2026· IEEE Transactions on Geoscience and Remote Sensing· Vol 64, pp. 4420017-4420017· 0 citations· 61 references
TL;DR
A local–global cross-modal fusion network (LGCF-Net), a hybrid fusion framework that explicitly models local–global feature interactions for HSI–LiDAR classification and achieves the best overall accuracy on MUUFL, Trento, and Augsburg, while attaining the highest average accuracy and Kappa on Houston.
Abstract
Hyperspectral imagery (HSI) and LiDAR data provide complementary spectral and structural information, which, when fused, can significantly improve land-cover classification. However, the heterogeneity of these modalities makes feature interaction and redundancy suppression challenging. In particular, existing approaches often overlook the importance of modeling interactions between local and global representations across modalities. This article proposes a local–global cross-modal fusion network (LGCF-Net), a hybrid fusion framework that explicitly models local–global feature interactions for HSI–LiDAR classification. The framework consists of four modules. First, the spectral–spatial transition refinement (SSTR) module extracts hierarchical spectral–spatial features using a pyramid convolution strategy. Second, the LiDAR feature enhancement module (LFEM) extracts spatial features from the LiDAR modality. Third, the cross-modal convolutional transformer (CMCT) incorporates multiscale convolutional layers into the transformer architecture to capture local–global contextual features, followed by residual-gated cross-modal attention (RGCA) for cross-modal interaction. RGCA facilitates information exchange between HSI and LiDAR while suppressing redundant features. Finally, the classification token mixer (CTM) module aggregates refined features for the final prediction. Extensive experiments on four benchmark HSI–LiDAR fusion datasets demonstrate that LGCF-Net achieves the best overall accuracy (OA) on MUUFL, Trento, and Augsburg, while attaining the highest average accuracy (AA) and Kappa on Houston.
Multimodal land-cover classification with hyperspectral imagery and light detection and ranging (LiDAR) data remains challenging because of spectral–spatial heterogeneity, modality differences, and limited local discriminability under small-sample supervision. This article proposes a dual-branch multimodal mutual-trans...
Man-Liang Cao, Xu-Kang Han, Bao-Jiang Li et al.· IEEE Journal of Selected Top...· 0 citations
The proposed TriFusion framework consistently achieves the best overall accuracy among recent CNN-based, Transformer-based, and hybrid methods, with gains of 0.26–1.42 percentage points over the strongest competing baseline across the four datasets.
Fei-Long Fan, An-Ming Dong, En Li et al.· IEEE Journal of Selected Top...· 0 citations
The integration of multisource information from hyperspectral imagery (HSI) and light detection and ranging (LiDAR) provides reliable data support for land cover classification. The heterogeneity between HSI and LiDAR data poses significant challenges for cross-modal feature alignment, while the rich structural priors...
Yu-Qing Zhao, Yu Song, Chao Liang et al.· IEEE Journal of Selected Top...· 0 citations
Hyperspectral images (HSIs), with their hundreds of contiguous narrow bands, capture detailed physicochemical properties of land covers; LiDAR provides high-precision 3-D spatial and geometric structure, and the two modalities are highly complementary. However, differences in imaging mechanisms lead to insufficient cro...
Shu-Fang Xu, Wei-Wen Xu, Qi-Yuan Xue et al.· IEEE Transactions on Geoscie...· 0 citations
Hyperspectral image classification is an important research topic in the field of remote sensing. Its core objective is to accurately identify different land-cover categories by jointly exploiting the spatial information and spectral characteristics of pixels. However, the complex and diverse spatial structures of grou...
Li-Guo Wang, Teng Wen, Dan-Feng Liu· Remote Sensing· 0 citations
Results confirm that BMCA effectively preserves fine-grained spatial details, promotes semantic consistency across modalities, and provides a robust and generalizable solution for feature-level SAR–MS fusion in remote-sensing semantic segmentation.
Hao-Tian Xu, Xi-Min Yuan, Xiu-Jie Wang et al.· Remote Sensing· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.