EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reliability-Aware Feedback-Controlled Fusion for Spatially Disjoint HSI–LiDAR Classification

Davaajargal Myagmarsuren, Haibin Wu, Aili Wang, Minhui Wang

Remote Sensing · 30.10.2026 · 18 (21) · 3749

DOI: 10.3390/rs18213749 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 30.10.2026. Verfasst von Davaajargal Myagmarsuren und 3 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Key Research and Development Plan Project of Heilongjiang, the National Key Support Project for Foreign Experts of Northeast Special Project, Shandong Provincial Natural Science Foundation Youth Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a reliability-aware feedback-controlled fusion framework for hyperspectral image (HSI) and LiDAR classification under spatially disjoint conditions. Instead of committing to a fixed fusion configuration, the framework couples a library of fusion operators (geometry-aware fusion, adaptive gating, cross-modal transformer fusion and physics-informed fusion), integrated within a unified GhostConv-based architecture, with a closed-loop controller that evaluates candidate operators on validation data, accepts them only when they improve validation accuracy, and applies feedback-guided residual refinement. Experiments are conducted on Houston2013, Muufl, and Augsburg under a sample-center spatially disjoint protocol, in which training and validation samples are drawn from development blocks that are spatially disjoint from the test blocks, with seven labeled samples per class and ten random partitions. The framework achieves mean overall accuracies of 70.00%, 73.20%, and 66.34%, improving the Baseline-Ghost model on Houston2013, Muufl, and Augsburg; the improvement achieved by closed-loop training is preserved under a patch-disjoint protocol. Budget-matched analyses show that, with seven labels per class, the gain stems mainly from validation-gated closed-loop training and feedback-guided refinement, whereas the benefit of adaptive operator switching emerges as the label budget increases.

Förderung

  • the Key Research and Development Plan Project of Heilongjiang
  • the National Key Support Project for Foreign Experts of Northeast Special Project
  • Shandong Provincial Natural Science Foundation Youth Project

Zitieren

APA

Myagmarsuren, D., Wu, H., Wang, A., & Wang, M. (2026). Reliability-Aware Feedback-Controlled Fusion for Spatially Disjoint HSI–LiDAR Classification. Remote Sensing, 18(21), 3749. https://doi.org/10.3390/rs18213749

Vancouver

Myagmarsuren D, Wu H, Wang A, Wang M. Reliability-Aware Feedback-Controlled Fusion for Spatially Disjoint HSI–LiDAR Classification. Remote Sensing. 2026;18(21):3749. doi:10.3390/rs18213749

BibTeX
@article{Myagmarsuren2026,
  author = {Myagmarsuren, Davaajargal and Wu, Haibin and Wang, Aili and Wang, Minhui},
  title = {Reliability-Aware Feedback-Controlled Fusion for Spatially Disjoint HSI–LiDAR Classification},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {21},
  pages = {3749},
  doi = {10.3390/rs18213749}
}
Kostenlos starten →