MoANet: A Motion Attention Network for Sea Fog Detection in Time Series Meteorological Satellite Imagery
Sea fog detection is a significant and challenging issue in meteorological satellite imagery. Distinguishing between sea fog and low clouds is challenging due to the similar morphology and brightness characteristics of these two phenomena on the imageries. Most of the existing deep learning methods...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10349931/ |
_version_ | 1797373156988551168 |
---|---|
author | Ziheng Yang Ming Wu Mengqiu Xu Xun Zhu Chuang Zhang Bin Zhang |
author_facet | Ziheng Yang Ming Wu Mengqiu Xu Xun Zhu Chuang Zhang Bin Zhang |
author_sort | Ziheng Yang |
collection | DOAJ |
description | Sea fog detection is a significant and challenging issue in meteorological satellite imagery. Distinguishing between sea fog and low clouds is challenging due to the similar morphology and brightness characteristics of these two phenomena on the imageries. Most of the existing deep learning methods are based on a single imagery feature extraction without the time-related features in imagery sequence. Although the designed temporal models, such as temporal U-Net, expand the available features from a single imagery to the consecutive frames and introduce general temporal information, the learned motion features are not explicit and can only be implicitly learned through a large amount of data. Thus, we introduce motion features obtained from continuous temporal imagery sequences into the sea fog detection task due to the discrepancy between sea fog and other types of clouds. In this article, under the motion features acquired by Horn–Schunck (HS) optical flow method and attention mechanisms, a Motion Attention Network (MoANet) for sea fog detection is proposed, named MoANet. We performed detailed experiments on the Himawaria-8 satellite imagery data set (H-8 Dataset). The Mean Intersection over Union (MIoU) of our method reaches 81.38%, which is 6.49% higher than the single imagery method. The visualization of the results shows that MoANet has more smooth edges, as well as detects more complete area than others. Furthermore, we validate on International Comprehensive Ocean-Atmosphere Data Set (ICOADS) through contrasting visibility value to prove the practicality of the proposed method and the accuracy achieves 90.65%. |
first_indexed | 2024-03-08T18:46:16Z |
format | Article |
id | doaj.art-abb37d05efcf47dca9db611baad210f2 |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-03-08T18:46:16Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-abb37d05efcf47dca9db611baad210f22023-12-29T00:02:24ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01171976198710.1109/JSTARS.2023.334090910349931MoANet: A Motion Attention Network for Sea Fog Detection in Time Series Meteorological Satellite ImageryZiheng Yang0https://orcid.org/0000-0003-0825-1288Ming Wu1https://orcid.org/0000-0001-8390-5398Mengqiu Xu2https://orcid.org/0000-0002-3029-7664Xun Zhu3https://orcid.org/0000-0001-8598-8748Chuang Zhang4https://orcid.org/0000-0002-1115-5580Bin Zhang5https://orcid.org/0009-0008-7206-144XSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, ChinaSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, ChinaSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, ChinaSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, ChinaAI lab, Beijing University of Posts and Telecommunications, Beijing, ChinaSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, ChinaSea fog detection is a significant and challenging issue in meteorological satellite imagery. Distinguishing between sea fog and low clouds is challenging due to the similar morphology and brightness characteristics of these two phenomena on the imageries. Most of the existing deep learning methods are based on a single imagery feature extraction without the time-related features in imagery sequence. Although the designed temporal models, such as temporal U-Net, expand the available features from a single imagery to the consecutive frames and introduce general temporal information, the learned motion features are not explicit and can only be implicitly learned through a large amount of data. Thus, we introduce motion features obtained from continuous temporal imagery sequences into the sea fog detection task due to the discrepancy between sea fog and other types of clouds. In this article, under the motion features acquired by Horn–Schunck (HS) optical flow method and attention mechanisms, a Motion Attention Network (MoANet) for sea fog detection is proposed, named MoANet. We performed detailed experiments on the Himawaria-8 satellite imagery data set (H-8 Dataset). The Mean Intersection over Union (MIoU) of our method reaches 81.38%, which is 6.49% higher than the single imagery method. The visualization of the results shows that MoANet has more smooth edges, as well as detects more complete area than others. Furthermore, we validate on International Comprehensive Ocean-Atmosphere Data Set (ICOADS) through contrasting visibility value to prove the practicality of the proposed method and the accuracy achieves 90.65%.https://ieeexplore.ieee.org/document/10349931/Attention mapimage segmentationmotion featuresoptical flowsea fog detection |
spellingShingle | Ziheng Yang Ming Wu Mengqiu Xu Xun Zhu Chuang Zhang Bin Zhang MoANet: A Motion Attention Network for Sea Fog Detection in Time Series Meteorological Satellite Imagery IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention map image segmentation motion features optical flow sea fog detection |
title | MoANet: A Motion Attention Network for Sea Fog Detection in Time Series Meteorological Satellite Imagery |
title_full | MoANet: A Motion Attention Network for Sea Fog Detection in Time Series Meteorological Satellite Imagery |
title_fullStr | MoANet: A Motion Attention Network for Sea Fog Detection in Time Series Meteorological Satellite Imagery |
title_full_unstemmed | MoANet: A Motion Attention Network for Sea Fog Detection in Time Series Meteorological Satellite Imagery |
title_short | MoANet: A Motion Attention Network for Sea Fog Detection in Time Series Meteorological Satellite Imagery |
title_sort | moanet a motion attention network for sea fog detection in time series meteorological satellite imagery |
topic | Attention map image segmentation motion features optical flow sea fog detection |
url | https://ieeexplore.ieee.org/document/10349931/ |
work_keys_str_mv | AT zihengyang moanetamotionattentionnetworkforseafogdetectionintimeseriesmeteorologicalsatelliteimagery AT mingwu moanetamotionattentionnetworkforseafogdetectionintimeseriesmeteorologicalsatelliteimagery AT mengqiuxu moanetamotionattentionnetworkforseafogdetectionintimeseriesmeteorologicalsatelliteimagery AT xunzhu moanetamotionattentionnetworkforseafogdetectionintimeseriesmeteorologicalsatelliteimagery AT chuangzhang moanetamotionattentionnetworkforseafogdetectionintimeseriesmeteorologicalsatelliteimagery AT binzhang moanetamotionattentionnetworkforseafogdetectionintimeseriesmeteorologicalsatelliteimagery |