Tunnel crack assessment using simultaneous localization and mapping (SLAM) and deep learning segmentation

Artificial intelligence algorithms and multi-sensor technologies are advancing tunnel crack detection. However, image-based detection methods fail to account for tunnel section curvature, limiting their ability to represent the spatial geometry of cracks. To address these problems, this paper presents a tunnel crack assessment method combining simultaneous localization and mapping (SLAM) with deep learning-based segmentation. The SLAM algorithm reconstructs the tunnel point cloud map, and a two-dimensional (2D) convex hull point cloud unfolding with a cloth simulation filter (CSF) algorithm is applied for denoising. A deep learning segmentation model is used to segment the tunnel cracks. The cracks are projected into a three-dimensional (3D) point cloud map, and the crack length and spatial location are calculated. Field tests demonstrate that the method reduces tunnel reconstruction time to 27 s (a 99 % time saving), with a maximum radius error of 0.03 m and accurate 3D crack projections. •LiDAR-IMU SLAM is utilized for tunnel inspections, significantly enhancing efficiency and accuracy.•A tunnel section denoising algorithm based on point cloud unfolding and the cloth simulation filter method is proposed.•A deep learning segmentation model is employed for tunnel crack extraction, enhancing bothefficiency and accuracy.•The location and extent of tunnel cracks are recovered by projecting 2D images onto a 3D point cloud.•The performance of the proposed framework is validated through tests conducted in an in-service tunnel.