A Multi-Modal Remote Sensing Image Classification Method Based on Physics-Guided Feature Decoupling and Adaptive Collaborative Fusion of HSI–LiDAR
Algorithms · 10.06.2026 · 19 (6) · 473
DOI: 10.3390/a19060473 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 10.06.2026. Verfasst von Xiaochen Liu und 2 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Provincial Major Science and Technology Special Project and Key R&D Program.
Abstract (Originalsprache)
Hyperspectral images (HSIs) and Light Detection and Ranging (LiDAR) data offer complementary spectral and spatial information and are extensively applied to land cover classification. Nevertheless, current fusion–classification approaches frequently suffer from cross-modal feature entanglement and insufficient exploitation of LiDAR physical priors, particularly the Digital Surface Model (DSM), which limits the interpretability of learned features and restricts classification accuracy. To address these issues, this study presents a Physics-Guided Adaptive Decoupling and Collaborative Enhancement Network (ADCE-Net) that embeds explicit geometric guidance into multimodal feature learning. In ADCE-Net, the DSM serves as an explicit geometric conditioning signal to guide feature decoupling, decomposing input representations into modality-shared semantic features (SSF) and modality-specific discriminative features (MSF), thereby mitigating cross-modal interference at an early stage. Based on this decomposition, an adaptive collaborative enhancement mechanism is designed using bidirectional cross-attention and dynamic gating to achieve context-aware mutual refinement between SSF and MSF, facilitating more effective utilization of cross-modal complementary information. Furthermore, a multi-level collaborative classification architecture is constructed to integrate multi-scale contextual representations, enhancing spatial consistency and boundary delineation. Extensive experiments on three benchmark datasets—Trento, Houston 2013, and Muufl Gulfport—demonstrate that ADCE-Net achieves overall accuracies of 99.69%, 97.37%, and 94.90%, respectively, surpassing multiple representative methods including support vector machines, 3D convolutional neural networks, transformer-based models, and recurrent neural networks. Noticeable improvements are also achieved for minority classes and classes with highly similar spectral signatures. The DSM-driven physics guidance boosts both classification performance and feature interpretability, providing a reliable and explainable paradigm for multimodal remote sensing classification.
Förderung
- Yunnan Provincial Major Science and Technology Special Project and Key R&D Program
Zitieren
APA
Liu, X., Zhao, J., & Chen, G. (2026). A Multi-Modal Remote Sensing Image Classification Method Based on Physics-Guided Feature Decoupling and Adaptive Collaborative Fusion of HSI–LiDAR. Algorithms, 19(6), 473. https://doi.org/10.3390/a19060473
Vancouver
Liu X, Zhao J, Chen G. A Multi-Modal Remote Sensing Image Classification Method Based on Physics-Guided Feature Decoupling and Adaptive Collaborative Fusion of HSI–LiDAR. Algorithms. 2026;19(6):473. doi:10.3390/a19060473
BibTeX
@article{Liu2026,
author = {Liu, Xiaochen and Zhao, Junsan and Chen, Guoping},
title = {A Multi-Modal Remote Sensing Image Classification Method Based on Physics-Guided Feature Decoupling and Adaptive Collaborative Fusion of HSI–LiDAR},
journal = {Algorithms},
year = {2026},
volume = {19},
number = {6},
pages = {473},
doi = {10.3390/a19060473}
}
EUVIMED