Tunnel SAM adapter: Adapting segment anything model for tunnel water leakage inspection
Junxin Chen, Xiaojie Yu, Shichang Liu, Tao Chen, Wei Wang, Gwanggil Jeon, Ben‐Guo He
Abstract
Water leakage inspection in the tunnels is a critical engineering job that has attracted increasing concerns. Leakage area detection via manual inspection techniques is time-consuming and might produce unreliable findings, so that automated techniques should be created to increase reliability and efficiency. Pre-trained foundational segmentation models for large datasets have attracted great interests recently. This paper proposes a novel SAM-based network for accurate automated water leakage inspection. The contributions of this paper include the efficient adaptation of the SAM (Segment Anything Model) for shield tunnel water leakage segmentation and the demonstration of the application effect by data experiments. Tunnel SAM Adapter has satisfactory performance, achieving 76.2 % mIoU and 77.5 % Dice. Experimental results demonstrate that our approach has advantages over peer studies and guarantees the integrity and safety of these vital assets while streamlining tunnel maintenance.