transformer
Swin-UNet
Target recognition
Vegetation
China
Online AccessGet full text

Cover

More Information
Summary:Cloud and cloud shadow detection in remote sensing images is an important preprocessing technique for quantitative analysis and large-scale mapping. To solve the problems of cloud and cloud shadow detection based on Convolutional Neural Network models, such as rough edges and insufficient overall accuracy, cloud and cloud shadow segmentation based on Swin-UNet was studied in the wide field of view (WFV) images of GaoFen-1 (GF-1). The Swin Transformer blocks help the model capture long-distance features and obtain deeper feature information in the network. This study selects a public GF1_WHU cloud and cloud shadow detection dataset for preprocessing and data optimization and conducts comparative experiments in different models. The results show that the algorithm performs well on vegetation, water, buildings, barren and other types. The average accuracy of cloud detection is 98.01%, the recall is 96.84% and the F1-score is 95.48%. The corresponding results of cloud shadow detection are 84.64%, 83.12% and 97.55%. In general, compared to U-Net, PSPNet and DeepLabV3+, this model performs better in cloud and cloud shadow detection, with clearer detection boundaries and a higher accuracy in complex surface conditions. This proves that Swin-UNet has great feature extraction capability in moderate and high-resolution remote sensing images.
ISSN:2073-4433
2073-4433
DOI:10.3390/atmos14111669