A Frequency Decoupling Network for Semantic Segmentation of Remote Sensing Images

被引:26
作者
Li, Xin [1 ,2 ]
Xu, Feng [1 ,2 ,3 ]
Yu, Anzhu [4 ]
Lyu, Xin [1 ,2 ]
Gao, Hongmin [1 ,2 ]
Zhou, Jun [5 ]
机构
[1] Hohai Univ, Coll Comp Sci & Software Engn, Nanjing 211100, Peoples R China
[2] Hohai Univ, Key Lab Water Big Data Technol Minist Water Resour, Nanjing 211100, Peoples R China
[3] Jiangsu Ocean Univ, Sch Comp Engn, Lianyungang 222005, Peoples R China
[4] Informat Engn Univ, Sch Surveying & Mapping, Zhengzhou 450001, Peoples R China
[5] Griffith Univ, Sch Informat & Commun Technol, Nathan, Qld 4111, Australia
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2025年 / 63卷
基金
中国国家自然科学基金;
关键词
Transformers; Frequency-domain analysis; Semantic segmentation; Accuracy; Context modeling; Remote sensing; Computational modeling; Attention mechanisms; Feature extraction; Water resources; Attention mechanism; frequency domain; remote sensing images (RSIs); semantic segmentation; HYPERSPECTRAL IMAGE; ATTENTION;
D O I
10.1109/TGRS.2025.3531879
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Semantic segmentation of remote sensing images (RSIs) is vital for numerous geospatial applications, including land-use mapping, urban planning, and environmental monitoring. Traditional neural networks for semantic segmentation primarily focus on learning in the spatial domain, which often results in suboptimal performance due to the complexity of RSIs that exhibit diverse and intricate structures. To address this problem, we propose a novel frequency decoupling network (FDNet) that enhances feature representation by independently refining high-frequency and low-frequency components in the frequency domain. FDNet introduces three core components: a sparse-aware spectral enhancement module (SSEM) that optimizes spectral feature learning by compressing redundant information while highlighting informative spectral bands, a frequency decoupling attention module (FDAM) that precisely distinguishes and enhances high-frequency and low-frequency features and an attentive frequency context module (AFCM) that integrates SSEM and FDAM into a cohesive framework for enriched spectral context modeling. Extensive experiments conducted on four benchmark datasets demonstrate that FDNet outperforms several state-of-the-art methods, achieving superior segmentation accuracy and robustness across various terrains and imaging conditions. Ablation experiments further confirm the impacts of SSEM, FDAM, and AFCM.
引用
收藏
页数:21
相关论文
共 103 条
[1]   A novel ensemble learning approach to extract urban impervious surface based on machine learning algorithms using SAR and optical data [J].
Ahmad, Muhammad Nasar ;
Shao, Zhenfeng ;
Xiao, Xiongwu ;
Fu, Peng ;
Javed, Akib ;
Ara, Iffat .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2024, 132
[2]   Modelling land use/land cover (LULC) change dynamics, future prospects, and its environmental impacts based on geospatial data models and remote sensing data [J].
Ahmad, Muhammad Nasar ;
Shao, Zhenfeng ;
Javed, Akib .
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2023, 30 (12) :32985-33001
[3]   Deep semantic segmentation of natural and medical images: a review [J].
Asgari Taghanaki, Saeid ;
Abhishek, Kumar ;
Cohen, Joseph Paul ;
Cohen-Adad, Julien ;
Hamarneh, Ghassan .
ARTIFICIAL INTELLIGENCE REVIEW, 2021, 54 (01) :137-178
[4]   Unlocking Fine-Grained Details with Wavelet-Based High-Frequency Enhancement in Transformers [J].
Azad, Reza ;
Kazerouni, Amirhossein ;
Sulaiman, Alaa ;
Bozorgpour, Afshin ;
Aghdam, Ehsan Khodapanah ;
Jose, Abin ;
Merhof, Dorit .
MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT I, 2024, 14348 :207-216
[5]   SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [J].
Badrinarayanan, Vijay ;
Kendall, Alex ;
Cipolla, Roberto .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) :2481-2495
[6]   Semantic Segmentation of Remote Sensing Images With Transformer-Based U-Net and Guided Focal-Axial Attention [J].
Blaga, Bianca-Cerasela-Zelia ;
Nedevschi, Sergiu .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 :18303-18318
[7]  
Bo DY, 2021, AAAI CONF ARTIF INTE, V35, P3950
[8]   DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].
Chen, Liang-Chieh ;
Papandreou, George ;
Kokkinos, Iasonas ;
Murphy, Kevin ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848
[9]   Updating Road Maps at City Scale With Remote Sensed Images and Existing Vector Maps [J].
Chen, Xin ;
Yu, Anzhu ;
Sun, Qun ;
Guo, Wenyue ;
Xu, Qing ;
Wen, Bowei .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 :1-21
[10]   DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images [J].
Demir, Ilke ;
Koperski, Krzysztof ;
Lindenbaum, David ;
Pang, Guan ;
Huang, Jing ;
Bast, Saikat ;
Hughes, Forest ;
Tuia, Devis ;
Raskar, Ramesh .
PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, :172-181