AB-SAM: A SAM-Based Asymmetric Boundary-Aware Model for the Semantic Segmentation of Small and Medium-Sized Landslides
Geomatics · 20.08.2026 · 6 (4) · 92
DOI: 10.3390/geomatics6040092 ↗Kurz gefasst
Fachartikel in der Zeitschrift Geomatics, online erschienen am 20.08.2026. Verfasst von Jiting Tang und 9 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Research Project, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Small- and medium-sized landslides frequently occur in clusters and exhibit fragmented morphologies, irregular boundaries, and spectral characteristics similar to surrounding roads, bare soil, and sparsely vegetated surfaces, making their automated extraction from remote sensing imagery challenging. Although the Segment Anything Model (SAM) provides strong general-purpose segmentation capabilities, its direct application to landslide mapping is limited by the geoscience domain gap and its dependence on external prompts. This study proposes the Asymmetric Boundary-aware Segment Anything Model (AB-SAM), a parameter-efficient adaptation of SAM for automated landslide semantic segmentation. AB-SAM integrates three task-specific components. First, the offline Multi-Feature Variation-Guided Prompting (MF-VGP) module generates cached auxiliary bounding boxes from registered pre- and post-event images without accessing ground-truth masks. Second, the Asymmetric Feature Augmentation (AFA) strategy combines geometric perturbation, CutMix, and asymmetric dual-branch supervision, in which a Hint-free branch serves as the primary optimization pathway and a lower-weight box-guided branch provides auxiliary spatial supervision. Third, the Boundary-Aware Morphological Prompting (BAMP) module injects trainable boundary-aware morphological information into the largely frozen SAM image encoder. During validation, testing, and application, only the Hint-free branch is retained, enabling inference using post-event imagery without external point, box, or mask prompts. On the fixed, spatially disjoint Zixing test set, AB-SAM achieved an overall accuracy of 96.171%, a precision of 68.149%, a recall of 60.011%, an F1-score of 63.822%, a landslide-class Intersection over Union of 46.867%, and a mean Intersection over Union of 71.452%. Repeated experiments with three random seeds showed low run-to-run variation. Direct evaluation without retraining on the Hokkaido Iburi-Tobu dataset yielded a mean Intersection over Union of 66.136%, providing evidence of cross-region and cross-event transferability. These results demonstrate that AB-SAM provides a practical parameter-efficient framework for automated, hint-free landslide segmentation, although further evaluation across additional regions, sensors, and landslide-size distributions remains necessary.
Förderung
- Yunnan Research Project
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- Henan Polytechnic University
Zitieren
APA
Tang, J., Liang, Z., Guo, S., Tong, B., Chen, J., Sun, G., Liu, J., Wang, C., Li, D., & Zhou, X. (2026). AB-SAM: A SAM-Based Asymmetric Boundary-Aware Model for the Semantic Segmentation of Small and Medium-Sized Landslides. Geomatics, 6(4), 92. https://doi.org/10.3390/geomatics6040092
Vancouver
Tang J, Liang Z, Guo S, Tong B, Chen J, Sun G, et al. AB-SAM: A SAM-Based Asymmetric Boundary-Aware Model for the Semantic Segmentation of Small and Medium-Sized Landslides. Geomatics. 2026;6(4):92. doi:10.3390/geomatics6040092
BibTeX
@article{Tang2026,
author = {Tang, Jiting and Liang, Zhiwei and Guo, Suli and Tong, Bin and Chen, Jun’an and Sun, Guoliang and Liu, Jiaxing and Wang, Can and Li, Dong and Zhou, Xin},
title = {AB-SAM: A SAM-Based Asymmetric Boundary-Aware Model for the Semantic Segmentation of Small and Medium-Sized Landslides},
journal = {Geomatics},
year = {2026},
volume = {6},
number = {4},
pages = {92},
doi = {10.3390/geomatics6040092}
}
EUVIMED