Distortion-Free Image Mosaicing for Tunnel Inspection Based on Robust Cylindrical Surface Estimation through Structure from Motion

Abstract

Visual inspection, although labor-intensive, costly, and inaccurate, is a common practice used in the condition assessment of underground tunnels to ensure safety and serviceability. This paper presents a system that- can construct a mosaic image of a tunnel surface with little distortion, allowing a large area of tunnels to be visualized, and enabling tunnel inspection to be carried out off-line. The system removes distortion by a robust estimation of a tunnel surface through structure from motion (SFM), which can create a 3D point cloud of the tunnel surface from uncalibrated images. SFM enables the mosaicing system to cope with images with a general camera motion, in contrast to standard mosaicing software that can cope only with a strict camera motion. The estimation of the tunnel surface is further improved by support vector machine (SVM), which is used to remove noise in the point cloud. Some curvatures are observed in the mosaics when an inaccurate surface is used for mosaicing, whereas the mosaics from a surface estimated using the proposed method are almost distortion-free, preserving all physical attributes, e.g., line parallelism and straightness, which is important for tunnel inspection.