EUVIMEDEUVIMED entdecken
Crossref

CulvertVision: Advancing AI-Augmented Inspection and Condition Assessment of Culverts

Rohan Singh Wilkho, Xinke Huang, Venkat Pitta, Afreen Ahmed, Nasir G. Gharaibeh

Journal of Infrastructure Systems · 01.12.2026 · 32 (4)

DOI: 10.1061/jitse4.iseng-2984 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Infrastructure Systems, erschienen am 01.12.2026. Verfasst von Rohan Singh Wilkho und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Culvert inspection remains a persistent bottleneck in infrastructure asset management, constrained by labor-intensive manual inspection, resource limitations, and varying reporting across varied environments. This study presents CulvertVision, a deep learning framework for automated defect detection in culvert inspection videos designed to align with the Pipeline Assessment and Certification Program (PACP) standards. Utilizing a ResNet-101 architecture fine-tuned via transfer learning from sewer infrastructure benchmarks, the system processes untrimmed inspection videos to generate temporally stable classifications for four categories: corrosion, settled deposits, joint offset, and normal. Evaluation across 6,600 annotated frames under shared-video, noise-augmented, and video-disjoint configurations reveals that while noise augmentation improves robustness in controlled settings ( F 1 - scores > 0.88 ), a significant generalization gap emerges in out-of-distribution scenarios, with joint offset performance declining to an F 1 -score of 0.55. Beyond accuracy, CulvertVision’s throughput analysis demonstrates high operational efficiency, offering substantial time savings compared to manual human review. By automating PACP-aligned defect detection, the framework enables agencies to streamline inspection workflows and support data-driven capital and maintenance planning. While current work explores dataset expansion through generative augmentation to address training limitations, CulvertVision represents a scalable prototype for artificial intelligence (AI)–augmented infrastructure inspection and broader field deployment.

Zitieren

APA

Wilkho, R. S., Huang, X., Pitta, V., Ahmed, A., & Gharaibeh, N. G. (2026). CulvertVision: Advancing AI-Augmented Inspection and Condition Assessment of Culverts. Journal of Infrastructure Systems, 32(4). https://doi.org/10.1061/jitse4.iseng-2984

Vancouver

Wilkho RS, Huang X, Pitta V, Ahmed A, Gharaibeh NG. CulvertVision: Advancing AI-Augmented Inspection and Condition Assessment of Culverts. Journal of Infrastructure Systems. 2026;32(4). doi:10.1061/jitse4.iseng-2984

BibTeX
@article{Wilkho2026,
  author = {Wilkho, Rohan Singh and Huang, Xinke and Pitta, Venkat and Ahmed, Afreen and Gharaibeh, Nasir G.},
  title = {CulvertVision: Advancing AI-Augmented Inspection and Condition Assessment of Culverts},
  journal = {Journal of Infrastructure Systems},
  year = {2026},
  volume = {32},
  number = {4},
  doi = {10.1061/jitse4.iseng-2984}
}
Kostenlos starten →