中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Bridging HSI and LiDAR Data With Frequency-Domain Hierarchical Fusion for Enhanced Classification

文献类型：期刊论文

作者Gong, Luqi1,2; Bai, Rui5; Li, Yilang4; Chen, Yue2; Fan, Fanda3; Zhao, Shuai1; Li, Chao2
刊名IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
出版日期2025
卷号63页码:18
关键词Frequency-domain analysis Laser radar Feature extraction Data mining Phase frequency detectors Remote sensing Principal component analysis Soft sensors Fast Fourier transforms Accuracy Category-aware frequency domain hyperspectral imaging (HSI) light detection and ranging (LiDAR) image
ISSN号0196-2892
DOI10.1109/TGRS.2025.3589080
英文摘要Remote sensing data from hyperspectral imaging (HSI) and light detection and ranging (LiDAR) provide complementary perspectives for terrain and object analysis. However, existing methods for multimodal data fusion primarily focus on spatial-domain feature alignment, often overlooking the potential of frequency-domain information to enhance classification accuracy. To bridge this gap, we introduce the frequency-domain hierarchical perception fusion network (FHPF-Net), a novel framework for precise classification of remote sensing images. This network leverages both spatial-domain information and frequency-domain information and provides a new perspective for heterogeneous data integration. To extract and utilize frequency-domain features, we propose the high-to-low spectral separation and mining (HLSSM) module, which isolates high-frequency details such as edges and textures from low-frequency structural patterns in HSI and LiDAR data. This separation facilitates targeted feature extraction (FE) while preserving crucial contextual information. Additionally, we introduce the hierarchical superimposed multidomain information fusion (HSMIF) module, which employs a multilevel fusion strategy to integrate spatial- and frequency-domain features, ensuring consistency and complementarity between the two data sources. Finally, we introduce a learnable voting pre-label fusion (LVPF) strategy to effectively integrate multibranch outputs, enhancing classification performance and model robustness. The proposed FHPF-Net effectively captures diverse responses across heterogeneous data types, enabling robust classification in complex environments. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods.
资助项目National Natural Science Foundation of China[62472043] ; National Natural Science Foundation of China[U21A20468] ; National Key Research and Development Program of China[2022YFB4501600]
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:001582016000008
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/41646]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhao, Shuai; Li, Chao
作者单位1.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China
2.Zhejiang Lab, Res Ctr Space Comp Syst, Hangzhou 311121, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
4.Changsha Univ Sci & Technol, Sch Phys & Elect, Changsha 410004, Peoples R China
5.Beihang Univ, Sch Econ & Management, Beijing 100191, Peoples R China
推荐引用方式
GB/T 7714		 Gong, Luqi,Bai, Rui,Li, Yilang,et al. Bridging HSI and LiDAR Data With Frequency-Domain Hierarchical Fusion for Enhanced Classification[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2025,63:18.
APA Gong, Luqi.,Bai, Rui.,Li, Yilang.,Chen, Yue.,Fan, Fanda.,...&Li, Chao.(2025).Bridging HSI and LiDAR Data With Frequency-Domain Hierarchical Fusion for Enhanced Classification.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,63,18.
MLA Gong, Luqi,et al."Bridging HSI and LiDAR Data With Frequency-Domain Hierarchical Fusion for Enhanced Classification".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63(2025):18.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。