Spatial-Spectral Bipartite Graph Clustering With Low-Frequency Tensor Regularization for Hyperspectral and LiDAR Data

The increasing complexity of remote sensing (RS) applications necessitates multimodal data fusion to overcome the inherent limitations of single-source data. In particular, the integration of hyperspectral images (HSIs) and light detection and ranging (LiDAR) data captures complementary spectral and...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing Vol. 63; pp. 1 - 17
Main Authors: Cao, Zhe, Lu, Yihang, Xin, Haonan, Yu, Chuanqiang, Wang, Rong, Nie, Feiping
Format: Journal Article
Language:English
Published: New York IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accuracy
Annotations
Band selection
Bipartite graph
Clustering
Clustering algorithms
Complexity
Computational efficiency
Data integration
Graph theory
Hyperspectral imaging
Information processing
Laser radar
Lidar
low-frequency tensor nuclear norm (LFTNN)
multimodal remote sensing (RS)
Multisensor fusion
Regularization
Remote sensing
Scene analysis
spatial bipartite graph
Spatial data
Surface topography
Synthetic aperture radar
Tensors
Unsupervised learning
ISSN:0196-2892, 1558-0644
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The increasing complexity of remote sensing (RS) applications necessitates multimodal data fusion to overcome the inherent limitations of single-source data. In particular, the integration of hyperspectral images (HSIs) and light detection and ranging (LiDAR) data captures complementary spectral and spatial features, significantly enhancing object discrimination. Unlike supervised methods requiring costly expert annotations, unsupervised clustering eliminates labeling needs, thereby offering an efficient solution for complex scene analysis with reduced deployment costs. However, existing unsupervised clustering methods still face several challenges, including insufficient utilization of spatial information, high data dimensionality, and interference from high-frequency noise, which collectively hinder their further development and practical application. To address these issues, this article proposes a novel method called spatial-spectral bipartite graph clustering with low-frequency tensor (SSBC-LFT) regularization for hyperspectral and LiDAR data. The proposed method first focuses on modeling clustering structures, innovatively constructing spatially informed bipartite graphs for each modality to enrich spatial details while reducing computational complexity. Additionally, an adaptive spectral band selection mechanism dynamically assigns higher weights to discriminative bands during clustering while suppressing redundant ones. Finally, through proposed low-frequency tensor nuclear norm (LFTNN) regularization, high-frequency noise is effectively filtered in the frequency domain, extracting stable and consistent cross-modal structural information from the low-rank space to further enhance clustering robustness and accuracy. Extensive experiments on real-world multimodal RS datasets demonstrate the superior performance of the SSBC-LFT model, offering a robust and effective solution for unsupervised clustering in complex scenarios.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2025.3622499