Panoramic Image Stitching for Arbitrarily Shaped Tunnel Lining Inspection

Abstract This article presents a low‐cost panoramic image stitching system for tunnel lining inspection. The system can produce a high‐quality layout panorama of the target lining using photographs taken freely in a tunnel with a hand‐held camera and the tunnel design information as inputs. The three‐dimensional (3D) freeform shape corresponding to the tunnel design geometry is used as the warping surface for photograph rectification. A newly designed random sample consensus algorithm is used to estimate the freeform tunnel shape from the 3D reconstructed point cloud, which can perform the registration between point sets with different sizes. These processes can make full use of the geometry information of a real tunnel and the reconstructed scene; thus, the photographs can be precisely rectified, and a planar motion stitching can composite them together. Two field applications demonstrate that the system can create a tunnel layout panorama with sufficient accuracy in tunnel lining inspection and that it is applicable to noncircular‐shaped tunnels.