What question did this study set out to answer?

This research aims to improve the detection and analysis of cracks and water leakage in tunnel linings.

August 13, 2026PLoS ONEOpen Access

Semantic segmentation and quantitative analysis of tunnel cracks and water leakage using a TransUNet framework

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved defect detection in tunnels, suggesting a robust framework for maintenance.

This research aims to improve the detection and analysis of cracks and water leakage in tunnel linings.
Developed an end-to-end semantic segmentation framework based on TransUNet.
Utilized a comprehensive dataset from public benchmarks and real-world images.
Evaluated against models like U-Net and DeepLabv3+.
Achieved an IoU of 71.57% for crack segmentation and Precision of 91.51% for water leakage.
Maintained geometric error for length and area measurements within 5%.
Achieved inference latency under 200 ms.

Li et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

August 13, 2026PLoS ONEOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved defect detection in tunnels, suggesting a robust framework for maintenance.

This research aims to improve the detection and analysis of cracks and water leakage in tunnel linings.
Developed an end-to-end semantic segmentation framework based on TransUNet.
Utilized a comprehensive dataset from public benchmarks and real-world images.
Evaluated against models like U-Net and DeepLabv3+.
Achieved an IoU of 71.57% for crack segmentation and Precision of 91.51% for water leakage.
Maintained geometric error for length and area measurements within 5%.
Achieved inference latency under 200 ms.

Li et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark