HDSA-Net: Haze Density and Semantic Awareness Network for Hyperspectral Image Dehazing

Hyperspectral image (HSI) dehazing is a challenging task due to the complex imaging conditions. Existing deep learning-based dehazing methods neither fully consider the physical characteristics of HSIs, nor take advantage of high-level semantic information to improve the dehazing performance. To rem...

Full description

Saved in:
Bibliographic Details
Main Authors: Qianru Liu, Tiecheng Song, Anyong Qin, Yin Liu, Feng Yang, Chenqiang Gao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10820032/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832582413375504384
author Qianru Liu
Tiecheng Song
Anyong Qin
Yin Liu
Feng Yang
Chenqiang Gao
author_facet Qianru Liu
Tiecheng Song
Anyong Qin
Yin Liu
Feng Yang
Chenqiang Gao
author_sort Qianru Liu
collection DOAJ
description Hyperspectral image (HSI) dehazing is a challenging task due to the complex imaging conditions. Existing deep learning-based dehazing methods neither fully consider the physical characteristics of HSIs, nor take advantage of high-level semantic information to improve the dehazing performance. To remedy these, in this article we propose a Haze Density and Semantic Awareness Network (HDSA-Net) for HSI dehazing. Our dual-awareness network not only provides low-level physical information guidance but also high-level semantic guidance for haze removal. Specifically, we estimate the haze density by considering both internal spectral characteristics and external dehazing effects. Based on this, we build a Haze Density Awareness (HDA) block, which enables the network to perceive and focus on difficult dehazing regions with high density. Moreover, we design a Semantic information Extraction Block (SEB) based on the pretrained Segment Anything Model (SAM), followed by several Semantic information Perception Blocks (SPBs), to provide semantic guidance for HSI dehazing. In particular, SEB adapts SAM for the special HSI data and SPBs enable the network to progressively recover semantic information via channel-level coarse guidance and pixel-level fine guidance. The experimental results on simulated and real datasets show the superiority of HDSA-Net over state-of-the-art methods.
format Article
id doaj-art-e9c54fe050184a1a992edeaac065104c
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-e9c54fe050184a1a992edeaac065104c2025-01-30T00:00:13ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183989400310.1109/JSTARS.2024.352507210820032HDSA-Net: Haze Density and Semantic Awareness Network for Hyperspectral Image DehazingQianru Liu0https://orcid.org/0009-0000-8510-0614Tiecheng Song1https://orcid.org/0000-0003-1264-2812Anyong Qin2https://orcid.org/0000-0002-2538-822XYin Liu3https://orcid.org/0000-0002-4555-1944Feng Yang4https://orcid.org/0000-0003-0413-8640Chenqiang Gao5https://orcid.org/0000-0003-4174-4148School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong, ChinaHyperspectral image (HSI) dehazing is a challenging task due to the complex imaging conditions. Existing deep learning-based dehazing methods neither fully consider the physical characteristics of HSIs, nor take advantage of high-level semantic information to improve the dehazing performance. To remedy these, in this article we propose a Haze Density and Semantic Awareness Network (HDSA-Net) for HSI dehazing. Our dual-awareness network not only provides low-level physical information guidance but also high-level semantic guidance for haze removal. Specifically, we estimate the haze density by considering both internal spectral characteristics and external dehazing effects. Based on this, we build a Haze Density Awareness (HDA) block, which enables the network to perceive and focus on difficult dehazing regions with high density. Moreover, we design a Semantic information Extraction Block (SEB) based on the pretrained Segment Anything Model (SAM), followed by several Semantic information Perception Blocks (SPBs), to provide semantic guidance for HSI dehazing. In particular, SEB adapts SAM for the special HSI data and SPBs enable the network to progressively recover semantic information via channel-level coarse guidance and pixel-level fine guidance. The experimental results on simulated and real datasets show the superiority of HDSA-Net over state-of-the-art methods.https://ieeexplore.ieee.org/document/10820032/Deep learningdehazinghaze removalhyperspectral imagesSAM
spellingShingle Qianru Liu
Tiecheng Song
Anyong Qin
Yin Liu
Feng Yang
Chenqiang Gao
HDSA-Net: Haze Density and Semantic Awareness Network for Hyperspectral Image Dehazing
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning
dehazing
haze removal
hyperspectral images
SAM
title HDSA-Net: Haze Density and Semantic Awareness Network for Hyperspectral Image Dehazing
title_full HDSA-Net: Haze Density and Semantic Awareness Network for Hyperspectral Image Dehazing
title_fullStr HDSA-Net: Haze Density and Semantic Awareness Network for Hyperspectral Image Dehazing
title_full_unstemmed HDSA-Net: Haze Density and Semantic Awareness Network for Hyperspectral Image Dehazing
title_short HDSA-Net: Haze Density and Semantic Awareness Network for Hyperspectral Image Dehazing
title_sort hdsa net haze density and semantic awareness network for hyperspectral image dehazing
topic Deep learning
dehazing
haze removal
hyperspectral images
SAM
url https://ieeexplore.ieee.org/document/10820032/
work_keys_str_mv AT qianruliu hdsanethazedensityandsemanticawarenessnetworkforhyperspectralimagedehazing
AT tiechengsong hdsanethazedensityandsemanticawarenessnetworkforhyperspectralimagedehazing
AT anyongqin hdsanethazedensityandsemanticawarenessnetworkforhyperspectralimagedehazing
AT yinliu hdsanethazedensityandsemanticawarenessnetworkforhyperspectralimagedehazing
AT fengyang hdsanethazedensityandsemanticawarenessnetworkforhyperspectralimagedehazing
AT chenqianggao hdsanethazedensityandsemanticawarenessnetworkforhyperspectralimagedehazing