EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CSFS-YOLOv8n: A complex terrain landslide detection model synergistically enhanced by SCConv and SCSA

Runchi Wang iD, Kangcheng Zhu, Hua Wu iD, Jianwei Zhou, Xingwang Chen, Xiangyun Kong, Haonan Wang, Mengke Li, Kexin Yang, Yongqing Zhou, Jiayi Lu, Chao Tian und 2 weitere

PLOS One · 16.11.2026 · 21 (11) · e0361878

DOI: 10.1371/journal.pone.0361878 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 16.11.2026. Verfasst von Runchi Wang und 13 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering, Xizang University, Lhasa, Xizang Autonomous Region, China. Hauptthemen laut MEDLINE: Landslides, Remote Sensing Technology, Models, Theoretical. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Program of Xizang Autonomous Region, China, 2026 Higher Education Reform and Development First-Class Discipline Construction Fund, Construction Project of Talent Innovation Team and Laboratory Platform of Xizang University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Landslides occur frequently in plateau and mountainous regions. Remote sensing images acquired over complex terrain typically suffer from strong background interference, weak features of small-scale landslide targets, imbalanced sample distributions, and difficulties in target localization, which make it difficult for existing detection models to balance detection accuracy with lightweight deployment requirements. To address these issues, this paper proposes CSFS-YOLOv8n, a lightweight model with high detection accuracy for remote sensing landslide detection based on the lightweight YOLOv8n network. First, the SCSA attention mechanism is introduced to enhance the network’s ability to perceive weak landslide features and effectively suppress background noise interference in complex terrain. Second, a synergistic optimization of Focal Loss and SIoU loss is adopted to alleviate sample class imbalance while improving the boundary localization accuracy of landslide targets. Furthermore, the lightweight SCConv convolutional module is embedded to strengthen multi-scale feature fusion, and the AdamW optimization strategy is used to further improve convergence stability and generalization capability. Experimental results show that compared with the original YOLOv8n model, CSFS-YOLOv8n improves precision, recall, mAP@0.5, and mAP@0.5:0.95 by 2.2%, 4.5%, 3.7%, and 3.9%, respectively. Meanwhile, the parameter count increases by only 0.14% and the computational cost by only 2.47%, achieving a significant improvement in detection accuracy while maintaining real-time inference capability. The results indicate that the proposed model has strong anti-interference ability and scene adaptability in complex plateau and mountainous remote sensing scenarios, and can provide efficient and reliable technical support for intelligent landslide disaster identification, hazard investigation, and disaster prevention and mitigation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LandslidesRemote Sensing TechnologyModels, TheoreticalDetection AlgorithmsAlgorithms

Autor:innen und Institutionen

  • College of Engineering, Xizang University, Lhasa, Xizang Autonomous Region, China.
  • Joint Laboratory of Plateau Surface Environmental Remote Sensing Monitoring, Lhasa, Xizang Autonomous Region, China.
  • Xizang Autonomous Region Key Laboratory of Satellite Remote Sensing and Applications, Lhasa, Xizang Autonomous Region, China.
  • Bomi Field Scientific Observation and Research Station for Geological Hazards, Ministry of Education, Nyingchi, Xizang Autonomous Region, China.
  • College of Ecology and Environment, Xizang University, Lhasa, Xizang Autonomous Region, China.
  • Geodynamics Laboratory, Xizang University, Lhasa, Xizang Autonomous Region, China.

ORCID-Profile: Runchi Wang, Hua Wu

Förderung

  • Science and Technology Program of Xizang Autonomous Region, China
  • 2026 Higher Education Reform and Development First-Class Discipline Construction Fund
  • Construction Project of Talent Innovation Team and Laboratory Platform of Xizang University

Zitieren

APA

Wang, R., Zhu, K., Wu, H., Zhou, J., Chen, X., Kong, X., Wang, H., Li, M., Yang, K., Zhou, Y., Lu, J., Tian, C., Wang, K., & He, W. (2026). CSFS-YOLOv8n: A complex terrain landslide detection model synergistically enhanced by SCConv and SCSA. PLOS One, 21(11), e0361878. https://doi.org/10.1371/journal.pone.0361878

Vancouver

Wang R, Zhu K, Wu H, Zhou J, Chen X, Kong X, et al. CSFS-YOLOv8n: A complex terrain landslide detection model synergistically enhanced by SCConv and SCSA. PLOS One. 2026;21(11):e0361878. doi:10.1371/journal.pone.0361878

BibTeX
@article{Wang2026,
  author = {Wang, Runchi and Zhu, Kangcheng and Wu, Hua and Zhou, Jianwei and Chen, Xingwang and Kong, Xiangyun and Wang, Haonan and Li, Mengke and Yang, Kexin and Zhou, Yongqing and Lu, Jiayi and Tian, Chao and Wang, Ke and He, Wenjie},
  title = {CSFS-YOLOv8n: A complex terrain landslide detection model synergistically enhanced by SCConv and SCSA},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0361878},
  doi = {10.1371/journal.pone.0361878}
}
Kostenlos starten →