A Multi-Feature Fusion Approach for Sea Fog Detection Under Complex Background

Sea fog is a natural phenomenon that significantly reduces visibility, posing navigational hazards for ships and impacting coastal activities. Geostationary meteorological satellite data have proven to be indispensable for sea fog monitoring due to their large spatial coverage and spatiotemporal con...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuyuan Yang, Yuzhu Tang, Zeming Zhou, Xiaofeng Zhao, Pinglv Yang, Yangfan Hu, Ran Bo
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/14/2409
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849419042273624064
author Shuyuan Yang
Yuzhu Tang
Zeming Zhou
Xiaofeng Zhao
Pinglv Yang
Yangfan Hu
Ran Bo
author_facet Shuyuan Yang
Yuzhu Tang
Zeming Zhou
Xiaofeng Zhao
Pinglv Yang
Yangfan Hu
Ran Bo
author_sort Shuyuan Yang
collection DOAJ
description Sea fog is a natural phenomenon that significantly reduces visibility, posing navigational hazards for ships and impacting coastal activities. Geostationary meteorological satellite data have proven to be indispensable for sea fog monitoring due to their large spatial coverage and spatiotemporal consistency. However, the spectral similarities between sea fog and low clouds result in omissions and misclassifications. Furthermore, high clouds obscure certain sea fog regions, leading to under-detection and high false alarm rates. In this paper, we present a novel sea fog detection method to alleviate the challenges. Specifically, the approach leverages a fusion of spectral, motion, and spatiotemporal texture consistency features to effectively differentiate sea fog and low clouds. Additionally, a multi-scale self-attention module is incorporated to recover the sea fog region obscured by clouds. Based on the spatial distribution characteristics of sea fog and clouds, we redesigned the loss function to integrate total variation loss, focal loss, and dice loss. Experimental results validate the effectiveness of the proposed method, and the detection accuracy is compared with the vertical feature mask produced by the CALIOP and exhibits a high level of consistency.
format Article
id doaj-art-6f9a225f4d8340f5ba35268e4eea6d4d
institution Kabale University
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-6f9a225f4d8340f5ba35268e4eea6d4d2025-08-20T03:32:15ZengMDPI AGRemote Sensing2072-42922025-07-011714240910.3390/rs17142409A Multi-Feature Fusion Approach for Sea Fog Detection Under Complex BackgroundShuyuan Yang0Yuzhu Tang1Zeming Zhou2Xiaofeng Zhao3Pinglv Yang4Yangfan Hu5Ran Bo6College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing 211169, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaCollege of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, ChinaSea fog is a natural phenomenon that significantly reduces visibility, posing navigational hazards for ships and impacting coastal activities. Geostationary meteorological satellite data have proven to be indispensable for sea fog monitoring due to their large spatial coverage and spatiotemporal consistency. However, the spectral similarities between sea fog and low clouds result in omissions and misclassifications. Furthermore, high clouds obscure certain sea fog regions, leading to under-detection and high false alarm rates. In this paper, we present a novel sea fog detection method to alleviate the challenges. Specifically, the approach leverages a fusion of spectral, motion, and spatiotemporal texture consistency features to effectively differentiate sea fog and low clouds. Additionally, a multi-scale self-attention module is incorporated to recover the sea fog region obscured by clouds. Based on the spatial distribution characteristics of sea fog and clouds, we redesigned the loss function to integrate total variation loss, focal loss, and dice loss. Experimental results validate the effectiveness of the proposed method, and the detection accuracy is compared with the vertical feature mask produced by the CALIOP and exhibits a high level of consistency.https://www.mdpi.com/2072-4292/17/14/2409sea fog detectioncomplex backgroundsmulti-feature fusionmulti-scale self-attention
spellingShingle Shuyuan Yang
Yuzhu Tang
Zeming Zhou
Xiaofeng Zhao
Pinglv Yang
Yangfan Hu
Ran Bo
A Multi-Feature Fusion Approach for Sea Fog Detection Under Complex Background
Remote Sensing
sea fog detection
complex backgrounds
multi-feature fusion
multi-scale self-attention
title A Multi-Feature Fusion Approach for Sea Fog Detection Under Complex Background
title_full A Multi-Feature Fusion Approach for Sea Fog Detection Under Complex Background
title_fullStr A Multi-Feature Fusion Approach for Sea Fog Detection Under Complex Background
title_full_unstemmed A Multi-Feature Fusion Approach for Sea Fog Detection Under Complex Background
title_short A Multi-Feature Fusion Approach for Sea Fog Detection Under Complex Background
title_sort multi feature fusion approach for sea fog detection under complex background
topic sea fog detection
complex backgrounds
multi-feature fusion
multi-scale self-attention
url https://www.mdpi.com/2072-4292/17/14/2409
work_keys_str_mv AT shuyuanyang amultifeaturefusionapproachforseafogdetectionundercomplexbackground
AT yuzhutang amultifeaturefusionapproachforseafogdetectionundercomplexbackground
AT zemingzhou amultifeaturefusionapproachforseafogdetectionundercomplexbackground
AT xiaofengzhao amultifeaturefusionapproachforseafogdetectionundercomplexbackground
AT pinglvyang amultifeaturefusionapproachforseafogdetectionundercomplexbackground
AT yangfanhu amultifeaturefusionapproachforseafogdetectionundercomplexbackground
AT ranbo amultifeaturefusionapproachforseafogdetectionundercomplexbackground
AT shuyuanyang multifeaturefusionapproachforseafogdetectionundercomplexbackground
AT yuzhutang multifeaturefusionapproachforseafogdetectionundercomplexbackground
AT zemingzhou multifeaturefusionapproachforseafogdetectionundercomplexbackground
AT xiaofengzhao multifeaturefusionapproachforseafogdetectionundercomplexbackground
AT pinglvyang multifeaturefusionapproachforseafogdetectionundercomplexbackground
AT yangfanhu multifeaturefusionapproachforseafogdetectionundercomplexbackground
AT ranbo multifeaturefusionapproachforseafogdetectionundercomplexbackground