Lightweight Band-Adaptive Hyperspectral Image Compression With Feature Decouple and Recurrent Model

Advanced deep-learning methodologies have led to notable improvements in hyperspectral image compression. While most existing deep learning approaches primarily concentrate on reducing spatial redundancy, the challenge of addressing spectral redundancy remains unresolved. Furthermore, the implementa...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiahui Liu, Lili Zhang, Jingang Wang, Lele Qu
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/11061775/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850101511247364096
author Jiahui Liu
Lili Zhang
Jingang Wang
Lele Qu
author_facet Jiahui Liu
Lili Zhang
Jingang Wang
Lele Qu
author_sort Jiahui Liu
collection DOAJ
description Advanced deep-learning methodologies have led to notable improvements in hyperspectral image compression. While most existing deep learning approaches primarily concentrate on reducing spatial redundancy, the challenge of addressing spectral redundancy remains unresolved. Furthermore, the implementation of current models in resource-limited settings is often impeded by their high parameter counts and computational demands. To address these challenges, we propose a lightweight band-adaptive hyperspectral image compression model (LBA-HIM) aimed at enhancing compression efficiency while ensuring low computational overhead. LBA-HIM incorporates a feature decoupling mechanism that effectively separates hyperspectral images into fundamental and detailed features, thereby facilitating the reduction of spatial redundancy while preserving critical image details. In addition, a recurrent structure is integrated into the band encoding and decoding processes, enabling the utilization of prior information from previously processed bands in subsequent operations. This strategy contributes to more efficient data compression by minimizing spectral redundancy. An adaptive weighted fusion mechanism is also employed to optimize the integration of multilevel features. Evaluation across six hyperspectral datasets indicates that the LBA-HIM model significantly enhances both compression efficiency and image quality while simultaneously lowering computational costs. At a compression rate of 0.25 bits per pixel per band, LBA-HIM achieves an average peak signal-to-noise ratio of 38.25 dB, which represents an improvement of approximately 2.5 dB over the current state-of-the-art techniques.
format Article
id doaj-art-b98e26d7656742caa4f1ba1bd2fea070
institution DOAJ
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-b98e26d7656742caa4f1ba1bd2fea0702025-08-20T02:39:59ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118167331674910.1109/JSTARS.2025.358493111061775Lightweight Band-Adaptive Hyperspectral Image Compression With Feature Decouple and Recurrent ModelJiahui Liu0https://orcid.org/0009-0006-6421-7833Lili Zhang1https://orcid.org/0000-0002-9287-3612Jingang Wang2Lele Qu3https://orcid.org/0000-0002-2794-8892College of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang, ChinaCollege of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang, ChinaCollege of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang, ChinaCollege of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang, ChinaAdvanced deep-learning methodologies have led to notable improvements in hyperspectral image compression. While most existing deep learning approaches primarily concentrate on reducing spatial redundancy, the challenge of addressing spectral redundancy remains unresolved. Furthermore, the implementation of current models in resource-limited settings is often impeded by their high parameter counts and computational demands. To address these challenges, we propose a lightweight band-adaptive hyperspectral image compression model (LBA-HIM) aimed at enhancing compression efficiency while ensuring low computational overhead. LBA-HIM incorporates a feature decoupling mechanism that effectively separates hyperspectral images into fundamental and detailed features, thereby facilitating the reduction of spatial redundancy while preserving critical image details. In addition, a recurrent structure is integrated into the band encoding and decoding processes, enabling the utilization of prior information from previously processed bands in subsequent operations. This strategy contributes to more efficient data compression by minimizing spectral redundancy. An adaptive weighted fusion mechanism is also employed to optimize the integration of multilevel features. Evaluation across six hyperspectral datasets indicates that the LBA-HIM model significantly enhances both compression efficiency and image quality while simultaneously lowering computational costs. At a compression rate of 0.25 bits per pixel per band, LBA-HIM achieves an average peak signal-to-noise ratio of 38.25 dB, which represents an improvement of approximately 2.5 dB over the current state-of-the-art techniques.https://ieeexplore.ieee.org/document/11061775/Adaptive weighted fusionband-adaptive compressionfeature decouplinghyperspectral image compressionlightweight modelrecurrent structure
spellingShingle Jiahui Liu
Lili Zhang
Jingang Wang
Lele Qu
Lightweight Band-Adaptive Hyperspectral Image Compression With Feature Decouple and Recurrent Model
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Adaptive weighted fusion
band-adaptive compression
feature decoupling
hyperspectral image compression
lightweight model
recurrent structure
title Lightweight Band-Adaptive Hyperspectral Image Compression With Feature Decouple and Recurrent Model
title_full Lightweight Band-Adaptive Hyperspectral Image Compression With Feature Decouple and Recurrent Model
title_fullStr Lightweight Band-Adaptive Hyperspectral Image Compression With Feature Decouple and Recurrent Model
title_full_unstemmed Lightweight Band-Adaptive Hyperspectral Image Compression With Feature Decouple and Recurrent Model
title_short Lightweight Band-Adaptive Hyperspectral Image Compression With Feature Decouple and Recurrent Model
title_sort lightweight band adaptive hyperspectral image compression with feature decouple and recurrent model
topic Adaptive weighted fusion
band-adaptive compression
feature decoupling
hyperspectral image compression
lightweight model
recurrent structure
url https://ieeexplore.ieee.org/document/11061775/
work_keys_str_mv AT jiahuiliu lightweightbandadaptivehyperspectralimagecompressionwithfeaturedecoupleandrecurrentmodel
AT lilizhang lightweightbandadaptivehyperspectralimagecompressionwithfeaturedecoupleandrecurrentmodel
AT jingangwang lightweightbandadaptivehyperspectralimagecompressionwithfeaturedecoupleandrecurrentmodel
AT lelequ lightweightbandadaptivehyperspectralimagecompressionwithfeaturedecoupleandrecurrentmodel