EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DINOv3-Driven Semantic Segmentation for Landslide Mapping in Mountainous Regions

Zhiyi Dou iD, Edore Akpokodje iD, Yuelin He, Yuxin Liu, Zixuan Ni, Chang'an Xu, Muhammad Aslam iD, Meng Tang iD

Sensors · 08.01.2026 · 26 (2) · 406

DOI: 10.3390/s26020406 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.01.2026. Verfasst von Zhiyi Dou und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Earth and Environmental Sciences, Faculty of Science, The University of Queensland, Brisbane, QLD 4072, Australia. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Landslide hazard assessment increasingly demands the joint analysis of heterogeneous remote sensing data; however, automating this process remains difficult due to the pronounced resolution and texture discrepancies existing between satellite and aerial sensors. To address these limitations, this study proposes a robust segmentation framework capable of extracting sensor-robust representations. The framework leverages a DINOv3 transformer encoder and exploits representations from multiple transformer layers to capture complementary visual information, ranging from fine-grained surface textures to global semantic contexts, overcoming the receptive field constraints of conventional CNNs. Experiments on the Longxi satellite dataset achieve a Dice coefficient of 0.96 and an IoU of 0.938, and experiments on the Longxi UAV dataset achieve a Dice coefficient of 0.965 and an IoU of 0.941. These results show consistent segmentation performance on both the Longxi satellite and UAV datasets, despite differences in spatial resolution and surface appearance between acquisition platforms.

Schlagwörter

Stichwörter der Autor:innen

cross-sensor applicabilitylandslide segmentationmulti-source data integrationremote sensingsensor processing

Autor:innen und Institutionen

  • School of Earth and Environmental Sciences, Faculty of Science, The University of Queensland, Brisbane, QLD 4072, Australia.
  • Department of Computer Science, Aberystwyth University, Penglais, Aberystwyth SY23 3DB, UK.
  • Department of Computer Science, Peking University, Beijing 100871, China.
  • State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China.
  • Institute of Chemical Engineering, Guangdong Academy of Sciences, Guangzhou 510665, China.

ORCID-Profile: Zhiyi Dou, Edore Akpokodje, Muhammad Aslam, Meng Tang

Zitieren

APA

Dou, Z., Akpokodje, E., He, Y., Liu, Y., Ni, Z., Xu, C., Aslam, M., & Tang, M. (2026). DINOv3-Driven Semantic Segmentation for Landslide Mapping in Mountainous Regions. Sensors, 26(2), 406. https://doi.org/10.3390/s26020406

Vancouver

Dou Z, Akpokodje E, He Y, Liu Y, Ni Z, Xu C, et al. DINOv3-Driven Semantic Segmentation for Landslide Mapping in Mountainous Regions. Sensors. 2026;26(2):406. doi:10.3390/s26020406

BibTeX
@article{Dou2026,
  author = {Dou, Zhiyi and Akpokodje, Edore and He, Yuelin and Liu, Yuxin and Ni, Zixuan and Xu, Chang'an and Aslam, Muhammad and Tang, Meng},
  title = {DINOv3-Driven Semantic Segmentation for Landslide Mapping in Mountainous Regions},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {406},
  doi = {10.3390/s26020406}
}
Kostenlos starten →