Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network
Cloud detection is an important and difficult task in the pre-processing of satellite remote sensing data. The results of traditional cloud detection methods are often unsatisfactory in complex environments or the presence of various noise disturbances. With the rapid development of artificial intel...
Published in: | Symmetry |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2020
|
Subjects: | |
Online Access: | https://doi.org/10.3390/sym12061056 |
id |
ftmdpi:oai:mdpi.com:/2073-8994/12/6/1056/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2073-8994/12/6/1056/ 2023-08-20T04:05:21+02:00 Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network Yanan Guo Xiaoqun Cao Bainian Liu Mei Gao 2020-06-25 application/pdf https://doi.org/10.3390/sym12061056 EN eng Multidisciplinary Digital Publishing Institute Computer Science and Symmetry/Asymmetry https://dx.doi.org/10.3390/sym12061056 https://creativecommons.org/licenses/by/4.0/ Symmetry; Volume 12; Issue 6; Pages: 1056 cloud detection remote sensing images U-Net architecture attention mechanism deep learning convolutional neural network Text 2020 ftmdpi https://doi.org/10.3390/sym12061056 2023-07-31T23:41:21Z Cloud detection is an important and difficult task in the pre-processing of satellite remote sensing data. The results of traditional cloud detection methods are often unsatisfactory in complex environments or the presence of various noise disturbances. With the rapid development of artificial intelligence technology, deep learning methods have achieved great success in many fields such as image processing, speech recognition, autonomous driving, etc. This study proposes a deep learning model suitable for cloud detection, Cloud-AttU, which is based on a U-Net network and incorporates an attention mechanism. The Cloud-AttU model adopts the symmetric Encoder-Decoder structure, which achieves the fusion of high-level features and low-level features through the skip-connection operation, making the output results contain richer multi-scale information. This symmetrical network structure is concise and stable, significantly enhancing the effect of image segmentation. Based on the characteristics of cloud detection, the model is improved by introducing an attention mechanism that allows model to learn more effective features and distinguish between cloud and non-cloud pixels more accurately. The experimental results show that the method proposed in this paper has a significant accuracy advantage over the traditional cloud detection method. The proposed method is also able to achieve great results in the presence of snow/ice disturbance and other bright non-cloud objects, with strong resistance to disturbance. The Cloud-AttU model proposed in this study has achieved excellent results in the cloud detection tasks, indicating that this symmetric network architecture has great potential for application in satellite image processing and deserves further research. Text Attu MDPI Open Access Publishing Symmetry 12 6 1056 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
cloud detection remote sensing images U-Net architecture attention mechanism deep learning convolutional neural network |
spellingShingle |
cloud detection remote sensing images U-Net architecture attention mechanism deep learning convolutional neural network Yanan Guo Xiaoqun Cao Bainian Liu Mei Gao Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network |
topic_facet |
cloud detection remote sensing images U-Net architecture attention mechanism deep learning convolutional neural network |
description |
Cloud detection is an important and difficult task in the pre-processing of satellite remote sensing data. The results of traditional cloud detection methods are often unsatisfactory in complex environments or the presence of various noise disturbances. With the rapid development of artificial intelligence technology, deep learning methods have achieved great success in many fields such as image processing, speech recognition, autonomous driving, etc. This study proposes a deep learning model suitable for cloud detection, Cloud-AttU, which is based on a U-Net network and incorporates an attention mechanism. The Cloud-AttU model adopts the symmetric Encoder-Decoder structure, which achieves the fusion of high-level features and low-level features through the skip-connection operation, making the output results contain richer multi-scale information. This symmetrical network structure is concise and stable, significantly enhancing the effect of image segmentation. Based on the characteristics of cloud detection, the model is improved by introducing an attention mechanism that allows model to learn more effective features and distinguish between cloud and non-cloud pixels more accurately. The experimental results show that the method proposed in this paper has a significant accuracy advantage over the traditional cloud detection method. The proposed method is also able to achieve great results in the presence of snow/ice disturbance and other bright non-cloud objects, with strong resistance to disturbance. The Cloud-AttU model proposed in this study has achieved excellent results in the cloud detection tasks, indicating that this symmetric network architecture has great potential for application in satellite image processing and deserves further research. |
format |
Text |
author |
Yanan Guo Xiaoqun Cao Bainian Liu Mei Gao |
author_facet |
Yanan Guo Xiaoqun Cao Bainian Liu Mei Gao |
author_sort |
Yanan Guo |
title |
Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network |
title_short |
Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network |
title_full |
Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network |
title_fullStr |
Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network |
title_full_unstemmed |
Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network |
title_sort |
cloud detection for satellite imagery using attention-based u-net convolutional neural network |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2020 |
url |
https://doi.org/10.3390/sym12061056 |
genre |
Attu |
genre_facet |
Attu |
op_source |
Symmetry; Volume 12; Issue 6; Pages: 1056 |
op_relation |
Computer Science and Symmetry/Asymmetry https://dx.doi.org/10.3390/sym12061056 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/sym12061056 |
container_title |
Symmetry |
container_volume |
12 |
container_issue |
6 |
container_start_page |
1056 |
_version_ |
1774715864554143744 |