EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Detection and Segmentation of Cracks in Urban Underground Structures Based on YOLOv8-SAM2

Chao Geng, Yajie Wang, Quanming Li, Zhentao Li, Xianfeng Shi, Botao Fu, Wei Li, Cheng Chen, Hong Zhang, Yukai Wang, Zhijie Duan

Buildings · 12.08.2026 · 16 (16) · 3211

DOI: 10.3390/buildings16163211 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 12.08.2026. Verfasst von Chao Geng und 10 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Outstanding Young Scientist Program Project of Beijing Universities, Key Science and Technology Program of the Ministry of Emergency Management of China, North China University of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the expansion of urban underground space, the structural safety of underground infrastructure has become increasingly critical. The urban underground utility tunnel is a typical deeply buried lifeline project. Its internal environment is humid and confined, and the structure is subjected to long-term heavy loads and earth pressure. Under such conditions, micro-cracks readily propagate into leakage channels and eventually cause structural damage. However, the slender morphology, low contrast, and complex background of cracks make it difficult for traditional inspection methods and general-purpose models to achieve reliable identification and accurate segmentation. This study proposes a two-stage framework that combines YOLOv8 with SAM2 and incorporates a coordinate attention module for high-quality crack segmentation. For image processing, a topology-aware post-processing strategy is introduced, together with a scoring function based on crack morphological features and a post-processing constraint mechanism, to ensure crack continuity and geometric consistency and to mitigate the over-segmentation that may occur during segmentation. YOLOv8-SAM2 achieves 85.2%, 90.5%, 77.2%, and 71.6% in mIoU, mDice, Recall, and Precision, respectively. Compared with YOLOv8-seg, mIoU and Precision are improved by 46.3 and 17.2 percentage points, respectively; compared with the baseline SAM2, mIoU and Precision are improved by 23.0 and 16.9 percentage points, respectively. In summary, on the self-built underground utility tunnel crack dataset, the proposed model significantly outperforms standalone YOLOv8 segmentation and the direct application of SAM2 in terms of intersection-over-union and precision, demonstrating its high-quality segmentation capability.

Förderung

  • Outstanding Young Scientist Program Project of Beijing Universities
  • Key Science and Technology Program of the Ministry of Emergency Management of China
  • North China University of Technology

Zitieren

APA

Geng, C., Wang, Y., Li, Q., Li, Z., Shi, X., Fu, B., Li, W., Chen, C., Zhang, H., Wang, Y., & Duan, Z. (2026). Automated Detection and Segmentation of Cracks in Urban Underground Structures Based on YOLOv8-SAM2. Buildings, 16(16), 3211. https://doi.org/10.3390/buildings16163211

Vancouver

Geng C, Wang Y, Li Q, Li Z, Shi X, Fu B, et al. Automated Detection and Segmentation of Cracks in Urban Underground Structures Based on YOLOv8-SAM2. Buildings. 2026;16(16):3211. doi:10.3390/buildings16163211

BibTeX
@article{Geng2026,
  author = {Geng, Chao and Wang, Yajie and Li, Quanming and Li, Zhentao and Shi, Xianfeng and Fu, Botao and Li, Wei and Chen, Cheng and Zhang, Hong and Wang, Yukai and Duan, Zhijie},
  title = {Automated Detection and Segmentation of Cracks in Urban Underground Structures Based on YOLOv8-SAM2},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {16},
  pages = {3211},
  doi = {10.3390/buildings16163211}
}
Kostenlos starten →