Dual-Domain Fusion Network Based on Wavelet Frequency Decomposition and Fuzzy Spatial Constraint for Remote Sensing Image Segmentation

被引:3
作者
Wei, Guangyi [1 ]
Xu, Jindong [1 ]
Yan, Weiqing [1 ]
Chong, Qianpeng [2 ]
Xing, Haihua [3 ]
Ni, Mengying [1 ]
机构
[1] Yantai Univ, Sch Comp & Control Engn, Yantai 264005, Peoples R China
[2] Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China
[3] Hainan Normal Univ, Sch Informat Sci & Technol, Haikou 571158, Peoples R China
基金
中国国家自然科学基金;
关键词
remote sensing; semantic segmentation; wavelet transform; type-2; fuzzy; SEMANTIC SEGMENTATION; CHALLENGES; CLASSIFICATION; FRAMEWORK;
D O I
10.3390/rs16193594
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Semantic segmentation is crucial for a wide range of downstream applications in remote sensing, aiming to classify pixels in remote sensing images (RSIs) at the semantic level. The dramatic variations in grayscale and the stacking of categories within RSIs lead to unstable inter-class variance and exacerbate the uncertainty around category boundaries. However, existing methods typically emphasize spatial information while overlooking frequency insights, making it difficult to achieve desirable results. To address these challenges, we propose a novel dual-domain fusion network that integrates both spatial and frequency features. For grayscale variations, a multi-level wavelet frequency decomposition module (MWFD) is introduced to extract and integrate multi-level frequency features to enhance the distinctiveness between spatially similar categories. To mitigate the uncertainty of boundaries, a type-2 fuzzy spatial constraint module (T2FSC) is proposed to achieve flexible higher-order fuzzy modeling to adaptively constrain the boundary features in the spatial by constructing upper and lower membership functions. Furthermore, a dual-domain feature fusion (DFF) module bridges the semantic gap between the frequency and spatial features, effectively realizes semantic alignment and feature fusion between the dual domains, which further improves the accuracy of segmentation results. We conduct comprehensive experiments and extensive ablation studies on three well-known datasets: Vaihingen, Potsdam, and GID. In these three datasets, our method achieved 74.56%, 73.60%, and 81.01% mIoU, respectively. Quantitative and qualitative results demonstrate that the proposed method significantly outperforms state-of-the-art methods, achieving an excellent balance between segmentation accuracy and computational overhead.
引用
收藏
页数:24
相关论文
共 70 条
[1]   Transformers in Remote Sensing: A Survey [J].
Aleissaee, Abdulaziz Amer ;
Kumar, Amandeep ;
Anwer, Rao Muhammad ;
Khan, Salman ;
Cholakkal, Hisham ;
Xia, Gui-Song ;
Khan, Fahad Shahbaz .
REMOTE SENSING, 2023, 15 (07)
[2]   More Than Accuracy: A Composite Learning Framework for Interval Type-2 Fuzzy Logic Systems [J].
Beke, Aykut ;
Kumbasar, Tufan .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2023, 31 (03) :734-744
[3]   Combining max-pooling and wavelet pooling strategies for semantic image segmentation [J].
Brito, Andre de Souza ;
Vieira, Marcelo Bernardes ;
Sguario Coelho de Andrade, Mauren Louise ;
Feitosa, Raul Queiroz ;
Giraldi, Gilson Antonio .
EXPERT SYSTEMS WITH APPLICATIONS, 2021, 183
[4]   A Historical Account of Types of Fuzzy Sets and Their Relationships [J].
Bustince, Humberto ;
Barrenechea, Edurne ;
Pagola, Miguel ;
Fernandez, Javier ;
Xu, Zeshui ;
Bedregal, Benjamin ;
Montero, Javier ;
Hagras, Hani ;
Herrera, Francisco ;
De Baets, Bernard .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2016, 24 (01) :179-194
[5]   Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [J].
Chen, Liang-Chieh ;
Zhu, Yukun ;
Papandreou, George ;
Schroff, Florian ;
Adam, Hartwig .
COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :833-851
[6]   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
[7]   Road extraction in remote sensing data: A survey [J].
Chen, Ziyi ;
Deng, Liai ;
Luo, Yuhua ;
Li, Dilong ;
Marcato Junior, Jose ;
Gonsalves, Wesley Nunes ;
Nurunnabi, Abdul Awal Md ;
Li, Jonathan ;
Wang, Cheng ;
Li, Deren .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2022, 112
[8]   Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities [J].
Cheng, Gong ;
Xie, Xingxing ;
Han, Junwei ;
Guo, Lei ;
Xia, Gui-Song .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2020, 13 :3735-3756
[9]   Pos-DANet: A dual-branch awareness network for small object segmentation within high-resolution remote sensing images [J].
Chong, Qianpeng ;
Ni, Mengying ;
Huang, Jianjun ;
Liang, Zongbao ;
Wang, Jie ;
Li, Ziyi ;
Xu, Jindong .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 133
[10]   A multiscale bidirectional fuzzy-driven learning network for remote sensing image segmentation [J].
Chong, Qianpeng ;
Xu, Jindong ;
Ding, Yang ;
Dai, Zhe .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2023, 44 (21) :6860-6881